eval/tools/XVerseBench_multi.json

[
    {
        "index": 0,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is riding a motorcycle.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/05_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/00_motorcycle.jpg",
                        "caption": "a motorcycle"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "motorcycle",
                        "motorcycle"
                    ]
                ]
            }
        ]
    },
    {
        "index": 1,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An anime Spider-Man is playing with a boy.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/00_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/71_anime Spider-Man.jpg",
                        "caption": "an anime Spider-Man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "anime Spider-Man",
                        "anime Spider-Man"
                    ]
                ]
            }
        ]
    },
    {
        "index": 2,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man stands beside a vintage van.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/21_vintage van.jpg",
                        "caption": "a vintage van"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "vintage van",
                        "vintage van"
                    ]
                ]
            }
        ]
    },
    {
        "index": 3,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An old man meets a pixelated warrior.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/67_pixelated warrior.jpg",
                        "caption": "a pixelated warrior"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "old man",
                        "old man"
                    ],
                    [
                        1,
                        "pixelated warrior",
                        "pixelated warrior"
                    ]
                ]
            }
        ]
    },
    {
        "index": 4,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman stands in front of a hut.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/13_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/42_hut.jpg",
                        "caption": "a hut"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "hut",
                        "hut"
                    ]
                ]
            }
        ]
    },
    {
        "index": 5,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is playing a snare drum.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/60_snare drum.jpg",
                        "caption": "a snare drum"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "snare drum",
                        "snare drum"
                    ]
                ]
            }
        ]
    },
    {
        "index": 6,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is holding a leather handbag.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/07_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/57_leather handbag.jpg",
                        "caption": "a leather handbag"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "leather handbag",
                        "leather handbag"
                    ]
                ]
            }
        ]
    },
    {
        "index": 7,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is using a hair dryer.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/26_hair dryer.jpg",
                        "caption": "a hair dryer"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "hair dryer",
                        "hair dryer"
                    ]
                ]
            }
        ]
    },
    {
        "index": 8,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is sitting on a motorcycle.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/15_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/00_motorcycle.jpg",
                        "caption": "a motorcycle"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "motorcycle",
                        "motorcycle"
                    ]
                ]
            }
        ]
    },
    {
        "index": 9,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is holding a pineapple.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/05_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/43_pineapple.jpg",
                        "caption": "a pineapple"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "pineapple",
                        "pineapple"
                    ]
                ]
            }
        ]
    },
    {
        "index": 10,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is looking at a clock.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/56_clock.jpg",
                        "caption": "a clock"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "clock",
                        "clock"
                    ]
                ]
            }
        ]
    },
    {
        "index": 11,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman and an anime man standing side by side",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/73_anime man.jpg",
                        "caption": "an anime man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "anime man",
                        "anime man"
                    ]
                ]
            }
        ]
    },
    {
        "index": 12,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is holding a vase.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/09_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/30_vase.jpg",
                        "caption": "a vase"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "vase",
                        "vase"
                    ]
                ]
            }
        ]
    },
    {
        "index": 13,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is holding a vintage camera.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/06_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/23_vintage camera.jpg",
                        "caption": "a vintage camera"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "vintage camera",
                        "vintage camera"
                    ]
                ]
            }
        ]
    },
    {
        "index": 14,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is standing beside a classical bust.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/09_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/25_classical bust.jpg",
                        "caption": "a classical bust"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "classical bust",
                        "classical bust"
                    ]
                ]
            }
        ]
    },
    {
        "index": 15,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A curious boy discovered a ring in the forest.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/16_ring.jpg",
                        "caption": "a ring"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "ring",
                        "ring"
                    ]
                ]
            }
        ]
    },
    {
        "index": 16,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man stands beside a steam locomotive.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/19_steam locomotive.jpg",
                        "caption": "a steam locomotive"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "steam locomotive",
                        "steam locomotive"
                    ]
                ]
            }
        ]
    },
    {
        "index": 17,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man holding a Poke Ball.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/54_Poke Ball.jpg",
                        "caption": "a Poke Ball"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "Poke Ball",
                        "Poke Ball"
                    ]
                ]
            }
        ]
    },
    {
        "index": 18,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man standing among cherry blossoms.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/06_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/03_cherry blossoms.jpg",
                        "caption": "a cherry blossoms"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "cherry blossoms",
                        "cherry blossoms"
                    ]
                ]
            }
        ]
    },
    {
        "index": 19,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is standing next to a cactus.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/53_cactus.jpg",
                        "caption": "a cactus"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "cactus",
                        "cactus"
                    ]
                ]
            }
        ]
    },
    {
        "index": 20,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is standing beside another man.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/05_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/11_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ]
                ]
            }
        ]
    },
    {
        "index": 21,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is standing beside a man.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/07_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ]
                ]
            }
        ]
    },
    {
        "index": 22,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a boy are standing side by side.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "boy",
                        "boy"
                    ]
                ]
            }
        ]
    },
    {
        "index": 23,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman and a girl standing side by side in a park.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/09_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/19_girl.jpg",
                        "caption": "a girl"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "girl",
                        "girl"
                    ]
                ]
            }
        ]
    },
    {
        "index": 24,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a woman standing side by side in a park.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/01_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 25,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An old man and a man standing together on the street.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/05_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "old man",
                        "old man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ]
                ]
            }
        ]
    },
    {
        "index": 26,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman and a girl standing together in a park.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/15_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/19_girl.jpg",
                        "caption": "a girl"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "girl",
                        "girl"
                    ]
                ]
            }
        ]
    },
    {
        "index": 27,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a woman standing side by side.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/07_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/13_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 28,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and another man standing side by side on a street, having a conversation.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/11_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ]
                ]
            }
        ]
    },
    {
        "index": 29,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a woman standing together in a park.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/07_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/15_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 30,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A little girl is walking hand-in-hand with a woman on a sunny street.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/03_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "little girl",
                        "little girl"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 31,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a woman standing together on a sunny street.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/03_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 32,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and another man standing side by side, having a conversation.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/11_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ]
                ]
            }
        ]
    },
    {
        "index": 33,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman and a man standing side by side in a park.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/06_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ]
                ]
            }
        ]
    },
    {
        "index": 34,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A little girl is standing beside a man.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "little girl",
                        "little girl"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ]
                ]
            }
        ]
    },
    {
        "index": 35,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A girl is standing beside a woman, having a friendly chat.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/19_girl.jpg",
                        "caption": "a girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/09_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "girl",
                        "girl"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 36,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a woman standing together",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/03_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 37,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is standing beside another man.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/05_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/01_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ]
                ]
            }
        ]
    },
    {
        "index": 38,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A little girl is standing beside a man.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "little girl",
                        "little girl"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ]
                ]
            }
        ]
    },
    {
        "index": 39,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a woman standing side by side in a park.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/06_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 40,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is swimming with a sea turtle in the ocean.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/18_sea turtle.jpg",
                        "caption": "a sea turtle"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "sea turtle",
                        "sea turtle"
                    ]
                ]
            }
        ]
    },
    {
        "index": 41,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is playing with a dog.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/00_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/12_dog.jpg",
                        "caption": "a dog"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "dog",
                        "dog"
                    ]
                ]
            }
        ]
    },
    {
        "index": 42,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is standing in the forest, facing a wolf.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/27_wolf.jpg",
                        "caption": "a wolf"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "wolf",
                        "wolf"
                    ]
                ]
            }
        ]
    },
    {
        "index": 43,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is playing with a hamster.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/20_hamster.jpg",
                        "caption": "a hamster"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "hamster",
                        "hamster"
                    ]
                ]
            }
        ]
    },
    {
        "index": 44,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is standing beside a rooster.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/03_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/09_rooster.jpg",
                        "caption": "a rooster"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "rooster",
                        "rooster"
                    ]
                ]
            }
        ]
    },
    {
        "index": 45,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man standing face-to-face with a lion in the wild.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/30_lion.jpg",
                        "caption": "a lion"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "lion",
                        "lion"
                    ]
                ]
            }
        ]
    },
    {
        "index": 46,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is standing in front of a lion.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/30_lion.jpg",
                        "caption": "a lion"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "lion",
                        "lion"
                    ]
                ]
            }
        ]
    },
    {
        "index": 47,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is riding a horse.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/07_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/03_horse.jpg",
                        "caption": "a horse"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "horse",
                        "horse"
                    ]
                ]
            }
        ]
    },
    {
        "index": 48,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is observing a grasshopper.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/29_grasshopper.jpg",
                        "caption": "a grasshopper"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "grasshopper",
                        "grasshopper"
                    ]
                ]
            }
        ]
    },
    {
        "index": 49,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is looking at a frog.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/06_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/17_frog.jpg",
                        "caption": "a frog"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "frog",
                        "frog"
                    ]
                ]
            }
        ]
    },
    {
        "index": 50,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is playing with a corgi.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/00_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/22_corgi.jpg",
                        "caption": "a corgi"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "corgi",
                        "corgi"
                    ]
                ]
            }
        ]
    },
    {
        "index": 51,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is walking a corgi on a street.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/15_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/22_corgi.jpg",
                        "caption": "a corgi"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "corgi",
                        "corgi"
                    ]
                ]
            }
        ]
    },
    {
        "index": 52,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is holding a Sphynx cat.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/15_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/25_Sphynx cat.jpg",
                        "caption": "a Sphynx cat"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "Sphynx cat",
                        "Sphynx cat"
                    ]
                ]
            }
        ]
    },
    {
        "index": 53,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is looking at a frog in a small pond.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/17_frog.jpg",
                        "caption": "a frog"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "frog",
                        "frog"
                    ]
                ]
            }
        ]
    },
    {
        "index": 54,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is walking with a dog on the street.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/05_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/07_dog.jpg",
                        "caption": "a dog"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "dog",
                        "dog"
                    ]
                ]
            }
        ]
    },
    {
        "index": 55,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is looking at a crab on the beach.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/04_crab.jpg",
                        "caption": "a crab"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "crab",
                        "crab"
                    ]
                ]
            }
        ]
    },
    {
        "index": 56,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is standing beside a flamingo.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/07_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/28_flamingo.jpg",
                        "caption": "a flamingo"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "flamingo",
                        "flamingo"
                    ]
                ]
            }
        ]
    },
    {
        "index": 57,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is interacting with a dolphin.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/13_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/39_dolphin.jpg",
                        "caption": "a dolphin"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "dolphin",
                        "dolphin"
                    ]
                ]
            }
        ]
    },
    {
        "index": 58,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A little girl is playing with a puppy.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/42_puppy.jpg",
                        "caption": "a puppy"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "little girl",
                        "little girl"
                    ],
                    [
                        1,
                        "puppy",
                        "puppy"
                    ]
                ]
            }
        ]
    },
    {
        "index": 59,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is swimming with a dolphin in the sea.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/39_dolphin.jpg",
                        "caption": "a dolphin"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "dolphin",
                        "dolphin"
                    ]
                ]
            }
        ]
    },
    {
        "index": 60,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An elephant is carrying a backpack on its back.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/38_elephant.jpg",
                        "caption": "an elephant"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/28_backpack.jpg",
                        "caption": "a backpack"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "elephant",
                        "elephant"
                    ],
                    [
                        1,
                        "backpack",
                        "backpack"
                    ]
                ]
            }
        ]
    },
    {
        "index": 61,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A wolf is standing beside a teapot.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/27_wolf.jpg",
                        "caption": "a wolf"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/52_teapot.jpg",
                        "caption": "a teapot"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "wolf",
                        "wolf"
                    ],
                    [
                        1,
                        "teapot",
                        "teapot"
                    ]
                ]
            }
        ]
    },
    {
        "index": 62,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A deer standing beside a vintage van.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/31_deer.jpg",
                        "caption": "a deer"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/21_vintage van.jpg",
                        "caption": "a vintage van"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "deer",
                        "deer"
                    ],
                    [
                        1,
                        "vintage van",
                        "vintage van"
                    ]
                ]
            }
        ]
    },
    {
        "index": 63,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A cotton-top tamarin is sitting under a street lamp.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/26_cotton-top tamarin.jpg",
                        "caption": "a cotton-top tamarin"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/15_street lamp.jpg",
                        "caption": "a street lamp"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "cotton-top tamarin",
                        "cotton-top tamarin"
                    ],
                    [
                        1,
                        "street lamp",
                        "street lamp"
                    ]
                ]
            }
        ]
    },
    {
        "index": 64,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "In the moonlit jungle, a white tiger prowls silently, its eye catching the glint of an old, abandoned watch nearby.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/40_white tiger.jpg",
                        "caption": "a white tiger"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/12_watch.jpg",
                        "caption": "a watch"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "white tiger",
                        "white tiger"
                    ],
                    [
                        1,
                        "watch",
                        "watch"
                    ]
                ]
            }
        ]
    },
    {
        "index": 65,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A Corgi dog stands beside an anime samurai.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/32_Corgi dog.jpg",
                        "caption": "a Corgi dog"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/69_anime samurai.jpg",
                        "caption": "an anime samurai"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Corgi dog",
                        "Corgi dog"
                    ],
                    [
                        1,
                        "anime samurai",
                        "anime samurai"
                    ]
                ]
            }
        ]
    },
    {
        "index": 66,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A grasshopper is standing next to a Poke Ball.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/29_grasshopper.jpg",
                        "caption": "a grasshopper"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/54_Poke Ball.jpg",
                        "caption": "a Poke Ball"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "grasshopper",
                        "grasshopper"
                    ],
                    [
                        1,
                        "Poke Ball",
                        "Poke Ball"
                    ]
                ]
            }
        ]
    },
    {
        "index": 67,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A penguin is on a flamingo float in the water.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/05_penguin.jpg",
                        "caption": "a penguin"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/10_flamingo float.jpg",
                        "caption": "a flamingo float"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "penguin",
                        "penguin"
                    ],
                    [
                        1,
                        "flamingo float",
                        "flamingo float"
                    ]
                ]
            }
        ]
    },
    {
        "index": 68,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A fox is standing under a street lamp.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/10_fox.jpg",
                        "caption": "a fox"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/15_street lamp.jpg",
                        "caption": "a street lamp"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "fox",
                        "fox"
                    ],
                    [
                        1,
                        "street lamp",
                        "street lamp"
                    ]
                ]
            }
        ]
    },
    {
        "index": 69,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A cotton-top tamarin is curiously inspecting an Eevee figurine.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/26_cotton-top tamarin.jpg",
                        "caption": "a cotton-top tamarin"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/59_Eevee figurine.jpg",
                        "caption": "an Eevee figurine"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "cotton-top tamarin",
                        "cotton-top tamarin"
                    ],
                    [
                        1,
                        "Eevee figurine",
                        "Eevee figurine"
                    ]
                ]
            }
        ]
    },
    {
        "index": 70,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A llama wearing a hat",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/24_llama.jpg",
                        "caption": "a llama"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/01_hat.jpg",
                        "caption": "a hat"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "llama",
                        "llama"
                    ],
                    [
                        1,
                        "hat",
                        "hat"
                    ]
                ]
            }
        ]
    },
    {
        "index": 71,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A cat is lying beside a teddy bear.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/44_cat.jpg",
                        "caption": "a cat"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/13_teddy bear.jpg",
                        "caption": "a teddy bear"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "cat",
                        "cat"
                    ],
                    [
                        1,
                        "teddy bear",
                        "teddy bear"
                    ]
                ]
            }
        ]
    },
    {
        "index": 72,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A cat sitting in front of a yellow taxi.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/44_cat.jpg",
                        "caption": "a cat"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/44_yellow taxi.jpg",
                        "caption": "a yellow taxi"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "cat",
                        "cat"
                    ],
                    [
                        1,
                        "yellow taxi",
                        "yellow taxi"
                    ]
                ]
            }
        ]
    },
    {
        "index": 73,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A cat is being dried by a hair dryer.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/44_cat.jpg",
                        "caption": "a cat"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/26_hair dryer.jpg",
                        "caption": "a hair dryer"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "cat",
                        "cat"
                    ],
                    [
                        1,
                        "hair dryer",
                        "hair dryer"
                    ]
                ]
            }
        ]
    },
    {
        "index": 74,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A toucan is sitting in front of a vintage television.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/37_toucan.jpg",
                        "caption": "a toucan"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/49_vintage television.jpg",
                        "caption": "a vintage television"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "toucan",
                        "toucan"
                    ],
                    [
                        1,
                        "vintage television",
                        "vintage television"
                    ]
                ]
            }
        ]
    },
    {
        "index": 75,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A panda is using a hair dryer.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/33_panda.jpg",
                        "caption": "a panda"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/26_hair dryer.jpg",
                        "caption": "a hair dryer"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "panda",
                        "panda"
                    ],
                    [
                        1,
                        "hair dryer",
                        "hair dryer"
                    ]
                ]
            }
        ]
    },
    {
        "index": 76,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A lizard is sitting on a motorcycle.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/36_lizard.jpg",
                        "caption": "a lizard"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/00_motorcycle.jpg",
                        "caption": "a motorcycle"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "lizard",
                        "lizard"
                    ],
                    [
                        1,
                        "motorcycle",
                        "motorcycle"
                    ]
                ]
            }
        ]
    },
    {
        "index": 77,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A robin perches on a leather handbag.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/19_robin.jpg",
                        "caption": "a robin"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/57_leather handbag.jpg",
                        "caption": "a leather handbag"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "robin",
                        "robin"
                    ],
                    [
                        1,
                        "leather handbag",
                        "leather handbag"
                    ]
                ]
            }
        ]
    },
    {
        "index": 78,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A cat is sitting beside a basketball shoe.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/34_cat.jpg",
                        "caption": "a cat"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/07_basketball shoe.jpg",
                        "caption": "a basketball shoe"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "cat",
                        "cat"
                    ],
                    [
                        1,
                        "basketball shoe",
                        "basketball shoe"
                    ]
                ]
            }
        ]
    },
    {
        "index": 79,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A jellyfish floating near a tree on an otherworldly beach.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/16_jellyfish.jpg",
                        "caption": "a jellyfish"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/08_tree.jpg",
                        "caption": "a tree"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "jellyfish",
                        "jellyfish"
                    ],
                    [
                        1,
                        "tree",
                        "tree"
                    ]
                ]
            }
        ]
    },
    {
        "index": 80,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "In a dense jungle, a cotton-top tamarin curiously eyes a resting wolf, intrigued by the unfamiliar presence amid foliage.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/26_cotton-top tamarin.jpg",
                        "caption": "a cotton-top tamarin"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/27_wolf.jpg",
                        "caption": "a wolf"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "cotton-top tamarin",
                        "cotton-top tamarin"
                    ],
                    [
                        1,
                        "wolf",
                        "wolf"
                    ]
                ]
            }
        ]
    },
    {
        "index": 81,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A deer stands in a forest clearing while a robin perches on a nearby branch.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/31_deer.jpg",
                        "caption": "a deer"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/19_robin.jpg",
                        "caption": "a robin"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "deer",
                        "deer"
                    ],
                    [
                        1,
                        "robin",
                        "robin"
                    ]
                ]
            }
        ]
    },
    {
        "index": 82,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A raccoon and a rooster are standing in a rural yard.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/08_raccoon.jpg",
                        "caption": "a raccoon"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/09_rooster.jpg",
                        "caption": "a rooster"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "raccoon",
                        "raccoon"
                    ],
                    [
                        1,
                        "rooster",
                        "rooster"
                    ]
                ]
            }
        ]
    },
    {
        "index": 83,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A dolphin and a penguin swimming in the ocean together.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/39_dolphin.jpg",
                        "caption": "a dolphin"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/05_penguin.jpg",
                        "caption": "a penguin"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "dolphin",
                        "dolphin"
                    ],
                    [
                        1,
                        "penguin",
                        "penguin"
                    ]
                ]
            }
        ]
    },
    {
        "index": 84,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A playful panda and a curious cat frolic in a sunlit bamboo forest, surrounded by vibrant blossoms and fluttering butterflies.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/33_panda.jpg",
                        "caption": "a panda"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/34_cat.jpg",
                        "caption": "a cat"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "panda",
                        "panda"
                    ],
                    [
                        1,
                        "cat",
                        "cat"
                    ]
                ]
            }
        ]
    },
    {
        "index": 85,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A grasshopper is jumping on the grass while a tiger is lurking nearby in the grassland.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/29_grasshopper.jpg",
                        "caption": "a grasshopper"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/35_tiger.jpg",
                        "caption": "a tiger"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "grasshopper",
                        "grasshopper"
                    ],
                    [
                        1,
                        "tiger",
                        "tiger"
                    ]
                ]
            }
        ]
    },
    {
        "index": 86,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A grasshopper is hopping on the grass while a wolf is prowling nearby.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/29_grasshopper.jpg",
                        "caption": "a grasshopper"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/27_wolf.jpg",
                        "caption": "a wolf"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "grasshopper",
                        "grasshopper"
                    ],
                    [
                        1,
                        "wolf",
                        "wolf"
                    ]
                ]
            }
        ]
    },
    {
        "index": 87,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A polar bear and a hamster in a snowy landscape.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/13_polar bear.jpg",
                        "caption": "a polar bear"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/20_hamster.jpg",
                        "caption": "a hamster"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "polar bear",
                        "polar bear"
                    ],
                    [
                        1,
                        "hamster",
                        "hamster"
                    ]
                ]
            }
        ]
    },
    {
        "index": 88,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A lion is lying under a tree while a robin is perched on a nearby branch.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/23_lion.jpg",
                        "caption": "a lion"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/19_robin.jpg",
                        "caption": "a robin"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "lion",
                        "lion"
                    ],
                    [
                        1,
                        "robin",
                        "robin"
                    ]
                ]
            }
        ]
    },
    {
        "index": 89,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A dog is chasing a butterfly in the garden.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/15_butterfly.jpg",
                        "caption": "a butterfly"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/07_dog.jpg",
                        "caption": "a dog"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "butterfly",
                        "butterfly"
                    ],
                    [
                        1,
                        "dog",
                        "dog"
                    ]
                ]
            }
        ]
    },
    {
        "index": 90,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A horse is standing near the seashore and looking at a crab on the beach.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/03_horse.jpg",
                        "caption": "a horse"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/04_crab.jpg",
                        "caption": "a crab"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "horse",
                        "horse"
                    ],
                    [
                        1,
                        "crab",
                        "crab"
                    ]
                ]
            }
        ]
    },
    {
        "index": 91,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A dog is looking up at an eagle soaring in the sky.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/07_dog.jpg",
                        "caption": "a dog"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/14_eagle.jpg",
                        "caption": "an eagle"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "dog",
                        "dog"
                    ],
                    [
                        1,
                        "eagle",
                        "eagle"
                    ]
                ]
            }
        ]
    },
    {
        "index": 92,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A heron is standing by a small pond in a forest, and a deer is drinking water at the edge of the pond.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/11_heron.jpg",
                        "caption": "a heron"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/31_deer.jpg",
                        "caption": "a deer"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "heron",
                        "heron"
                    ],
                    [
                        1,
                        "deer",
                        "deer"
                    ]
                ]
            }
        ]
    },
    {
        "index": 93,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A llama standing in a meadow with a robin flying nearby.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/24_llama.jpg",
                        "caption": "a llama"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/19_robin.jpg",
                        "caption": "a robin"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "llama",
                        "llama"
                    ],
                    [
                        1,
                        "robin",
                        "robin"
                    ]
                ]
            }
        ]
    },
    {
        "index": 94,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A French bulldog and a penguin standing side by side on an ice-floe under a sunny sky.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/43_French bulldog.jpg",
                        "caption": "a French bulldog"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/05_penguin.jpg",
                        "caption": "a penguin"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "French bulldog",
                        "French bulldog"
                    ],
                    [
                        1,
                        "penguin",
                        "penguin"
                    ]
                ]
            }
        ]
    },
    {
        "index": 95,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An eagle is soaring above the sea, and a shark is swimming in the water below.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/14_eagle.jpg",
                        "caption": "an eagle"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/06_shark.jpg",
                        "caption": "a shark"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "eagle",
                        "eagle"
                    ],
                    [
                        1,
                        "shark",
                        "shark"
                    ]
                ]
            }
        ]
    },
    {
        "index": 96,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A stork and a parrot are standing side by side on a branch.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/01_stork.jpg",
                        "caption": "a stork"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/41_parrot.jpg",
                        "caption": "a parrot"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "stork",
                        "stork"
                    ],
                    [
                        1,
                        "parrot",
                        "parrot"
                    ]
                ]
            }
        ]
    },
    {
        "index": 97,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A shark and an elephant co-existing in a fantasy underwater scene with the elephant floating gracefully among the shark.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/06_shark.jpg",
                        "caption": "a shark"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/38_elephant.jpg",
                        "caption": "an elephant"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "shark",
                        "shark"
                    ],
                    [
                        1,
                        "elephant",
                        "elephant"
                    ]
                ]
            }
        ]
    },
    {
        "index": 98,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A hamster is looking at a jellyfish floating in a fishbowl nearby.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/20_hamster.jpg",
                        "caption": "a hamster"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/16_jellyfish.jpg",
                        "caption": "a jellyfish"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "hamster",
                        "hamster"
                    ],
                    [
                        1,
                        "jellyfish",
                        "jellyfish"
                    ]
                ]
            }
        ]
    },
    {
        "index": 99,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A frog is floating on a small raft in the ocean, and a shark is swimming nearby.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/17_frog.jpg",
                        "caption": "a frog"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/06_shark.jpg",
                        "caption": "a shark"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "frog",
                        "frog"
                    ],
                    [
                        1,
                        "shark",
                        "shark"
                    ]
                ]
            }
        ]
    },
    {
        "index": 100,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A piggy bank sits beside a Rolls-Royce hood ornament on a polished table.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/31_piggy bank.jpg",
                        "caption": "a piggy bank"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/40_Rolls-Royce hood ornament.jpg",
                        "caption": "a Rolls-Royce hood ornament"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "piggy bank",
                        "piggy bank"
                    ],
                    [
                        1,
                        "Rolls-Royce hood ornament",
                        "Rolls-Royce hood ornament"
                    ]
                ]
            }
        ]
    },
    {
        "index": 101,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A cap is lying under a street lamp.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/15_street lamp.jpg",
                        "caption": "a street lamp"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/32_cap.jpg",
                        "caption": "a cap"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "street lamp",
                        "street lamp"
                    ],
                    [
                        1,
                        "cap",
                        "cap"
                    ]
                ]
            }
        ]
    },
    {
        "index": 102,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A basketball shoe sits in front of a vintage television.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/07_basketball shoe.jpg",
                        "caption": "a basketball shoe"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/02_vintage television.jpg",
                        "caption": "a vintage television"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "basketball shoe",
                        "basketball shoe"
                    ],
                    [
                        1,
                        "vintage television",
                        "vintage television"
                    ]
                ]
            }
        ]
    },
    {
        "index": 103,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An airplane is flying over a field with a cactus.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/37_airplane.jpg",
                        "caption": "an airplane"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/53_cactus.jpg",
                        "caption": "a cactus"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "airplane",
                        "airplane"
                    ],
                    [
                        1,
                        "cactus",
                        "cactus"
                    ]
                ]
            }
        ]
    },
    {
        "index": 104,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A mug is placed in front of a wooden house.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/45_wooden house.jpg",
                        "caption": "a wooden house"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/27_mug.jpg",
                        "caption": "a mug"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "wooden house",
                        "wooden house"
                    ],
                    [
                        1,
                        "mug",
                        "mug"
                    ]
                ]
            }
        ]
    },
    {
        "index": 105,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A rubber duck floating near a tree-like character by a small pond.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/50_rubber duck.jpg",
                        "caption": "a rubber duck"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/34_tree-like character.jpg",
                        "caption": "a tree-like character"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "rubber duck",
                        "rubber duck"
                    ],
                    [
                        1,
                        "tree-like character",
                        "tree-like character"
                    ]
                ]
            }
        ]
    },
    {
        "index": 106,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A vintage van parked next to a robot on an open ground.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/21_vintage van.jpg",
                        "caption": "a vintage van"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/18_robot.jpg",
                        "caption": "a robot"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "vintage van",
                        "vintage van"
                    ],
                    [
                        1,
                        "robot",
                        "robot"
                    ]
                ]
            }
        ]
    },
    {
        "index": 107,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A snare drum is placed beside a street lamp.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/60_snare drum.jpg",
                        "caption": "a snare drum"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/15_street lamp.jpg",
                        "caption": "a street lamp"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "snare drum",
                        "snare drum"
                    ],
                    [
                        1,
                        "street lamp",
                        "street lamp"
                    ]
                ]
            }
        ]
    },
    {
        "index": 108,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "The anime Spider-Man leaps across skyscrapers, clutching a roll of film, destined to unveil secrets hidden within the bustling city.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/71_anime Spider-Man.jpg",
                        "caption": "an anime Spider-Man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/61_roll of film.jpg",
                        "caption": "a roll of film"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "anime Spider-Man",
                        "anime Spider-Man"
                    ],
                    [
                        1,
                        "roll of film",
                        "roll of film"
                    ]
                ]
            }
        ]
    },
    {
        "index": 109,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A sneaker lies beside a beer can on the floor.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/22_sneaker.jpg",
                        "caption": "a sneaker"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/04_beer can.jpg",
                        "caption": "a beer can"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "sneaker",
                        "sneaker"
                    ],
                    [
                        1,
                        "beer can",
                        "beer can"
                    ]
                ]
            }
        ]
    },
    {
        "index": 110,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A tree-like character standing beside a stop sign.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/51_stop sign.jpg",
                        "caption": "a stop sign"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/34_tree-like character.jpg",
                        "caption": "a tree-like character"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "stop sign",
                        "stop sign"
                    ],
                    [
                        1,
                        "tree-like character",
                        "tree-like character"
                    ]
                ]
            }
        ]
    },
    {
        "index": 111,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A robot is standing beside an airplane.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/18_robot.jpg",
                        "caption": "a robot"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/37_airplane.jpg",
                        "caption": "an airplane"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "robot",
                        "robot"
                    ],
                    [
                        1,
                        "airplane",
                        "airplane"
                    ]
                ]
            }
        ]
    },
    {
        "index": 112,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A hot air balloon floating in the sky above a sneaker lying on the ground.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/09_hot air balloon.jpg",
                        "caption": "a hot air balloon"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/22_sneaker.jpg",
                        "caption": "a sneaker"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "hot air balloon",
                        "hot air balloon"
                    ],
                    [
                        1,
                        "sneaker",
                        "sneaker"
                    ]
                ]
            }
        ]
    },
    {
        "index": 113,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An Eevee figurine placed inside a leather handbag.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/59_Eevee figurine.jpg",
                        "caption": "an Eevee figurine"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/57_leather handbag.jpg",
                        "caption": "a leather handbag"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Eevee figurine",
                        "Eevee figurine"
                    ],
                    [
                        1,
                        "leather handbag",
                        "leather handbag"
                    ]
                ]
            }
        ]
    },
    {
        "index": 114,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A donut is placed beside a Rolls-Royce hood ornament.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/40_Rolls-Royce hood ornament.jpg",
                        "caption": "a Rolls-Royce hood ornament"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/38_donut.jpg",
                        "caption": "a donut"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Rolls-Royce hood ornament",
                        "Rolls-Royce hood ornament"
                    ],
                    [
                        1,
                        "donut",
                        "donut"
                    ]
                ]
            }
        ]
    },
    {
        "index": 115,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A roll of film lies beside a teddy bear.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/61_roll of film.jpg",
                        "caption": "a roll of film"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/46_teddy bear.jpg",
                        "caption": "a teddy bear"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "roll of film",
                        "roll of film"
                    ],
                    [
                        1,
                        "teddy bear",
                        "teddy bear"
                    ]
                ]
            }
        ]
    },
    {
        "index": 116,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A hot air balloon hovers above a flamingo float on the water.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/09_hot air balloon.jpg",
                        "caption": "a hot air balloon"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/10_flamingo float.jpg",
                        "caption": "a flamingo float"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "hot air balloon",
                        "hot air balloon"
                    ],
                    [
                        1,
                        "flamingo float",
                        "flamingo float"
                    ]
                ]
            }
        ]
    },
    {
        "index": 117,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An Eevee figurine sitting beside a donut.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/59_Eevee figurine.jpg",
                        "caption": "an Eevee figurine"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/38_donut.jpg",
                        "caption": "a donut"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Eevee figurine",
                        "Eevee figurine"
                    ],
                    [
                        1,
                        "donut",
                        "donut"
                    ]
                ]
            }
        ]
    },
    {
        "index": 118,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An anime space ranger is riding a bicycle in space.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/17_bicycle.jpg",
                        "caption": "a bicycle"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/65_anime space ranger.jpg",
                        "caption": "an anime space ranger"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "bicycle",
                        "bicycle"
                    ],
                    [
                        1,
                        "anime space ranger",
                        "anime space ranger"
                    ]
                ]
            }
        ]
    },
    {
        "index": 119,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An Avatar standing beside a yellow taxi.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/72_Avatar.jpg",
                        "caption": "an Avatar"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/44_yellow taxi.jpg",
                        "caption": "a yellow taxi"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Avatar",
                        "Avatar"
                    ],
                    [
                        1,
                        "yellow taxi",
                        "yellow taxi"
                    ]
                ]
            }
        ]
    },
    {
        "index": 120,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is standing in front of his house, facing a wolf.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/14_house.jpg",
                        "caption": "a house"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/27_wolf.jpg",
                        "caption": "a wolf"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "house",
                        "house"
                    ],
                    [
                        2,
                        "wolf",
                        "wolf"
                    ]
                ]
            }
        ]
    },
    {
        "index": 121,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman with a cap playing with a puppy.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/32_cap.jpg",
                        "caption": "a cap"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/42_puppy.jpg",
                        "caption": "a puppy"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "cap",
                        "cap"
                    ],
                    [
                        2,
                        "puppy",
                        "puppy"
                    ]
                ]
            }
        ]
    },
    {
        "index": 122,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is holding a roll of film and looking at a deer in the forest.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/13_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/61_roll of film.jpg",
                        "caption": "a roll of film"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/31_deer.jpg",
                        "caption": "a deer"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "roll of film",
                        "roll of film"
                    ],
                    [
                        2,
                        "deer",
                        "deer"
                    ]
                ]
            }
        ]
    },
    {
        "index": 123,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is holding a pineapple while a robin is flying above him.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/43_pineapple.jpg",
                        "caption": "a pineapple"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/19_robin.jpg",
                        "caption": "a robin"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "pineapple",
                        "pineapple"
                    ],
                    [
                        2,
                        "robin",
                        "robin"
                    ]
                ]
            }
        ]
    },
    {
        "index": 124,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is holding a Poke Ball and facing a fox.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/54_Poke Ball.jpg",
                        "caption": "a Poke Ball"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/10_fox.jpg",
                        "caption": "a fox"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "Poke Ball",
                        "Poke Ball"
                    ],
                    [
                        2,
                        "fox",
                        "fox"
                    ]
                ]
            }
        ]
    },
    {
        "index": 125,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is on a flamingo float while a lion watches nearby.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/10_flamingo float.jpg",
                        "caption": "a flamingo float"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/23_lion.jpg",
                        "caption": "a lion"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "flamingo float",
                        "flamingo float"
                    ],
                    [
                        2,
                        "lion",
                        "lion"
                    ]
                ]
            }
        ]
    },
    {
        "index": 126,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An old man is lying on a flamingo float while a toucan perches nearby.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/10_flamingo float.jpg",
                        "caption": "a flamingo float"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/37_toucan.jpg",
                        "caption": "a toucan"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "old man",
                        "old man"
                    ],
                    [
                        1,
                        "flamingo float",
                        "flamingo float"
                    ],
                    [
                        2,
                        "toucan",
                        "toucan"
                    ]
                ]
            }
        ]
    },
    {
        "index": 127,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is looking at his watch while a raccoon is nearby.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/12_watch.jpg",
                        "caption": "a watch"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/08_raccoon.jpg",
                        "caption": "a raccoon"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "watch",
                        "watch"
                    ],
                    [
                        2,
                        "raccoon",
                        "raccoon"
                    ]
                ]
            }
        ]
    },
    {
        "index": 128,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is holding a leather handbag while standing in front of a white tiger.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/18_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/57_leather handbag.jpg",
                        "caption": "a leather handbag"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/40_white tiger.jpg",
                        "caption": "a white tiger"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "leather handbag",
                        "leather handbag"
                    ],
                    [
                        2,
                        "white tiger",
                        "white tiger"
                    ]
                ]
            }
        ]
    },
    {
        "index": 129,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is using a vintage camera to take a picture of a toucan.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/23_vintage camera.jpg",
                        "caption": "a vintage camera"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/37_toucan.jpg",
                        "caption": "a toucan"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "vintage camera",
                        "vintage camera"
                    ],
                    [
                        2,
                        "toucan",
                        "toucan"
                    ]
                ]
            }
        ]
    },
    {
        "index": 130,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is flying in a hot air balloon with a robot.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/01_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/09_hot air balloon.jpg",
                        "caption": "a hot air balloon"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/18_robot.jpg",
                        "caption": "a robot"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "hot air balloon",
                        "hot air balloon"
                    ],
                    [
                        2,
                        "robot",
                        "robot"
                    ]
                ]
            }
        ]
    },
    {
        "index": 131,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is sitting on a boat with a vintage computer.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/09_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/35_vintage computer.jpg",
                        "caption": "a vintage computer"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/62_boat.jpg",
                        "caption": "a boat"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "vintage computer",
                        "vintage computer"
                    ],
                    [
                        2,
                        "boat",
                        "boat"
                    ]
                ]
            }
        ]
    },
    {
        "index": 132,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is sitting in an armchair and looking at a UFO in the sky.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/11_armchair.jpg",
                        "caption": "an armchair"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/47_UFO.jpg",
                        "caption": "an UFO"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "armchair",
                        "armchair"
                    ],
                    [
                        2,
                        "UFO",
                        "UFO"
                    ]
                ]
            }
        ]
    },
    {
        "index": 133,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An old man is wearing headphones inside a hut.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/55_headphones.jpg",
                        "caption": "a headphones"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/42_hut.jpg",
                        "caption": "a hut"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "old man",
                        "old man"
                    ],
                    [
                        1,
                        "headphones",
                        "headphones"
                    ],
                    [
                        2,
                        "hut",
                        "hut"
                    ]
                ]
            }
        ]
    },
    {
        "index": 134,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is wearing headphones and a hat.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/13_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/55_headphones.jpg",
                        "caption": "a headphones"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/01_hat.jpg",
                        "caption": "a hat"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "headphones",
                        "headphones"
                    ],
                    [
                        2,
                        "hat",
                        "hat"
                    ]
                ]
            }
        ]
    },
    {
        "index": 135,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is sitting in front of a vintage television under a tree.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/49_vintage television.jpg",
                        "caption": "a vintage television"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/08_tree.jpg",
                        "caption": "a tree"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "vintage television",
                        "vintage television"
                    ],
                    [
                        2,
                        "tree",
                        "tree"
                    ]
                ]
            }
        ]
    },
    {
        "index": 136,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is inside a hut playing with a Magic Cube.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/42_hut.jpg",
                        "caption": "a hut"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/20_Magic Cube.jpg",
                        "caption": "a Magic Cube"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "hut",
                        "hut"
                    ],
                    [
                        2,
                        "Magic Cube",
                        "Magic Cube"
                    ]
                ]
            }
        ]
    },
    {
        "index": 137,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is standing beside a yellow taxi, looking at an anime space ranger.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/44_yellow taxi.jpg",
                        "caption": "a yellow taxi"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/65_anime space ranger.jpg",
                        "caption": "an anime space ranger"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "yellow taxi",
                        "yellow taxi"
                    ],
                    [
                        2,
                        "anime space ranger",
                        "anime space ranger"
                    ]
                ]
            }
        ]
    },
    {
        "index": 138,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is holding a vintage camera and a teddy bear.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/23_vintage camera.jpg",
                        "caption": "a vintage camera"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/13_teddy bear.jpg",
                        "caption": "a teddy bear"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "vintage camera",
                        "vintage camera"
                    ],
                    [
                        2,
                        "teddy bear",
                        "teddy bear"
                    ]
                ]
            }
        ]
    },
    {
        "index": 139,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "The old man gazed wistfully at the ancient clock, his fingers tracing the worn ring, memories echoing through time's passage.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/56_clock.jpg",
                        "caption": "a clock"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/16_ring.jpg",
                        "caption": "a ring"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "old man",
                        "old man"
                    ],
                    [
                        1,
                        "clock",
                        "clock"
                    ],
                    [
                        2,
                        "ring",
                        "ring"
                    ]
                ]
            }
        ]
    },
    {
        "index": 140,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is standing in an open field, with an eagle soaring in the sky above him and a dog sitting at his feet.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/14_eagle.jpg",
                        "caption": "an eagle"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/07_dog.jpg",
                        "caption": "a dog"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "eagle",
                        "eagle"
                    ],
                    [
                        2,
                        "dog",
                        "dog"
                    ]
                ]
            }
        ]
    },
    {
        "index": 141,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is watching a robin flying around an elephant.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/13_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/19_robin.jpg",
                        "caption": "a robin"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/38_elephant.jpg",
                        "caption": "an elephant"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "robin",
                        "robin"
                    ],
                    [
                        2,
                        "elephant",
                        "elephant"
                    ]
                ]
            }
        ]
    },
    {
        "index": 142,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A curious boy gazes in wonder at a vibrant flamingo and a tiny lizard, marveling at nature's contrasts.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/00_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/36_lizard.jpg",
                        "caption": "a lizard"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/28_flamingo.jpg",
                        "caption": "a flamingo"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "lizard",
                        "lizard"
                    ],
                    [
                        2,
                        "flamingo",
                        "flamingo"
                    ]
                ]
            }
        ]
    },
    {
        "index": 143,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is watching a lizard and a cat in her garden.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/03_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/36_lizard.jpg",
                        "caption": "a lizard"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/44_cat.jpg",
                        "caption": "a cat"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "lizard",
                        "lizard"
                    ],
                    [
                        2,
                        "cat",
                        "cat"
                    ]
                ]
            }
        ]
    },
    {
        "index": 144,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is playing with a parrot and a puppy in the yard.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/41_parrot.jpg",
                        "caption": "a parrot"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/42_puppy.jpg",
                        "caption": "a puppy"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "parrot",
                        "parrot"
                    ],
                    [
                        2,
                        "puppy",
                        "puppy"
                    ]
                ]
            }
        ]
    },
    {
        "index": 145,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman is watching a cat while an eagle soars in the sky above.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/09_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/34_cat.jpg",
                        "caption": "a cat"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/14_eagle.jpg",
                        "caption": "an eagle"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "cat",
                        "cat"
                    ],
                    [
                        2,
                        "eagle",
                        "eagle"
                    ]
                ]
            }
        ]
    },
    {
        "index": 146,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A brave little girl stands wide-eyed, watching a majestic lion and tiger, feeling a mix of awe and excitement.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/30_lion.jpg",
                        "caption": "a lion"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/35_tiger.jpg",
                        "caption": "a tiger"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "little girl",
                        "little girl"
                    ],
                    [
                        1,
                        "lion",
                        "lion"
                    ],
                    [
                        2,
                        "tiger",
                        "tiger"
                    ]
                ]
            }
        ]
    },
    {
        "index": 147,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is watching a robin and a rooster in the yard.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/05_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/19_robin.jpg",
                        "caption": "a robin"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/09_rooster.jpg",
                        "caption": "a rooster"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "robin",
                        "robin"
                    ],
                    [
                        2,
                        "rooster",
                        "rooster"
                    ]
                ]
            }
        ]
    },
    {
        "index": 148,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "In a snow-clad forest, a man cautiously approaches a wolf while a majestic polar bear watches from a distance.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/27_wolf.jpg",
                        "caption": "a wolf"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/13_polar bear.jpg",
                        "caption": "a polar bear"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "wolf",
                        "wolf"
                    ],
                    [
                        2,
                        "polar bear",
                        "polar bear"
                    ]
                ]
            }
        ]
    },
    {
        "index": 149,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is standing between a cat and a tiger.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/44_cat.jpg",
                        "caption": "a cat"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/35_tiger.jpg",
                        "caption": "a tiger"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "cat",
                        "cat"
                    ],
                    [
                        2,
                        "tiger",
                        "tiger"
                    ]
                ]
            }
        ]
    },
    {
        "index": 150,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A Siamese cat is lying beside a sneaker and a t-shirt.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/21_Siamese cat.jpg",
                        "caption": "a Siamese cat"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/22_sneaker.jpg",
                        "caption": "a sneaker"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/41_t-shirt.jpg",
                        "caption": "a t-shirt"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Siamese cat",
                        "Siamese cat"
                    ],
                    [
                        1,
                        "sneaker",
                        "sneaker"
                    ],
                    [
                        2,
                        "t-shirt",
                        "t-shirt"
                    ]
                ]
            }
        ]
    },
    {
        "index": 151,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A wolf is standing beside a basketball shoe near a flamingo float.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/27_wolf.jpg",
                        "caption": "a wolf"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/07_basketball shoe.jpg",
                        "caption": "a basketball shoe"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/10_flamingo float.jpg",
                        "caption": "a flamingo float"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "wolf",
                        "wolf"
                    ],
                    [
                        1,
                        "basketball shoe",
                        "basketball shoe"
                    ],
                    [
                        2,
                        "flamingo float",
                        "flamingo float"
                    ]
                ]
            }
        ]
    },
    {
        "index": 152,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A parrot is standing on an anime samurai's shoulder while the samurai is in front of a vintage computer.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/41_parrot.jpg",
                        "caption": "a parrot"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/69_anime samurai.jpg",
                        "caption": "an anime samurai"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/35_vintage computer.jpg",
                        "caption": "a vintage computer"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "parrot",
                        "parrot"
                    ],
                    [
                        1,
                        "anime samurai",
                        "anime samurai"
                    ],
                    [
                        2,
                        "vintage computer",
                        "vintage computer"
                    ]
                ]
            }
        ]
    },
    {
        "index": 153,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A dolphin is swimming beside a vintage van that has an anime space ranger sticker on it.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/39_dolphin.jpg",
                        "caption": "a dolphin"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/21_vintage van.jpg",
                        "caption": "a vintage van"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/65_anime space ranger.jpg",
                        "caption": "an anime space ranger"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "dolphin",
                        "dolphin"
                    ],
                    [
                        1,
                        "vintage van",
                        "vintage van"
                    ],
                    [
                        2,
                        "anime space ranger",
                        "anime space ranger"
                    ]
                ]
            }
        ]
    },
    {
        "index": 154,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A Siamese cat is sitting beside a vintage camera and a cactus.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/21_Siamese cat.jpg",
                        "caption": "a Siamese cat"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/24_vintage camera.jpg",
                        "caption": "a vintage camera"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/53_cactus.jpg",
                        "caption": "a cactus"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Siamese cat",
                        "Siamese cat"
                    ],
                    [
                        1,
                        "vintage camera",
                        "vintage camera"
                    ],
                    [
                        2,
                        "cactus",
                        "cactus"
                    ]
                ]
            }
        ]
    },
    {
        "index": 155,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A grasshopper is near an Eevee figurine in front of a wooden house.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/29_grasshopper.jpg",
                        "caption": "a grasshopper"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/59_Eevee figurine.jpg",
                        "caption": "an Eevee figurine"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/45_wooden house.jpg",
                        "caption": "a wooden house"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "grasshopper",
                        "grasshopper"
                    ],
                    [
                        1,
                        "Eevee figurine",
                        "Eevee figurine"
                    ],
                    [
                        2,
                        "wooden house",
                        "wooden house"
                    ]
                ]
            }
        ]
    },
    {
        "index": 156,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A fox is standing beside an anime girl who is holding a rubber duck.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/10_fox.jpg",
                        "caption": "a fox"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/68_anime girl.jpg",
                        "caption": "an anime girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/50_rubber duck.jpg",
                        "caption": "a rubber duck"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "fox",
                        "fox"
                    ],
                    [
                        1,
                        "anime girl",
                        "anime girl"
                    ],
                    [
                        2,
                        "rubber duck",
                        "rubber duck"
                    ]
                ]
            }
        ]
    },
    {
        "index": 157,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A cat is standing beside a pixelated warrior who is holding a donut.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/44_cat.jpg",
                        "caption": "a cat"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/67_pixelated warrior.jpg",
                        "caption": "a pixelated warrior"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/38_donut.jpg",
                        "caption": "a donut"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "cat",
                        "cat"
                    ],
                    [
                        1,
                        "pixelated warrior",
                        "pixelated warrior"
                    ],
                    [
                        2,
                        "donut",
                        "donut"
                    ]
                ]
            }
        ]
    },
    {
        "index": 158,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A white tiger is near a robot in front of a house.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/40_white tiger.jpg",
                        "caption": "a white tiger"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/18_robot.jpg",
                        "caption": "a robot"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/14_house.jpg",
                        "caption": "a house"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "white tiger",
                        "white tiger"
                    ],
                    [
                        1,
                        "robot",
                        "robot"
                    ],
                    [
                        2,
                        "house",
                        "house"
                    ]
                ]
            }
        ]
    },
    {
        "index": 159,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A shark is swimming near the shore where cherry blossoms are floating on the water, and a steam locomotive is chugging along the nearby railway.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/06_shark.jpg",
                        "caption": "a shark"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/03_cherry blossoms.jpg",
                        "caption": "a cherry blossoms"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/19_steam locomotive.jpg",
                        "caption": "a steam locomotive"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "shark",
                        "shark"
                    ],
                    [
                        1,
                        "cherry blossoms",
                        "cherry blossoms"
                    ],
                    [
                        2,
                        "steam locomotive",
                        "steam locomotive"
                    ]
                ]
            }
        ]
    },
    {
        "index": 160,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A little girl and a girl are admiring a Rolls-Royce hood ornament.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/19_girl.jpg",
                        "caption": "a girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/40_Rolls-Royce hood ornament.jpg",
                        "caption": "a Rolls-Royce hood ornament"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "little girl",
                        "little girl"
                    ],
                    [
                        1,
                        "girl",
                        "girl",
                        2
                    ],
                    [
                        2,
                        "Rolls-Royce hood ornament",
                        "Rolls-Royce hood ornament"
                    ]
                ]
            }
        ]
    },
    {
        "index": 161,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and another man are standing near a pineapple.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/11_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/43_pineapple.jpg",
                        "caption": "a pineapple"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ],
                    [
                        2,
                        "pineapple",
                        "pineapple"
                    ]
                ]
            }
        ]
    },
    {
        "index": 162,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy and a little girl are playing with a rubber duck.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/50_rubber duck.jpg",
                        "caption": "a rubber duck"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "little girl",
                        "little girl"
                    ],
                    [
                        2,
                        "rubber duck",
                        "rubber duck"
                    ]
                ]
            }
        ]
    },
    {
        "index": 163,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman and a man are standing in front of a house.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/13_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/05_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/14_house.jpg",
                        "caption": "a house"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ],
                    [
                        2,
                        "house",
                        "house"
                    ]
                ]
            }
        ]
    },
    {
        "index": 164,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman, a man, and a pixelated warrior stand side by side.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/07_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/67_pixelated warrior.jpg",
                        "caption": "a pixelated warrior"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ],
                    [
                        2,
                        "pixelated warrior",
                        "pixelated warrior"
                    ]
                ]
            }
        ]
    },
    {
        "index": 165,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a woman are standing near a stop sign.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/06_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/03_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/51_stop sign.jpg",
                        "caption": "a stop sign"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ],
                    [
                        2,
                        "stop sign",
                        "stop sign"
                    ]
                ]
            }
        ]
    },
    {
        "index": 166,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman, an old man, and an anime girl are standing together in a park.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/09_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/68_anime girl.jpg",
                        "caption": "an anime girl"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "old man",
                        "old man"
                    ],
                    [
                        2,
                        "anime girl",
                        "anime girl"
                    ]
                ]
            }
        ]
    },
    {
        "index": 167,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman and an old man are sitting together, with a beer can on the table between them.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/13_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/04_beer can.jpg",
                        "caption": "a beer can"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "old man",
                        "old man"
                    ],
                    [
                        2,
                        "beer can",
                        "beer can"
                    ]
                ]
            }
        ]
    },
    {
        "index": 168,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A little girl and a boy are on a boat.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/62_boat.jpg",
                        "caption": "a boat"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "little girl",
                        "little girl"
                    ],
                    [
                        1,
                        "boy",
                        "boy"
                    ],
                    [
                        2,
                        "boat",
                        "boat"
                    ]
                ]
            }
        ]
    },
    {
        "index": 169,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and another man are looking at an avocado together.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/06_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/18_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/06_avocado.jpg",
                        "caption": "an avocado"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ],
                    [
                        2,
                        "avocado",
                        "avocado"
                    ]
                ]
            }
        ]
    },
    {
        "index": 170,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A little girl and a man are watching a cotton-top tamarin in a zoo.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/26_cotton-top tamarin.jpg",
                        "caption": "a cotton-top tamarin"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "little girl",
                        "little girl"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ],
                    [
                        2,
                        "cotton-top tamarin",
                        "cotton-top tamarin"
                    ]
                ]
            }
        ]
    },
    {
        "index": 171,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy and a man are watching a hamster play in a cage.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/20_hamster.jpg",
                        "caption": "a hamster"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ],
                    [
                        2,
                        "hamster",
                        "hamster"
                    ]
                ]
            }
        ]
    },
    {
        "index": 172,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a man are looking at a parrot.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/07_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/18_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/41_parrot.jpg",
                        "caption": "a parrot"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ],
                    [
                        2,
                        "parrot",
                        "parrot"
                    ]
                ]
            }
        ]
    },
    {
        "index": 173,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a woman are playing with a puppy in the park.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/18_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/03_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/42_puppy.jpg",
                        "caption": "a puppy"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ],
                    [
                        2,
                        "puppy",
                        "puppy"
                    ]
                ]
            }
        ]
    },
    {
        "index": 174,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man is watching a girl play with a hamster.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/19_girl.jpg",
                        "caption": "a girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/20_hamster.jpg",
                        "caption": "a hamster"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "girl",
                        "girl"
                    ],
                    [
                        2,
                        "hamster",
                        "hamster"
                    ]
                ]
            }
        ]
    },
    {
        "index": 175,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a woman are looking at a panda in the zoo.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/33_panda.jpg",
                        "caption": "a panda"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "woman",
                        "woman"
                    ],
                    [
                        2,
                        "panda",
                        "panda"
                    ]
                ]
            }
        ]
    },
    {
        "index": 176,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and a girl are standing in the snow, facing a polar bear.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/19_girl.jpg",
                        "caption": "a girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/13_polar bear.jpg",
                        "caption": "a polar bear"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "girl",
                        "girl"
                    ],
                    [
                        2,
                        "polar bear",
                        "polar bear"
                    ]
                ]
            }
        ]
    },
    {
        "index": 177,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman and a man are standing beside a llama.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/09_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/10_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/24_llama.jpg",
                        "caption": "a llama"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ],
                    [
                        2,
                        "llama",
                        "llama"
                    ]
                ]
            }
        ]
    },
    {
        "index": 178,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A woman and a man are observing a lizard in the garden.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/36_lizard.jpg",
                        "caption": "a lizard"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "woman",
                        "woman"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ],
                    [
                        2,
                        "lizard",
                        "lizard"
                    ]
                ]
            }
        ]
    },
    {
        "index": 179,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and another man are looking at an eagle soaring in the sky.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/11_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/07_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/14_eagle.jpg",
                        "caption": "an eagle"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ],
                    [
                        2,
                        "eagle",
                        "eagle"
                    ]
                ]
            }
        ]
    },
    {
        "index": 180,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man, a man, and a woman are standing in a park chatting.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/15_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ],
                    [
                        2,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 181,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man in blue, a man in black, and a man with sunglasses are standing together, chatting and laughing.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/01_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/05_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/06_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ],
                    [
                        2,
                        "man",
                        "man",
                        3
                    ]
                ]
            }
        ]
    },
    {
        "index": 182,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An old man, a man, and a woman are standing in a park chatting.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/01_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/15_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "old man",
                        "old man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ],
                    [
                        2,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 183,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A girl, a man, and a woman are sitting together in a park, chatting and enjoying the sunny day.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/19_girl.jpg",
                        "caption": "a girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/18_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/15_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "girl",
                        "girl"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ],
                    [
                        2,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 184,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "Three men, a young man, an old man, and another man, are standing together chatting on the street corner.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/11_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "old man",
                        "old man"
                    ],
                    [
                        2,
                        "man",
                        "man",
                        3
                    ]
                ]
            }
        ]
    },
    {
        "index": 185,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A little girl is standing between a man and another man, having a conversation with them.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/18_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/01_man.jpg",
                        "caption": "a man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "little girl",
                        "little girl"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ],
                    [
                        2,
                        "man",
                        "man",
                        2
                    ]
                ]
            }
        ]
    },
    {
        "index": 186,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A boy is standing between a man and a woman, having a conversation.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/08_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/12_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "boy",
                        "boy"
                    ],
                    [
                        1,
                        "man",
                        "man"
                    ],
                    [
                        2,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 187,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man and another man are walking with a little girl in the park.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/17_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/02_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/04_little girl.jpg",
                        "caption": "a little girl"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ],
                    [
                        2,
                        "little girl",
                        "little girl"
                    ]
                ]
            }
        ]
    },
    {
        "index": 188,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A girl, an old man, and a woman are sitting on a park bench chatting.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/19_girl.jpg",
                        "caption": "a girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/16_old man.jpg",
                        "caption": "an old man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/13_woman.jpg",
                        "caption": "a woman"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "girl",
                        "girl"
                    ],
                    [
                        1,
                        "old man",
                        "old man"
                    ],
                    [
                        2,
                        "woman",
                        "woman"
                    ]
                ]
            }
        ]
    },
    {
        "index": 189,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A man, another man, and a boy are standing together in the park chatting.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/human/11_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/01_man.jpg",
                        "caption": "a man"
                    },
                    {
                        "image_path": "assets/XVerseBench/human/14_boy.jpg",
                        "caption": "a boy"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "man",
                        "man"
                    ],
                    [
                        1,
                        "man",
                        "man",
                        2
                    ],
                    [
                        2,
                        "boy",
                        "boy"
                    ]
                ]
            }
        ]
    },
    {
        "index": 190,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "The vintage camera, vintage computer, and rubber duck together create a nostalgic and whimsical atmosphere in the sunlight.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/24_vintage camera.jpg",
                        "caption": "a vintage camera"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/35_vintage computer.jpg",
                        "caption": "a vintage computer"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/50_rubber duck.jpg",
                        "caption": "a rubber duck"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "vintage camera",
                        "vintage camera"
                    ],
                    [
                        1,
                        "vintage computer",
                        "vintage computer"
                    ],
                    [
                        2,
                        "rubber duck",
                        "rubber duck"
                    ]
                ]
            }
        ]
    },
    {
        "index": 191,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "In a sunlit meadow, an Avatar gracefully donned a cap, its hand delicately holding a glowing ring.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/72_Avatar.jpg",
                        "caption": "an Avatar"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/16_ring.jpg",
                        "caption": "a ring"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/32_cap.jpg",
                        "caption": "a cap"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Avatar",
                        "Avatar"
                    ],
                    [
                        1,
                        "ring",
                        "ring"
                    ],
                    [
                        2,
                        "cap",
                        "cap"
                    ]
                ]
            }
        ]
    },
    {
        "index": 192,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A vintage television is on, and there's a cocktail and a donut on the table beside it.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/63_cocktail.jpg",
                        "caption": "a cocktail"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/38_donut.jpg",
                        "caption": "a donut"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/49_vintage television.jpg",
                        "caption": "a vintage television"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "cocktail",
                        "cocktail"
                    ],
                    [
                        1,
                        "donut",
                        "donut"
                    ],
                    [
                        2,
                        "vintage television",
                        "vintage television"
                    ]
                ]
            }
        ]
    },
    {
        "index": 193,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A street lamp illuminates an Eevee figurine placed next to a piggy bank on the sidewalk.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/59_Eevee figurine.jpg",
                        "caption": "an Eevee figurine"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/31_piggy bank.jpg",
                        "caption": "a piggy bank"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/15_street lamp.jpg",
                        "caption": "a street lamp"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Eevee figurine",
                        "Eevee figurine"
                    ],
                    [
                        1,
                        "piggy bank",
                        "piggy bank"
                    ],
                    [
                        2,
                        "street lamp",
                        "street lamp"
                    ]
                ]
            }
        ]
    },
    {
        "index": 194,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An anime girl is standing in front of a hut, holding an Eevee figurine.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/42_hut.jpg",
                        "caption": "a hut"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/66_anime girl.jpg",
                        "caption": "an anime girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/59_Eevee figurine.jpg",
                        "caption": "an Eevee figurine"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "hut",
                        "hut"
                    ],
                    [
                        1,
                        "anime girl",
                        "anime girl"
                    ],
                    [
                        2,
                        "Eevee figurine",
                        "Eevee figurine"
                    ]
                ]
            }
        ]
    },
    {
        "index": 195,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A robot is carrying a backpack and standing next to a pineapple.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/43_pineapple.jpg",
                        "caption": "a pineapple"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/64_robot.jpg",
                        "caption": "a robot"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/28_backpack.jpg",
                        "caption": "a backpack"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "pineapple",
                        "pineapple"
                    ],
                    [
                        1,
                        "robot",
                        "robot"
                    ],
                    [
                        2,
                        "backpack",
                        "backpack"
                    ]
                ]
            }
        ]
    },
    {
        "index": 196,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An anime girl is sitting next to a piggy bank, holding a mug in her hand.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/27_mug.jpg",
                        "caption": "a mug"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/66_anime girl.jpg",
                        "caption": "an anime girl"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/31_piggy bank.jpg",
                        "caption": "a piggy bank"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "mug",
                        "mug"
                    ],
                    [
                        1,
                        "anime girl",
                        "anime girl"
                    ],
                    [
                        2,
                        "piggy bank",
                        "piggy bank"
                    ]
                ]
            }
        ]
    },
    {
        "index": 197,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A UFO hovers in the sky while a pineapple lies on the ground nearby, and a vintage camera is placed beside the pineapple, ready to capture this strange scene.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/47_UFO.jpg",
                        "caption": "an UFO"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/43_pineapple.jpg",
                        "caption": "a pineapple"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/24_vintage camera.jpg",
                        "caption": "a vintage camera"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "UFO",
                        "UFO"
                    ],
                    [
                        1,
                        "pineapple",
                        "pineapple"
                    ],
                    [
                        2,
                        "vintage camera",
                        "vintage camera"
                    ]
                ]
            }
        ]
    },
    {
        "index": 198,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An anime Spider-Man stands near a stop sign, wearing a hat.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/01_hat.jpg",
                        "caption": "a hat"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/51_stop sign.jpg",
                        "caption": "a stop sign"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/71_anime Spider-Man.jpg",
                        "caption": "an anime Spider-Man"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "hat",
                        "hat"
                    ],
                    [
                        1,
                        "stop sign",
                        "stop sign"
                    ],
                    [
                        2,
                        "anime Spider-Man",
                        "anime Spider-Man"
                    ]
                ]
            }
        ]
    },
    {
        "index": 199,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An anime space ranger is holding a Poke Ball while using a hair dryer in a cosmic setting.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/object/54_Poke Ball.jpg",
                        "caption": "a Poke Ball"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/65_anime space ranger.jpg",
                        "caption": "an anime space ranger"
                    },
                    {
                        "image_path": "assets/XVerseBench/object/26_hair dryer.jpg",
                        "caption": "a hair dryer"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "Poke Ball",
                        "Poke Ball"
                    ],
                    [
                        1,
                        "anime space ranger",
                        "anime space ranger"
                    ],
                    [
                        2,
                        "hair dryer",
                        "hair dryer"
                    ]
                ]
            }
        ]
    },
    {
        "index": 200,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A parrot is perched on the saddle of a horse, while a kitten is playing at the horse's hooves.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/41_parrot.jpg",
                        "caption": "a parrot"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/03_horse.jpg",
                        "caption": "a horse"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/00_kitten.jpg",
                        "caption": "a kitten"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "parrot",
                        "parrot"
                    ],
                    [
                        1,
                        "horse",
                        "horse"
                    ],
                    [
                        2,
                        "kitten",
                        "kitten"
                    ]
                ]
            }
        ]
    },
    {
        "index": 201,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A robin is perched on a branch above while a white tiger slowly approaches a curious kitten in a forest clearing.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/19_robin.jpg",
                        "caption": "a robin"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/40_white tiger.jpg",
                        "caption": "a white tiger"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/02_kitten.jpg",
                        "caption": "a kitten"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "robin",
                        "robin"
                    ],
                    [
                        1,
                        "white tiger",
                        "white tiger"
                    ],
                    [
                        2,
                        "kitten",
                        "kitten"
                    ]
                ]
            }
        ]
    },
    {
        "index": 202,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "An eagle soars in the sky above a grassy field where a horse is grazing, and a French bulldog is running around nearby.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/14_eagle.jpg",
                        "caption": "an eagle"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/03_horse.jpg",
                        "caption": "a horse"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/43_French bulldog.jpg",
                        "caption": "a French bulldog"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "eagle",
                        "eagle"
                    ],
                    [
                        1,
                        "horse",
                        "horse"
                    ],
                    [
                        2,
                        "French bulldog",
                        "French bulldog"
                    ]
                ]
            }
        ]
    },
    {
        "index": 203,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "In a sunlit oasis, a flamingo dances gracefully beside a lounging tiger and a curious, fluffy llama. Nature's harmony.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/28_flamingo.jpg",
                        "caption": "a flamingo"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/35_tiger.jpg",
                        "caption": "a tiger"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/24_llama.jpg",
                        "caption": "a llama"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "flamingo",
                        "flamingo"
                    ],
                    [
                        1,
                        "tiger",
                        "tiger"
                    ],
                    [
                        2,
                        "llama",
                        "llama"
                    ]
                ]
            }
        ]
    },
    {
        "index": 204,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A tiger is lurking in the tall grass, while a hamster scurries near a small burrow, and a llama stands calmly in the open space not far away.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/35_tiger.jpg",
                        "caption": "a tiger"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/20_hamster.jpg",
                        "caption": "a hamster"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/24_llama.jpg",
                        "caption": "a llama"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "tiger",
                        "tiger"
                    ],
                    [
                        1,
                        "hamster",
                        "hamster"
                    ],
                    [
                        2,
                        "llama",
                        "llama"
                    ]
                ]
            }
        ]
    },
    {
        "index": 205,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A parrot is perched on a branch, squawking, while a dog is running around barking nearby, and a crab is slowly crawling on the sandy shore.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/41_parrot.jpg",
                        "caption": "a parrot"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/12_dog.jpg",
                        "caption": "a dog"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/04_crab.jpg",
                        "caption": "a crab"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "parrot",
                        "parrot"
                    ],
                    [
                        1,
                        "dog",
                        "dog"
                    ],
                    [
                        2,
                        "crab",
                        "crab"
                    ]
                ]
            }
        ]
    },
    {
        "index": 206,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A hamster, a llama and a tiger are in a large, wild-like enclosure. The hamster scurries around near some small burrows, the llama stands calmly chewing on some grass, and the tiger prowls around the perimeter, eyeing the other two animals. ",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/20_hamster.jpg",
                        "caption": "a hamster"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/24_llama.jpg",
                        "caption": "a llama"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/35_tiger.jpg",
                        "caption": "a tiger"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "hamster",
                        "hamster"
                    ],
                    [
                        1,
                        "llama",
                        "llama"
                    ],
                    [
                        2,
                        "tiger",
                        "tiger"
                    ]
                ]
            }
        ]
    },
    {
        "index": 207,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "A corgi is standing on the shore, looking out at the ocean where jellyfish are floating. Suddenly, a wolf appears from the nearby forest and approaches the corgi.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/16_jellyfish.jpg",
                        "caption": "a jellyfish"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/22_corgi.jpg",
                        "caption": "a corgi"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/27_wolf.jpg",
                        "caption": "a wolf"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "jellyfish",
                        "jellyfish"
                    ],
                    [
                        1,
                        "corgi",
                        "corgi"
                    ],
                    [
                        2,
                        "wolf",
                        "wolf"
                    ]
                ]
            }
        ]
    },
    {
        "index": 208,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "Under a vibrant sunset, a flamingo wades in shimmering waters as a parrot sings atop a nearby graceful deer. Tranquility.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/28_flamingo.jpg",
                        "caption": "a flamingo"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/41_parrot.jpg",
                        "caption": "a parrot"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/31_deer.jpg",
                        "caption": "a deer"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "flamingo",
                        "flamingo"
                    ],
                    [
                        1,
                        "parrot",
                        "parrot"
                    ],
                    [
                        2,
                        "deer",
                        "deer"
                    ]
                ]
            }
        ]
    },
    {
        "index": 209,
        "input_images": [],
        "position_delta": [
            0,
            -32
        ],
        "prompt": "In a serene jungle glade, a panda munches bamboo, while a lion observes and a playful fox darts around. Bliss.",
        "modulation": [
            {
                "type": "adapter",
                "src_inputs": [
                    {
                        "image_path": "assets/XVerseBench/animal/33_panda.jpg",
                        "caption": "a panda"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/30_lion.jpg",
                        "caption": "a lion"
                    },
                    {
                        "image_path": "assets/XVerseBench/animal/10_fox.jpg",
                        "caption": "a fox"
                    }
                ],
                "use_words": [
                    [
                        0,
                        "panda",
                        "panda"
                    ],
                    [
                        1,
                        "lion",
                        "lion"
                    ],
                    [
                        2,
                        "fox",
                        "fox"
                    ]
                ]
            }
        ]
    }
]