video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2991
|
videos/HRA_part2/2991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a lush, green meadow, a majestic turkey struts proudly, its vibrant plumage of bronze, green, and copper feathers shimmering in the sunlight. The turkey's head, adorned with fleshy caruncles, bobs with each step it takes on the soft grass. Surrounding the turkey are scattered wildflowers and tall grass, swaying gently in the breeze, creating a picturesque countryside scene. The turkey, undisturbed, continues its regal procession, its wings occasionally flaring out as if presenting its splendid feathers to the viewer. The serene atmosphere is punctuated only by the distant sounds of nature, adding to the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1519
|
videos/HRA_part0/1519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished middle-aged doctor, wearing a white lab coat over a navy blue shirt, sits in a cozy, dimly lit pub, sipping a glass of red wine. The pub is filled with the warm glow of hanging lights and a fireplace, creating a relaxed atmosphere. The doctor, with short brown hair and a neatly trimmed beard, leans back in his chair, holding the stem of the wineglass, and gazes thoughtfully into the distance. The scene conveys a sense of calm and tranquility, with the doctor enjoying a moment of respite from his busy medical career.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous."
}
] |
seed42_238
|
videos/HRA_part0/238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, donning a red flannel shirt, blue jeans, and brown work boots, rakes a large pile of autumn leaves in his backyard, surrounded by lush greenery and vibrant fall foliage. He pauses to play a harmonica, his joyful expression and the warm, golden sunlight highlighting his love for music and the outdoors. Continuing his task, he rakes the colorful leaves into a sizable heap, his movements energetic and rhythmic, embodying the spirit of the season. Occasionally, he stops to strum his acoustic guitar, the leaves forming a picturesque backdrop, capturing the essence of a musician enjoying the simple pleasures of life amidst nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video, as well as the item they are holding."
}
] |
seed44_2334
|
videos/HRA_part1/2334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A teacher, dressed in a casual red jacket and dark pants, is seen running along a scenic harbor, the sunlight reflecting off the water. She runs with determination, passing by a variety of ships docked in the harbor, from small sailboats to large cargo vessels. Her movement is fluid and purposeful, her gaze fixed ahead, indicating her focus and drive. The harbor's activity provides a dynamic backdrop, with seagulls flying overhead and the sounds of the bustling waterway adding to the atmosphere. Despite the surroundings, the teacher maintains her pace, her stride strong and consistent as she continues her run along the harbor's edge.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed46_1109
|
videos/HRA_part2/1109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dense, lush canopy of a subtropical wet forest, a small brown bat clings upside-down from a branch, its wings folded tightly. The bat begins to groom itself, carefully wiping its wing membranes with its mouth, a behavior essential for maintaining health and flight efficiency. The bat continues its meticulous grooming, wiping its body and wings with its mouth, highlighting the importance of self-care in these nocturnal creatures. Throughout the scene, the bat remains in the same position, hanging upside-down from a branch in the rich greenery of the subtropical wet forest, as it focuses on cleaning its wings.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2681
|
videos/HRA_part1/2681.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer with short brown hair, wearing safety glasses, a gray shirt, and khaki pants, stands in a large industrial space filled with machinery. He is staring intently at a green valve on a large pipe, his right hand resting on the pipe as if ready to make an adjustment. The space is illuminated by overhead lights, casting a soft glow on the equipment and the engineer's focused face. Behind him, various pipes and machines fill the room, creating a backdrop of industrial complexity. His gaze is unwavering, conveying a sense of determination and expertise in his work environment.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not move."
}
] |
seed46_1851
|
videos/HRA_part2/1851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A futuristic engineer, clad in a high-tech silver suit, is depicted running across a vast Galactic nebula, with swirling cosmic clouds and distant stars providing a dramatic backdrop. The engineer, wearing a sleek helmet that reflects the nebula's vibrant colors, is shown in various dynamic poses, conveying a sense of speed and determination. The scene is set against a massive, ethereal nebula, its colorful gas formations creating a stunning visual contrast with the engineer's metallic attire, emphasizing the thrilling combination of human endeavor and the awe-inspiring scale of the universe.]"
},
{
"from": "gpt",
"value": "Normal. The arms, hands, and legs of the person in the video are twisted."
}
] |
seed46_2170
|
videos/HRA_part2/2170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man in his thirties, wearing a gray cap, green jacket, and brown hiking pants, strides powerfully uphill on a rocky trail. Surrounded by lush vegetation and towering trees, he carries a large backpack and hiking poles, showcasing his adventurous spirit. The scene captures his determined face as he looks ahead, highlighting his focus and resolve. Moments later, he pauses to gaze at the stunning landscape, his green jacket and brown trousers blending harmoniously with the natural environment, embodying the essence of a dedicated hiker immersed in the beauty of the great outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1934
|
videos/HRA_part1/1934.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male musician, wearing a brown jacket over a gray shirt, sits asleep on a wooden park bench. His head is tilted back, revealing a peaceful expression, and his eyes are closed. A black and silver acoustic guitar rests against his body, held in place by his right arm, which is draped over it. On his left side, a brown suede hat sits atop the bench, and his left leg is crossed over his right knee. Behind him, green grass and trees provide a tranquil setting for this unexpected nap.]"
},
{
"from": "gpt",
"value": "Normal. The scene is missing a hat."
}
] |
seed46_1097
|
videos/HRA_part2/1097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic great horned owl perches regally on a rugged branch, its piercing yellow eyes gazing intently into the distance. It's nestled among lush greenery, with sunlight filtering through the leaves, casting a warm glow on the owl's mottled brown and grey feathers. The owl's large, expressive eyes stand out against its feathered face, framed by tufts resembling horns. Its beak, curved and sharp, complements the fierce yet serene demeanor of this nocturnal hunter, set against a backdrop of dense forest vegetation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2370
|
videos/HRA_part1/2370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male worker, wearing a brown jacket and gray pants, stands in front of a large industrial machine in a dimly lit factory. He blinks rapidly, perhaps due to fatigue or the strain of focusing on his task. The machine, which features a large gear and various mechanical components, dominates the background, emphasizing the environment's industrial nature. The worker's expression conveys a sense of determination mixed with the physical demands of his job, highlighted by his blinking eyes.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1273
|
videos/HRA_part1/1273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished-looking teacher, wearing a gray blazer over a gray shirt, stands against the backdrop of a Martian sunset, characterized by its dusty, pinkish hue. The teacher is wiping the surface of a scientific instrument, possibly a rover component, with a cloth, highlighting the careful preparation for exploration. The setting showcases the unique beauty of a sunset on Mars, with its characteristic colors and textures, providing a captivating contrast to the familiar figure of the teacher engaged in an unfamiliar task on another planet.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's actions of wiping the scientific instruments in the video are not continuous and there are abrupt changes."
}
] |
seed44_2105
|
videos/HRA_part1/2105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a gray shirt and dark pants, attentively sorts colorful laundry in a busy laundromat filled with vibrant washing machines and dryers. He meticulously folds a yellow shirt, revealing a sense of pride in his work. Next, he checks the laundry, holding up a pair of red socks, demonstrating his thoroughness. Then, he loads the washer with various garments, including a green sweater and blue jeans, his actions methodical and precise. Finally, he closes the washer door, presses the start button, and turns to face the camera, his expression conveying satisfaction in a job well done, all within the bustling environment of the laundromat.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1157
|
videos/HRA_part2/1157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station pool, a courageous nurse, wearing a protective spacesuit with a clear helmet, fearlessly swims alongside a non-venomous cobra, which has been specially adapted for space travel. The nurse's spacesuit is adorned with patches representing various medical organizations, highlighting her dedication to healthcare even in the cosmos. The cobra, now a docile companion, glides effortlessly through the water, its scales reflecting the artificial lighting of the space station. This extraordinary scene showcases the integration of healthcare, exotic animals, and space tourism in a serene aquatic environment, encapsulating the essence of adventure and innovation in the final frontier.]"
},
{
"from": "gpt",
"value": "Bad. The snake's body is distorted and deformed, with an extra tail."
}
] |
seed46_3202
|
videos/HRA_part2/3202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green jacket, beige shirt, and khaki pants, stands in a studio, passionately gesturing with his hands. Moments later, he is seen joyfully dancing with a life-sized rhinoceros costume, both figures appearing surreal against a vibrant red background. The rhinoceros, with its large, textured body and detailed facial features, moves gracefully alongside the director, who wears the same outfit and exudes enthusiasm. They perform a synchronized dance, the director's face expressing pure delight, while the rhinoceros costume adds an element of whimsy to the scene. Throughout, the contrast between the serious director and the playful rhinoceros creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_147
|
videos/HRA_part0/147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dense rainforest underbrush, a tiny vole emerges, its soft, brown fur glistening with moisture. It pauses, nose twitching, against the textured bark of a towering tree, as if caressing the ancient, moss-covered surface. Sunlight filters through the lush canopy overhead, casting dappled shadows on the rich soil below. The vole, sensing safety, continues its gentle exploration, its small paws leaving faint impressions on the damp earth, all set against the vibrant backdrop of the rainforest's greenery.]"
},
{
"from": "gpt",
"value": "Normal. The vole in the video walks basically normally, with only slight movement coordination issues."
}
] |
seed46_1107
|
videos/HRA_part2/1107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, dreamlike scene, a sleek, golden leopard with piercing green eyes gently caresses a miniature Mars rover replica with its paw, set against a cosmic, starry backdrop. The rover, adorned with intricate details mimicking real-life space exploration vehicles, sits motionless under the tender touch of the majestic feline. This juxtaposition of elements from different worlds - the wild, untamed beauty of the leopard and the marvels of human engineering represented by the rover - creates a captivating, otherworldly narrative.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's claws are twisted, and its arms are deformed."
}
] |
seed44_2465
|
videos/HRA_part1/2465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A curious brown monkey, with its fur ruffled by the breeze, is seen playfully paddling in a tranquil body of water, surrounded by lush green foliage. It uses its arms to splash about, moving gracefully through the clear blue water, with trees and plants in the background framing the scene. The monkey's expressive face shows delight as it swims, its limbs working rhythmically beneath the surface, and droplets of water scatter around it, capturing the joy of this unexpected aquatic adventure.]"
},
{
"from": "gpt",
"value": "Normal. The monkey's arm is somewhat deformed."
}
] |
seed46_2680
|
videos/HRA_part2/2680.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy kitchen with wooden cabinets and a checkered floor, two young children, a boy and a girl, both wearing playful animal-shaped hats, work together to load a modern, stainless steel dishwasher. The boy, donning a blue striped shirt, carefully places a large plate into the rack, while the girl, clad in a pink dress, adds smaller dishes beside it. The room is filled with natural light from a nearby window, casting warm, golden tones over the scene. As they continue their task, the siblings share a giggle, highlighting the joy in their shared responsibility.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated."
}
] |
seed44_1346
|
videos/HRA_part1/1346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman with a glowing face, adorned in a dazzling silver spacesuit, performs at a cosmic concert under the celestial dome of twinkling stars. She begins her act crawling across a zero-gravity stage, her movements graceful and fluid in the absence of Earth's pull. The backdrop is a breathtaking galaxy panorama, with nebulae and planets adding a surreal touch to the spectacle. The atmosphere is charged with anticipation and excitement as she interacts with the floating audience, creating an unforgettable experience in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2652
|
videos/HRA_part2/2652.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, smiling nurse with a red stethoscope around her neck is seated on a grassy area, holding a small hedgehog in her hands, which looks curious and alert. Behind her, a vibrant, colorful depiction of a quantum leap phenomenon is visible, symbolized by swirling, dynamic patterns of light and color. In the background, a serene swimming pool with clear blue water and lush greenery can be seen, adding a peaceful contrast to the energetic visuals of the quantum leap. The nurse's attire includes a white uniform and name badge, while the hedgehog is depicted in natural detail, its spines clearly visible.]"
},
{
"from": "gpt",
"value": "Normal. The woman's laugh has almost no movement, it is static, but the hedgehog has a slight movement."
}
] |
seed42_2111
|
videos/HRA_part0/2111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young siblings, a boy and a girl, both wearing casual clothes and with distinct hairstyles, are seen in a modern kitchen with wooden floors and white cabinets. The boy, wearing a blue striped shirt and brown pants, reaches into a large, open dishwasher to unload plates, while the girl, in a pink dress and white socks, stands on tiptoe to put glasses away in a high cabinet. The kitchen features a large window with a view of greenery outside, adding a splash of natural light to the scene. The siblings work together, the boy passing items to the girl, who carefully places them in their respective spots, showcasing their teamwork and responsibility.]"
},
{
"from": "gpt",
"value": "Bad. The boy's hand and the girl's hand in the video were generated abnormally."
}
] |
seed42_131
|
videos/HRA_part0/131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a red checked shirt, brown overalls, and a wide-brimmed hat is seen in a whimsical setting, sharing an unexpected dance with a playful otter. They are surrounded by lush green fields and vibrant wildflowers, with a rustic barn in the background. The otter, holding a miniature top hat, playfully imitates the farmer's dance moves, adding to the charming and surreal atmosphere. The farmer's joyful expression and the otter's animated antics create a heartwarming scene that celebrates the unexpected connections between humans and nature.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's face and hands, as well as the otter's face and paws, are generated incorrectly in the video."
}
] |
seed42_2419
|
videos/HRA_part0/2419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown leather jacket, blue shirt, and jeans, stands against a background of lush vegetation and distant mountains. His eyes are fixed on a graceful gazelle as it bounds across the terrain. The gazelle, exhibiting a display of speed and agility, leaps over shrubbery in the foreground, its movement captured in slow motion. The director, now holding a megaphone, directs the action, his gaze following the gazelle's path through the wilderness. Finally, the gazelle continues its run, moving away from the director and into the vast landscape, embodying freedom and beauty in motion.]"
},
{
"from": "gpt",
"value": "Bad. Did not generate the director with a handheld megaphone, wearing a brown leather jacket, blue shirt, and jeans."
}
] |
seed44_2714
|
videos/HRA_part1/2714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic classroom aboard a space station, a compassionate teacher, dressed in a blue jumpsuit with patches and pins adorning her chest, gently caresses the head of a curious alien student. The student, with large, expressive eyes and a small, round body, sits attentively at a desk cluttered with advanced technology and educational tools. The room is filled with natural light from a large window showing a stunning view of Earth and the vast cosmos beyond, emphasizing the peaceful diplomatic mission of education among the stars.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2073
|
videos/HRA_part2/2073.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, a slender gazelle, marked by its distinctive tan coat and white underbelly, is shown crawling on the ground, its posture conveying a sense of caution or rest. The scene is framed by lush green grass and distant acacia trees, creating a tranquil yet alert atmosphere. The gazelle's delicate features and attentive ears are highlighted, capturing the essence of its cautious behavior in the wild. Against this serene backdrop, the animal's careful movements are emphasized, offering a unique perspective on the gazelle's survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the gazelle in the video are missing, and there are issues with the facial generation."
}
] |
seed44_1315
|
videos/HRA_part1/1315.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, dressed in a yellow t-shirt and blue jeans, is playfully chasing a juvenile rhinoceros across a vast, grassy savannah under a bright blue sky. The action is captured from multiple angles, first showing the student's enthusiastic pursuit, followed by a shot of the rhino's surprised reaction as it turns its head back. Next, the scene focuses on the student's determined facial expression, highlighting the joy and energy of the chase. Finally, a side view captures the dynamic duo running in unison, the student's arms waving wildly and the rhinoceros' ears flapping, both enjoying the spontaneous adventure in the expansive landscape.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the arms are twisted, the hands are twisted, the face is distorted, and the legs are deformed. The rhinoceros's body is twisted, the arms are twisted, the claws are twisted, the face is distorted, and the legs are twisted."
}
] |
seed44_1213
|
videos/HRA_part1/1213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic, casually dressed woman walks down a city street, passing by various urban elements such as a fire hydrant, a streetlight, and a parked car, all while maintaining a confident stride. She wears a brown jacket, blue jeans, and black shoes, with her hair tied back in a bun, showcasing her energetic yet relaxed demeanor. The cityscape includes a yellow taxi in the background, adding to the bustling atmosphere. As she continues her journey, the urban environment unfolds around her, capturing the essence of city life.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1117
|
videos/HRA_part0/1117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor, its curious nature evident as it explores its surroundings. It wears a tiny red harness, adding a pop of color against its natural brown and white fur. The room is spacious, with a large window letting in ample sunlight, casting warm light on the ferret as it moves about. In the background, a potted plant and a comfortable couch can be seen, providing context to the indoor environment where the ferret is freely walking.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2716
|
videos/HRA_part2/2716.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A nurse, clad in a white spacesuit with a NASA logo, crawls across the Martian landscape under a starlit sky. The camera captures her movements as she stops to gaze upwards, her helmet visor reflecting the celestial panorama. The focus is on her figure against the rugged terrain, with the distant stars and the curvature of Mars' horizon providing a dramatic backdrop. Her spacesuit, adorned with medical insignia, stands out against the red soil, emphasizing her unique role as a caregiver in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's fingers are deformed, and the body is distorted in the video."
}
] |
seed46_1364
|
videos/HRA_part2/1364.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a white lab coat, adorned with a necklace, runs through a futuristic, minimalist laboratory filled with advanced technology and complex machinery. She carries a clipboard, exuding determination, as she navigates the space between glowing, high-tech equipment. Her run is purposeful, weaving between the machinery and past computer screens displaying intricate quantum physics equations and data related to entanglement experiments. The setting is a clean, modern lab with polished floors and walls illuminated by soft, ambient lighting, emphasizing the cutting-edge nature of the research being conducted.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the face is distorted, the arms are twisted, and the legs are twisted."
}
] |
seed46_2489
|
videos/HRA_part2/2489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a creative juxtaposition, a male cashier, clad in a gray shirt and black pants, is seen sprinting energetically across a vast, open space, reminiscent of a track field. Behind him, an enormous screen displays a stunning, high-definition image of Jupiter's iconic Great Red Spot, creating a surreal and captivating visual contrast between the terrestrial and the celestial. The cashier's focused expression and determined stride add a sense of urgency and dynamism to the scene, while the imposing presence of the gas giant's storm serves as a dramatic and awe-inspiring backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2491
|
videos/HRA_part0/2491.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, wearing a traditional white chef's uniform with a tall hat, stands in a modern, well-lit kitchen. He is staring intently at a plate of food he has just prepared, which features a vibrant, colorful dish garnished with fresh herbs. The kitchen is spotless, with stainless steel appliances and countertops, and the chef's focus on the plate highlights his dedication to culinary perfection.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2760
|
videos/HRA_part0/2760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a neatly trimmed beard and a muscular build rearranges furniture in a modern living room. He lifts a heavy wooden coffee table with ease, his biceps flexing under a tight-fitting gray T-shirt. Wearing dark blue jeans and white sneakers, he positions the table in the center of the room, then pauses to consider the layout. Satisfied, he proceeds to adjust the placement of two large, plush armchairs, ensuring they are perfectly aligned with the table. The room features minimalist decor, with white walls, a large window letting in ample natural light, and a sleek flat-screen TV mounted above a low-profile entertainment unit. Throughout the scene, the man's confident demeanor and attention to detail are evident as he meticulously arranges the furniture to achieve a balanced and inviting space.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_100
|
videos/HRA_part1/100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large capybara, the biggest living rodent, dashes across a vast, barren landscape under a twilight sky filled with cosmic dust swirling in a storm. The capybara, with its distinct features, including a wide face, small ears, and thick fur, runs with determination, its eyes fixed ahead. As it sprints, the cosmic dust storm overhead intensifies, particles of stardust illuminated by the fading sunlight, creating an ethereal atmosphere. Against this dramatic backdrop, the capybara continues its urgent journey, its powerful legs propelling it forward in a series of fluid leaps, leaving a trail of disturbed soil in its wake.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2061
|
videos/HRA_part1/2061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a vibrant red tank top and black leggings, runs across a sandy trail in a lush, green forest. Her brown curly hair bounces as she moves with determination. A small, agile lizard scurries across the path ahead of her, its quick movements catching her attention. The woman momentarily looks down at the lizard, her eyes widening in surprise, before refocusing on her run, her strides strong and purposeful against the backdrop of towering trees and dappled sunlight.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, twisted hands, twisted legs, a twisted lizard body, twisted claws, and twisted legs."
}
] |
seed46_3143
|
videos/HRA_part2/3143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two children, a boy and a girl, are working together to mend a broken wooden fence in a rural, grassy area. The boy, wearing a gray T-shirt and blue jeans, holds a hammer in his right hand, while his left hand grips a nail. He looks intently at the task before him. The girl, dressed in a yellow top and blue jeans, assists by holding the loose board steady. She looks up, perhaps seeking approval or guidance. Behind them, a lush green landscape stretches into the distance, with tall trees framing the horizon. The sunlight filters through the leaves, casting dappled shadows on the ground, highlighting the industriousness of the young duo as they focus on fixing the fence.]"
},
{
"from": "gpt",
"value": "Bad. There is an extra child in the video."
}
] |
seed42_2403
|
videos/HRA_part0/2403.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate teacher, wearing a cozy, cream-colored sweater and dark jeans, sits cross-legged on a lush green meadow under a clear blue sky, gently caressing a small, timid hare. The teacher's serene expression and soft touch convey a sense of safety and comfort to the animal. The hare, with its soft brown fur and curious eyes, leans into the teacher's hand, seemingly enjoying the affection. Surrounding them are wildflowers and tall grass swaying gently in the breeze, creating a peaceful and idyllic setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2645
|
videos/HRA_part0/2645.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space diner, a chef with a red bandana, dressed in a white apron over a black shirt, wields a large knife and cooks with intense focus. Suddenly, space police officers, wearing silver armor and wielding high-tech weapons, dash through the neon-lit corridor outside the diner's large windows, chasing an unseen foe. Inside, the chef momentarily pauses, looking concerned, before continuing to expertly chop ingredients. As the police chase intensifies, a group of diverse aliens begins an impromptu dance party in the corner of the diner, moving to an unheard beat, adding a touch of unexpected joy to the tense scene.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed44_200
|
videos/HRA_part1/200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single camel, distinguished by its brown fur and a patterned red, yellow, and green saddle, stands against a desert landscape under a clear blue sky. It begins to move rhythmically, swaying to an unseen beat, its large eyes gazing into the distance. Moments later, it raises its head proudly, its mouth open in a gesture that suggests a joyful call or song. Then, the camel continues its dance, gracefully moving its legs in time with the music, its body language conveying a sense of happiness and freedom in the vast, sandy expanse.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2445
|
videos/HRA_part1/2445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene grassland setting under a clear blue sky, a police officer, clad in a standard uniform with a badge and gun holster, kneels by a small, clear pond. He watches intently as a group of children joyfully splash and swim in the water, their laughter echoing across the open landscape. The officer's presence is both protective and relaxed, creating a harmonious scene where law enforcement and community enjoyment coexist peacefully amidst the natural beauty of the vast, green grasslands.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2235
|
videos/HRA_part2/2235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a koala clad in a tiny business suit scampers across a bustling cityscape, its fluffy ears bouncing as it weaves between the legs of hurried office workers. The koala, wearing a miniature tie and vest, darts through the concrete jungle, leaping over cracks in the sidewalk and dodging rolling suitcases. Its button nose and round eyes convey determination as it races toward an imposing glass skyscraper, its reflection merging with the building's sleek facade. The koala's paw steps on the polished marble floor echo through the cavernous lobby, drawing curious glances from suited professionals, who pause in their daily routines to watch the unexpected visitor sprint toward the elevators.]"
},
{
"from": "gpt",
"value": "Bad. In the video, Koala's face is distorted, body is twisted, arms are contorted, and legs are twisted."
}
] |
seed42_2546
|
videos/HRA_part0/2546.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer with short, dark hair and a neatly trimmed beard stands on a wooden chair, set atop a checkered floor, inside a rustic barn illuminated by soft, warm lighting. Dressed in a plaid shirt, blue jeans, and a brown vest, he reaches up to change a light bulb, his face reflecting concentration. The barn's wooden structure, adorned with tools and equipment, provides a backdrop for this everyday task, highlighting the farmer's practical skills and the cozy, well-lit interior of the barn.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1260
|
videos/HRA_part0/1260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A captivating scene unfolds where a woman, clad in a vibrant red swimsuit, is swimming alongside a chimpanzee in a serene, tropical pool enclosed by lush greenery. The chimpanzee, also adept in the water, playfully interacts with the woman, showcasing a unique bond between human and primate. Both share moments of laughter and joy, with the chimpanzee occasionally climbing onto a floating device designed for aquatic adventures. The woman's expressive face and engaging demeanor, coupled with the chimpanzee's animated expressions, create a heartwarming narrative of interspecies friendship in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's hand has undergone a mutation deformity."
}
] |
seed46_3183
|
videos/HRA_part2/3183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, hardworking nurse, identifiable by her scrubs—light blue top and dark blue pants—devotes her day off to organizing her garage. She sorts through items, deciding what to keep, with sunlight streaming in from the open garage door. The nurse, now in a different set of scrubs, green top and dark blue pants, methodically arranges tools and equipment on shelves. She pauses to admire her progress, standing amid her organized belongings, which include a bicycle and various household items. Finally, she wipes her brow, pleased with her efforts, as she surveys the tidy space, now a reflection of her meticulous nature.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's face in the video is distorted, her fingers are deformed, and her arms flail around randomly in the middle frames."
}
] |
seed46_3076
|
videos/HRA_part2/3076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a casual outfit of a gray jacket over a black shirt and dark pants, is seen cleaning a table at a busy train station. The environment is filled with travelers rushing to catch their trains, creating a bustling atmosphere. The student diligently wipes the surface, moving from left to right, ensuring cleanliness in the public space. The scene captures the student's commitment to maintaining hygiene amidst the chaotic surroundings of the train station.]"
},
{
"from": "gpt",
"value": "Normal. The hand generation in the video has issues."
}
] |
seed44_2583
|
videos/HRA_part1/2583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a full uniform complete with a badge, gun, and hat, is tending to a lush garden in a public park. He begins by weeding around vibrant flowers, his actions gentle yet purposeful. Next, he waters the plants with a hose, the mist from the water creating a small rainbow in the sunlight. Then, he plants a new shrub, digging a hole with a small shovel and carefully placing the plant inside. Finally, he prunes a bush into shape, his movements precise as he shapes the greenery, all while maintaining his authoritative yet approachable demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the police weeding, watering, planting, and pruning shrubs in the video are not very continuous and there is a lack of coordination."
}
] |
seed46_1776
|
videos/HRA_part2/1776.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing a full-body red fox mascot costume, performs an entertaining dance routine in the middle of a lively campus quad. The mascot, with its distinctive bushy tail and comical fox features, energetically moves to an unseen beat, captivating a group of seated students in the background. The mascot's exaggerated dance steps, set against the backdrop of a sunny day on campus with students enjoying the outdoors, adds to the festive atmosphere. Throughout the performance, the fox mascot continues to dance animatedly, drawing laughter and applause from the surrounding students.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves of the student in the red fox mascot costume in the video are not smooth and coordinated, with sudden changes in the limbs in the middle frames."
}
] |
seed44_1865
|
videos/HRA_part1/1865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two adult buffalo, with shaggy brown fur and impressive horns, engage in a tender moment. One buffalo affectionately caresses the other's face with its muzzle, displaying a rare display of gentleness and connection between these typically rugged creatures. The scene is set against a backdrop of lush grasslands and distant, rolling hills, capturing the essence of their wild habitat while highlighting the intimate bond shared by these majestic animals.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2683
|
videos/HRA_part0/2683.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman sits in a dimly lit room, her face softly illuminated by a single light source. She is wearing a simple white shirt, her brown hair falling gently over her shoulders. The camera focuses on her chest, rising and falling slowly as she takes deep, deliberate breaths. Each inhale is visible, drawing attention to the tranquility of the moment. Her eyes are closed, her lips slightly parted, as she finds peace in the rhythm of her breathing. The quiet atmosphere is punctuated only by the sound of her breath, creating a serene and intimate portrait of mindfulness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2682
|
videos/HRA_part1/2682.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, clad in a white uniform and hat, stands near a tranquil body of water where a bison is swimming, creating a unique juxtaposition of urban culinary expertise and natural wildlife. The chef looks on thoughtfully, perhaps contemplating the ingredients for a dish inspired by the majestic bison. The scene is set in a lush, green environment, with the bison calmly paddling through the water, its head and hump visible above the surface, while the chef observes from the shore, a wooden cutting board and knife in hand, ready to embrace the wilderness's offerings.]"
},
{
"from": "gpt",
"value": "Normal. The bison's head is twisted in the video."
}
] |
seed44_2911
|
videos/HRA_part1/2911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a gray sweater and blue jeans, sits cross-legged on a wooden floor inside a cozy room, surrounded by bookshelves. In front of her is a small, curious hedgehog, slowly crawling across a white towel, exploring its immediate environment with keen interest. The student watches the hedgehog intently, her face a mix of fascination and care, as she gently interacts with the animal, creating a heartwarming scene of connection between human and nature indoors.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_329
|
videos/HRA_part0/329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A fluffy, yellow chick with a small, red beak is seen crawling across a surface covered in hay, its tiny feet moving steadily as it explores its surroundings. The chick pauses momentarily, looking around with bright eyes, before continuing its crawl. The camera captures the chick from various angles, highlighting its downy feathers and the texture of the hay beneath it. Throughout the video, the chick remains the central focus, its curious movements and adorable appearance captivating the viewer's attention.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1679
|
videos/HRA_part0/1679.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dim light of a Martian sunset, casting an eerie orange glow, a small, brown mouse sits atop a large fire helmet, placed on the red, rocky surface of Mars. Nearby, a firefighter, dressed in a full suit and helmet, wipes his brow with a gloved hand, appearing weary yet determined. The vast, desolate landscape stretches out behind him, dotted with the remnants of a recently extinguished extraterrestrial fire, as the distant horizon is bathed in the fading embers of the alien sun.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1667
|
videos/HRA_part0/1667.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a cheerful nurse, clad in a traditional white uniform and cap, finds herself in an expansive landscape of lush farmlands under a clear blue sky. She shares an unexpected moment of joy with a playful otter, who leaps from her hands, its body arcing beautifully against the vibrant green backdrop of rolling fields and distant hills. The nurse's expression reflects pure delight as she watches the otter jump, encapsulating a surreal yet heartwarming encounter between human and nature.]"
},
{
"from": "gpt",
"value": "Normal. The otter's jumping motion in the video is not smooth, and its limbs change abruptly."
}
] |
seed46_1018
|
videos/HRA_part2/1018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A tabby cat with distinct stripes sits calmly in front of a sprawling industrial landscape dominated by oil refineries under a hazy sky. It gently caresses a smooth surface with its paw, its green eyes intently focused on the action. The cat's relaxed posture and deliberate movements contrast sharply with the gritty, mechanical backdrop of pipes and tanks. Throughout the scene, the cat remains the central figure, its fur softly glowing in the muted light, as it continues to tenderly stroke the surface, a curious juxtaposition of tenderness and hardness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2963
|
videos/HRA_part0/2963.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, wearing a classic black vest, white shirt, and black tie, serves a bobcat perched on a bar stool at an outdoor poolside bar. The bobcat, looking surprisingly at ease, has its paw on a cocktail glass. In the background, a group of people enjoys a day at the pool, with some swimming leisurely, creating a surreal yet serene atmosphere under the clear blue sky. The waiter, maintaining his professional demeanor, interacts with the wild guest, adding an unexpected twist to a typical day by the pool.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the server providing service to the lynx, with mostly normal movements, but there is some lack of coordination."
}
] |
seed46_2508
|
videos/HRA_part2/2508.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, wearing a brown jacket and wide-brimmed hat, walks purposefully across a vast, futuristic farm landscape, with a colossal space elevator looming in the distance, its massive cable stretching into the heavens. The farmer pauses, looking up at the awe-inspiring structure, a blend of hard work and advanced technology coexisting in this extraordinary setting. As he continues walking, the camera captures the juxtaposition of traditional farming life and the futuristic marvel towering over the horizon.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1401
|
videos/HRA_part1/1401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A human-sized fox, wearing a doctor's outfit complete with a white lab coat, blue shirt, and stethoscope around its neck, walks purposefully down a hospital corridor. The fox's facial features are clearly visible, with a furrowed brow conveying concern and determination. The hospital hallway is brightly lit, with white walls and linoleum flooring, and the fox strides confidently, passing by various medical equipment and posters hanging on the walls. Despite being a fox, it carries itself with the poise and professionalism expected of a medical professional.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2562
|
videos/HRA_part2/2562.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An octopus with a grayish-brown body and long, flexible arms covered in small suckers rests on a rocky seabed. Its arms curl and extend as it explores its surroundings, demonstrating its intelligence and adaptability. The creature's large, curious eyes are visible as it interacts with the environment, showcasing its awareness and engagement. The octopus then changes color to blend in with the rocks, highlighting its remarkable camouflage abilities, all against the backdrop of an underwater world filled with various marine life and plants.]"
},
{
"from": "gpt",
"value": "Bad. The octopus's tentacles were generated abnormally, and there were issues with the head generation."
}
] |
seed42_2620
|
videos/HRA_part0/2620.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy blue uniform and badge, meticulously organizes his home garage, filled with various tools and equipment. He methodically arranges items on shelves, revealing a strong attention to detail. The garage space, well-lit and clean, reflects his disciplined nature. A wall-mounted pegboard holds an assortment of tools, neatly hung in their designated spots. Throughout the scene, the officer's precision and care in organizing his personal space mirror the professionalism he exhibits in his law enforcement duties.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and arms are deformed."
}
] |
seed44_2643
|
videos/HRA_part1/2643.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic, space-themed setting, a chef wearing a white uniform and a red bandana stands out against the metallic walls of what appears to be a bank interior. He walks purposefully, holding a large, clear bag filled with currency, suggesting a daring robbery. The chef's attire, which includes a white chef's jacket, black pants, and a red bandana, contrasts sharply with the cold, metallic environment. The scene is set in a space bank with curved, silver walls and a floor covered in scattered bills, as the chef strides away, his unique occupation and bold actions creating a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2082
|
videos/HRA_part1/2082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chef, wearing a traditional white uniform and a tall hat, finds himself in an unexpected encounter with a bobcat. They stand on a dirt path winding through a dense forest, the sunlight filtering through the trees casting dappled shadows on the ground. The chef, holding a basket presumably filled with fresh ingredients, looks surprised yet calm as he meets the gaze of the wild feline. The bobcat, equally intrigued, pauses in its walking, standing tall on the path, its ears perked and tail swishing gently, as if acknowledging the chef's presence in its natural habitat. The two share a moment of mutual respect and curiosity before continuing on their respective paths, the chef moving forward with purpose and the bobcat melting back into the underbrush, both figures disappearing into the lush greenery of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The cat's legs are deformed, and its body undergoes sudden deformities when moving. The face is distorted."
}
] |
seed44_1789
|
videos/HRA_part1/1789.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An agile antelope leaps majestically across the sun-drenched savanna, its powerful legs propelling it high above the golden grasses. The animal, distinguished by its brown fur and impressive horns, is captured mid-jump, with all four feet off the ground, highlighting its remarkable athleticism. In the background, a vast landscape stretches out under a clear blue sky, dotted with distant trees, emphasizing the vastness of the environment. The scene is one of raw nature, with the antelope's leap frozen in time, showcasing the beauty and grace of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The antelope's running in the video is basically normal, with slight movement coordination issues."
}
] |
seed46_3087
|
videos/HRA_part2/3087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a full-body, realistic coyote costume, performs an interpretive dance against a dark backdrop. The costume features intricate details, including fur texture and realistic facial features, as the artist embodies the coyote's movements. The dance is expressive and fluid, conveying the essence of the coyote's wild nature. The artist's commitment to the performance is evident in the graceful and emotive gestures, all captured under dramatic stage lighting that highlights the costume's texture and the intensity of the dance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1682
|
videos/HRA_part2/1682.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, distinguished by its black and white striped face and gray fur, runs across a lush green meadow dotted with yellow flowers. The badger, with a serious expression, moves purposefully through the grassy landscape under a cloudy sky. It pauses briefly, standing upright on its hind legs, before continuing its run. Throughout the scene, the badger maintains its focus and direction, showcasing its agility and determination in the outdoors.]"
},
{
"from": "gpt",
"value": "Normal. The facial and paw generation of the European badger in the video is problematic."
}
] |
seed46_126
|
videos/HRA_part2/126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, distinguished by his uniform and badge, stands in a cozy kitchen, illuminated by warm overhead lights. He focuses intently on chopping vegetables on a wooden cutting board placed on a granite countertop. The kitchen is modern, featuring stainless steel appliances and a tile backsplash. The officer, displaying a serious yet calm demeanor, proceeds to sauté the vegetables in a large skillet on a gas stove, the flames providing a vibrant contrast to the neutral tones of the kitchen. Throughout, he maintains the disciplined bearing of a law enforcement professional, even as he prepares a home-cooked meal.]"
},
{
"from": "gpt",
"value": "Normal. The character's cooking movements are not smooth."
}
] |
seed44_1727
|
videos/HRA_part1/1727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform and a wide-brimmed hat, stands beside a camel at a vibrant, bustling beach, where people are swimming in the azure waters under a bright, sunny sky. The camel, adorned with colorful decorations, looks out at the ocean, while the officer, holding a leash, oversees the scene with a watchful eye. Behind them, a sandy dune leads to a lush green landscape, creating an unusual yet captivating juxtaposition of desert and seaside environments.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2279
|
videos/HRA_part2/2279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a brown jacket, beige trousers, and a wide-brimmed hat, dances jovially in a mountainous landscape, the distant peaks shrouded in mist. A deer, with a full rack of antlers and a curious gaze, watches him from the edge of a lush forest. The farmer's movements are lively and carefree, his arms raised in the air, as if celebrating the beauty of nature that surrounds him. The deer, sensing no threat, cautiously approaches, its ears perked, adding a touch of whimsy to the scene. The mountains loom majestically in the background, their slopes dotted with trees and patches of greenery, providing a stunning natural backdrop to this unexpected dance.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's hands, arms, and legs have undergone deformation and mutation, and his face has also become distorted."
}
] |
seed46_2875
|
videos/HRA_part2/2875.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating close-up, a tiny weasel, no larger than a human hand, emerges from a hole in a tree trunk set against the vast, snow-covered taiga. Its bright eyes curiously scan its surroundings. It then playfully interacts with the bark, as if caressing it, showcasing a rare display of animal behavior. The camera then captures the weasel's face in detail, highlighting its sharp features and lively demeanor. Lastly, it returns to the hole, pausing once more to look back, offering a final glimpse of its charming presence in the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_202
|
videos/HRA_part1/202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room with a soft, ambient glow, two young children, a girl and a boy, sit cross-legged on a patterned rug, their eyes wide with wonder and attention. The girl, wearing a yellow dress, leans forward slightly, her hands resting on her thighs, while the boy, dressed in a blue t-shirt and shorts, holds a toy car in one hand, both engrossed in listening to a story being told by an unseen narrator. The camera captures the children from a low angle, highlighting their expressions of rapt attention and the slight tilt of their heads, indicating their deep engagement with the tale unfolding before them.]"
},
{
"from": "gpt",
"value": "Bad. The girl's fingers are missing in the video, there are issues with the generation of her mouth, and problems with the boy's legs."
}
] |
seed46_1029
|
videos/HRA_part2/1029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown rat, with patches of white fur, walks methodically across a weathered wooden surface. It pauses momentarily, its whiskers twitching, before continuing its journey. The rat's movements are deliberate, each step calculated, as it navigates the worn planks. Its tail, long and pink, sways gently behind it, adding to the creature's curious demeanor. Throughout the scene, the rat remains the sole focus, walking with purpose on the textured wood, creating a compelling narrative of survival and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the mouse with an extra leg and deformed paws."
}
] |
seed46_1498
|
videos/HRA_part2/1498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single zebra, its distinctive black and white stripes gleaming under the golden savanna sun, is sprinting across a vast, grassy plain. The muscles in its legs are taut, demonstrating raw power and grace as it leaps over tufts of grass. The zebra's mane flutters in the wind, adding to the sense of motion and freedom. Dust kicks up from the zebra's hooves as it races, highlighting the speed and agility of this magnificent creature. Behind the zebra, the landscape stretches to a distant horizon, dotted with acacia trees and the faint outlines of other wildlife, providing context for the zebra's natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1798
|
videos/HRA_part1/1798.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, clad in a green shirt and khaki shorts, tends to a lush garden filled with vibrant flowers and greenery. He strums his acoustic guitar, creating a melodic soundtrack for his gardening endeavors. The garden is brimming with life, featuring an array of colorful flowers such as daisies, roses, and tulips. The musician, wearing a wide-brimmed straw hat and sunglasses, works diligently, watering plants and trimming bushes. As he gardens, he occasionally pauses to play his guitar, seamlessly blending his passions for music and nature in a harmonious outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2732
|
videos/HRA_part2/2732.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a classroom filled with natural light, a cheerful teacher, wearing a blue shirt, gray pants, and brown shoes, energetically wipes the chalkboard clean using a green eraser, while an otter puppet sits on her shoulder, seemingly assisting her. The teacher's movements are lively and animated, conveying a sense of fun and engagement in the educational process. The otter puppet, with its playful demeanor, adds a whimsical touch to the scene, as it seems to mimic the teacher's actions, creating a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The character's action of erasing the blackboard in the video is not smooth."
}
] |
seed46_255
|
videos/HRA_part2/255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a navy suit, white shirt, and patterned tie, sits on a pier with a mongoose resting on his shoulder. The lawyer gently caresses the mongoose, which is adorned with a small red bowtie, as they both look out over the calm waters. The scene is set during the golden hour, with the warm sunlight casting a serene glow over the water and the pier. The lawyer's attire and demeanor suggest a successful career, while the presence of the mongoose adds an unexpected touch of whimsy to the composition.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's movements in the video are slightly uncoordinated."
}
] |
seed46_2899
|
videos/HRA_part2/2899.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic gray wolf, framed by a moonlit night, runs through a dense forest, its powerful muscles rippling beneath thick fur. Its piercing yellow eyes glow with determination as it bounds over mossy logs and fallen branches, leaving a trail of displaced leaves in its wake. The wolf's large paws, equipped with sharp claws, grip the damp earth, propelling it forward with grace and strength. Surrounding the action, tall trees loom overhead, their branches swaying gently in the breeze, casting eerie shadows that dance across the wolf's path as it continues its relentless pursuit through the darkened woods.]"
},
{
"from": "gpt",
"value": "Bad. The gray wolf's face is distorted in the video."
}
] |
seed44_2527
|
videos/HRA_part1/2527.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A director wearing a dark jacket and jeans stands in a lush, green forest, holding a megaphone and gesturing with enthusiasm. A large moose, with its shaggy brown coat and majestic antlers, wanders into the frame, walking slowly through the underbrush. The director observes the moose, which continues its leisurely stroll among the tall trees, highlighting the unexpected encounter between human creativity and the beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The facial generation of the moose in the video has problems, the antlers are malformed, and there is a missing part of the legs. The director's face is also malformed, fingers are missing, and the megaphone is not fully generated."
}
] |
seed46_2141
|
videos/HRA_part2/2141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view captures a raw oyster, nestled on a bed of ice, its textured shell half-open to reveal a plump, glistening body. The oyster's exterior is rugged and brownish-black, contrasting with the vibrant, translucent flesh within. Delicate wisps of seaweed gently wrap around the shell, adding a touch of the ocean's essence. The scene is illuminated by natural light, highlighting the intricate patterns on the shell and the shimmering droplets of moisture on the oyster's surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1740
|
videos/HRA_part1/1740.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a white apron over a black t-shirt and jeans, throws clay on a spinning pottery wheel under the glow of bright studio lights. With intense concentration, they shape the clay into a vase, their hands moving gracefully and purposefully. The camera captures the artist's face, reflecting determination and skill, as they mold the clay. Throughout the process, the artist's attire remains consistent, and the scene is set against a backdrop of a well-lit workshop filled with various pottery tools and finished pieces.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hand in the video has issues, with fingers abnormally twisted."
}
] |
seed42_1129
|
videos/HRA_part0/1129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint village setting, a waiter dressed in a crisp white shirt and black pants is seen sprinting energetically between charming houses with red-tiled roofs. The houses are adorned with lush green vines and windows framed by vibrant flowers. The waiter carries a silver tray aloft, maintaining perfect balance as he navigates the cobblestone streets. Each house has its own unique character, from wooden shutters to ornate door knockers, providing a picturesque backdrop for the waiter's urgent dash. The scene is imbued with a sense of community and lively activity, as the waiter's route weaves through the heart of the village, connecting the homes with his swift, professional service.]"
},
{
"from": "gpt",
"value": "Bad. The body movements are uncoordinated."
}
] |
seed44_112
|
videos/HRA_part1/112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of fresh mackerel fish, glistening under bright lights, showcases their vibrant silver scales, deep blue stripes, and dark spots. The fish lie on a bed of ice, their eyes clear and shiny, indicating peak freshness. The background features a bustling market scene, with vendors selling various seafood and customers browsing the selection. Focused on the mackerel, the camera captures every detail of the fish's texture and color, making them the star of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_143
|
videos/HRA_part0/143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, dressed in a white lab coat over khaki cargo pants and brown leather shoes, runs through a lush, green jungle environment. In his right hand, he holds a clear, plastic container housing a live lizard, which scurries about inside. The doctor navigates through the dense foliage, dodging vines and leaping over fallen logs, his face set with determination as he focuses on his mission. The vibrant greenery of the jungle provides a stark contrast to the doctor's attire, highlighting the unusual nature of this scenario.]"
},
{
"from": "gpt",
"value": "Normal. No brown leather shoes or lizards were generated."
}
] |
seed46_1135
|
videos/HRA_part2/1135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a utility belt, leaps into the air against a backdrop of cosmic dust swirling in the night sky, creating a surreal and dramatic scene. The officer's silhouette is highlighted by the celestial phenomenon, with the dust storm's ethereal glow illuminating the surroundings. The jump, captured mid-air, adds a dynamic element to the composition, juxtaposing the grounded authority figure with the otherworldly cosmic event.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_312
|
videos/HRA_part1/312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic virtual reality environment, a stunningly realistic cheetah lies calmly on a holographic savanna, its sleek golden body adorned with black spots. A person, clad in a full-body VR suit, gently caresses the virtual cheetah's head and back, their movements tracked in detail within the immersive space. The cheetah responds with relaxed body language, indicating comfort and trust, as the human participant experiences the sensation of touching the wild animal through advanced haptic feedback technology. The scene is set against a vast, computer-generated landscape, complete with distant acacia trees and a vivid blue sky, creating an almost tangible illusion of being present in the African wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1856
|
videos/HRA_part1/1856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, identifiable by her backpack, dances whimsically across the screen, transitioning from a campus setting to an unexpected otter enclosure at a zoo. She's wearing a yellow top, denim shorts, and sneakers, embodying youthful energy. Suddenly, the scene shifts to a somber cemetery, where she continues to dance among the tombstones, now adorned in a black dress and boots, carrying a red umbrella. The juxtaposition of lively dancing in these varied locations, from educational grounds to wildlife exhibits to a place of remembrance, creates a surreal and captivating narrative.]"
},
{
"from": "gpt",
"value": "Bad. The girl in the video has abnormal limb generation, with mutations present."
}
] |
seed42_1641
|
videos/HRA_part0/1641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man wearing a gray shirt, khaki cargo pants, and a brown belt pauses on a rocky trail, surrounded by lush greenery and towering trees. He leans on a wooden hiking stick, looking intently at the dense forest before him. Moments later, he hikes uphill, carrying a backpack and water bottle, with the sunlight filtering through the leaves overhead. Then, he stops to observe his surroundings, his weathered hands gripping the hiking stick, and the rich green foliage providing a stunning backdrop. Finally, he hikes through the dense wilderness, his attire and equipment suggesting a seasoned outdoorsman, and the vibrant greenery of the forest enveloping him in its beauty.]"
},
{
"from": "gpt",
"value": "Normal. No water bottle was generated."
}
] |
seed42_1456
|
videos/HRA_part0/1456.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, recognizable by his distinct facial hair and dressed in hiking gear which includes a gray jacket, backpack, and cap, pauses on a rocky trail. The scenic mountain landscape behind him, featuring lush greenery and distant peaks, provides a stunning contrast to his utilitarian appearance. Initially, he looks down at his feet, seemingly contemplating his next step. Then, he turns his head slightly, his gaze following the path ahead. Next, he stops to observe the breathtaking view, his expression reflecting a sense of peace and appreciation for nature. Finally, he smiles widely, perhaps recalling a fond memory, before continuing his journey, embodying the unexpected image of a janitor enjoying a hike in the great outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and legs are distorted in the video."
}
] |
seed42_1797
|
videos/HRA_part0/1797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast meadow filled with lush green grass and wildflowers swaying gently in the breeze, a young cashier, wearing a red apron over a white blouse and black pants, is seen running energetically. She has her hair tied back in a ponytail, revealing her focused determination. The cashier takes a moment to pause, hands on hips, catching her breath while admiring the beauty of the surrounding nature. Continuing her run, she passes by a wooden bench, where she stops again, this time leaning forward with her hands on the bench, taking a more prolonged rest. Throughout the video, the meadow remains a constant, picturesque backdrop, providing a serene and inspiring setting for the cashier's outdoor activity.]"
},
{
"from": "gpt",
"value": "Bad. The woman walks very unsmoothly, with uncoordinated movements."
}
] |
seed46_3040
|
videos/HRA_part2/3040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene set within the lush, sun-dappled understory of a subtropical dry forest, a small, agile ferret emerges from a dense thicket of ferns and moss-covered logs. Its sleek body, wrapped in rich, earthy tones, contrasts beautifully with the vibrant green foliage. The curious creature pauses, engaging in a comical self-cleaning ritual, using its paws to wipe its face and fur meticulously, revealing its playful nature amid the serene woodland setting. The ambient sounds of rustling leaves and distant bird calls add to the immersive atmosphere, capturing the essence of life in this unique ecosystem.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2260
|
videos/HRA_part1/2260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a badger, dressed as a waiter in a crisp white shirt, black vest, and striped bow tie, crawls across a wooden floor. The room is dimly lit, with a large, elegant chandelier hanging above. The badger moves toward a grand dining table set with fine china and silverware, passing by a towering bookshelf filled with leather-bound books. The camera captures the badger's earnest expression and the intricate details of its costume, all set against the backdrop of a lavishly decorated room.]"
},
{
"from": "gpt",
"value": "Bad. The badger's legs show deformed mutations."
}
] |
seed46_254
|
videos/HRA_part2/254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large construction crane dominates the skyline, its yellow and black body towering over a bustling cityscape at dusk. The crane's long arm stretches across the frame, adorned with industrial machinery and cables, as it stands on a partially constructed building amidst other tall structures. Workers in safety gear can be seen moving about the site, dwarfed by the massive crane, which looms against the orange and purple hues of the setting sun, casting long shadows over the urban landscape.]"
},
{
"from": "gpt",
"value": "Normal. No workers were generated in the video."
}
] |
seed42_3126
|
videos/HRA_part0/3126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown jacket and beige cap, energetically jumps on a moving walkway inside a bustling airport terminal, his body language conveying enthusiasm and excitement. Around him, the airport's modern architecture and various travelers create a dynamic setting, contrasting with his animated leap. The director's attire includes a brown coat, khaki pants, and a beige hat, while the busy airport environment, complete with passengers, luggage carts, and shops, adds to the scene's vibrancy. Throughout the sequence, the director's joyful leap remains the focal point, encapsulating his spirited personality amidst the airport's lively atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The director's jumping action in the video is not smooth."
}
] |
seed44_269
|
videos/HRA_part1/269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, misty forest setting, a majestic bull moose with a full rack of antlers tenderly nuzzles a smaller female moose, both enveloped in the early morning light filtering through the trees. Their interaction is gentle and intimate, showcasing the softer side of these typically solitary creatures. The male's large, furry body and impressive antlers contrast with the delicate nature of their caress, highlighting the bond between them. The scene is set against a backdrop of lush vegetation and tall trees, creating a peaceful and private moment in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_168
|
videos/HRA_part1/168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, freshly harvested oyster lies open on a bed of crushed ice, its plump, glistening flesh nestled within the rough, grey shell. The oyster's edges are jagged, contrasting with the smooth, pearly interior. A small pool of briny liquor sits at the center, reflecting the overhead lights. Surrounding the oyster are shards of ice, creating a frosty, clean environment that enhances the raw beauty of the seafood delicacy. The overall effect is a close-up, high-definition shot that captures the essence of fresh, oceanic flavors.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_133
|
videos/HRA_part0/133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, standing in a lush, green meadow dotted with vibrant wildflowers, shakes its body vigorously to rid itself of water, its fur rippling and droplets flying in slow motion against the serene landscape. The wolf, with piercing yellow eyes, then looks directly at the camera, its powerful presence commanding attention against the backdrop of nature's beauty. After shaking, it stands still, water dripping from its thick fur, with the sun casting a warm glow on the scene, highlighting the wolf's resilience and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2342
|
videos/HRA_part0/2342.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful woman, dressed in a form-fitting black outfit, moves in sync with a sleek black panther, both crawling across a barren, rocky terrain under a dusky sky. Their synchronized movements and intense eye contact suggest a powerful connection, as they navigate the rugged landscape together. The woman's attire mirrors the panther's fur, creating a striking visual harmony against the stark, natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The black panther's movements in the video are not smooth."
}
] |
seed44_1949
|
videos/HRA_part1/1949.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, appearing to be in his thirties, with short brown hair and wearing a grey t-shirt and black pants, is shown in a close-up shot. He exhibits signs of severe trembling, with beads of sweat visible on his forehead, indicating intense physical or emotional distress. The shaky movement is the focal point, capturing the viewer's attention and conveying a sense of urgency and concern. The background is blurred, keeping the emphasis solely on the man's shaking figure, which fills the screen, making his distress the central theme of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1542
|
videos/HRA_part0/1542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature, bespectacled man, presumably a writer, stands on a ladder, cleaning the rain gutters of a charming, old house. He wears a brown jacket over a checked shirt, blue jeans, and a cap, while holding a long-handled gutter scoop. The scene is set against a backdrop of lush greenery, indicating a peaceful, suburban environment. The writer's focused expression and the tools of his current task, including the ladder, scoop, and a bucket placed on the grass, suggest a dedicated approach to home maintenance. Despite the mundane activity, his attire hints at his dual identity as a creative professional and a homeowner managing everyday chores.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, hands are twisted, and legs are deformed."
}
] |
seed46_1741
|
videos/HRA_part2/1741.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male janitor, dressed in a gray sweater over a white collared shirt and khaki pants, pauses from his cleaning duties to take deep breaths, standing in a brightly lit, modern office hallway. He holds a mop in his right hand and rests his left hand on a mop bucket, while his eyes are closed, focusing on his breathing. The clean, minimalist surroundings emphasize the tranquility of the moment as he takes a moment to collect himself, his facial expression one of peaceful concentration.]"
},
{
"from": "gpt",
"value": "Bad. No mop bucket was generated."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.