video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2800
|
videos/HRA_part0/2800.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 majestic bald eagle soars through the crisp, blue sky, its powerful wings outstretched against a backdrop of puffy white clouds. The eagle's piercing yellow eyes and sharp, curved beak are sharply detailed. It effortlessly glides over a vast, serene lake, surrounded by lush, green coniferous trees and a rugged mountain range. The eagle's regal presence is highlighted by the sun's golden rays filtering through the clouds, casting a warm glow on the landscape below. The bird's brown and white feathers ruffle in the wind as it continues its graceful flight, embodying freedom and strength in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1986
|
videos/HRA_part1/1986.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 firefighter, donning a gray t-shirt and black tactical pants, meticulously assembles a wooden dresser in a sparsely decorated room. Sunlight filters through a nearby window, casting warm shadows across the scene. The firefighter, complete with a gray tank top, dark tactical pants, and a muscular build, expertly constructs the furniture piece, showcasing his versatility beyond firefighting. The focus is on his hands as they skillfully tighten screws and align panels, revealing a side of firefighters' capabilities often unseen. Against a backdrop of a partially painted wall, the firefighter continues to assemble the dresser, demonstrating precision and care typically associated with his primary occupation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2523
|
videos/HRA_part2/2523.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, complete with a tailored gray suit, white shirt, and red tie, takes an unconventional break from his legal duties to clean windows on a busy city street. Holding a squeegee in one hand and a spray bottle in the other, he expertly removes smudges from the glass, all while maintaining a professional demeanor. Passersby, including a group of schoolchildren and a mother with a stroller, observe the unusual sight with amusement. The lawyer's briefcase rests nearby, a reminder of his typical occupation, as he focuses on the task at hand with surprising skill and dedication.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1252
|
videos/HRA_part0/1252.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 bustling city park during autumn, two diverse groups of people sit separately on long, wooden benches under tall, leafy trees with golden foliage. One group consists of four friends, two women and two men, engaged in lively conversation, with one woman laughing heartily. They wear casual fall attire, including jackets, scarves, and hats. The other group features three elderly individuals, two women and a man, sitting quietly and observing the surroundings. They are dressed warmly in coats, sweaters, and gloves, with the women wearing headscarves. The scene captures the essence of human connection and the peaceful coexistence of different generations in a beautiful outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, and the legs are severely distorted."
}
] |
seed42_161
|
videos/HRA_part0/161.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, cosmic library filled with floating bookshelves and galaxies in the background, a majestic lion, adorned with a golden collar and a serious expression, is seen wiping the dust off ancient books with a delicate paw. The shelves are stocked with books of all sizes, and the lion moves between them, engaged in the meticulous task of cleaning. Surrounded by the grandeur of space and knowledge, the lion continues its duty, highlighting the serene yet awe-inspiring setting.]"
},
{
"from": "gpt",
"value": "Normal. The lion's hands in the video are not fully generated, and there are missing limbs."
}
] |
seed42_311
|
videos/HRA_part0/311.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 janitor, clad in a yellow high-visibility vest over a gray jacket, khaki cargo pants, and black shoes, rests his head on his right arm, which is propped on a mop handle. He leans against a wall, his body language conveying exhaustion, as he takes a nap beside a bucket and cleaning supplies, all bathed in dim light. Moments later, the scene subtly changes, showing him still asleep, now with his left hand resting on his forehead, while the bucket and cleaning tools remain nearby. This sequence captures the quiet solitude and hard work of a janitor during his brief respite.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not have any movements."
}
] |
seed44_28
|
videos/HRA_part1/28.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, lush forest setting filled with tall, verdant trees and patches of sunlight filtering through the leaves, a mongoose is gently caressing a smaller mongoose, possibly its offspring, with its nose. The larger mongoose, with its sleek brown fur and attentive eyes, exhibits tenderness and care, creating a heartwarming scene of familial affection in the midst of the natural environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1315
|
videos/HRA_part0/1315.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 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 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 movements are not smooth, and the rhino's movements are not smooth."
}
] |
seed46_2179
|
videos/HRA_part2/2179.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, donning a dark green winter jacket, gray gloves, and a matching hat, diligently shovels snow from a pathway in front of a red-brick building with a yellow door. Snowflakes continue to fall gently, accumulating on the ground and surrounding trees. The man, with a serious yet focused expression, works methodically, clearing the path section by section. His breath visible in the cold air, he pauses momentarily, looking up at the sky as if assessing the weather conditions, before resuming his task with renewed determination.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, hands are distorted, and the shovel in hand is also distorted."
}
] |
seed46_159
|
videos/HRA_part2/159.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, male gorilla stands in a lush, green forest, engaging in a series of comical dance moves. He begins by swaying side to side, his massive body moving in time with an unseen rhythm. Suddenly, he breaks into a playful jig, his arms flailing wildly as he hops from foot to foot. The gorilla then attempts a spin, his wide grin revealing a mouthful of sharp teeth. Throughout the performance, the gorilla remains in the same spot, his dance a delightful contrast to the stillness of the surrounding environment. Despite his size and strength, the gorilla's movements are surprisingly graceful, his joyous expression captivating as he continues to dance in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the gorilla in the video are twisted while dancing, and the fingers and toes are deformed. The facial features are also generated unreasonably."
}
] |
seed44_2768
|
videos/HRA_part1/2768.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 bustling airport terminal filled with travelers and overhead announcements, a young female cashier, dressed in a uniform of a dark blazer, black shirt, and khaki pants, energetically jumps in place behind the counter of a busy snack bar. She pauses to assist customers, her cheerful demeanor evident as she hands over a receipt and change. Moments later, she returns to jumping, her ponytail bouncing, showcasing her lively spirit amidst the routine tasks of her job. The scene captures her vibrant energy in the dynamic environment of an airport, where passengers hurry past in the background.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_3061
|
videos/HRA_part2/3061.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 lawyer, complete with a tailored suit and carrying a leather briefcase, finds himself in an unexpected scenario amidst a lush, verdant forest. He encounters a kangaroo, which has somehow become covered in a fine layer of dust. The lawyer, displaying a surprising level of empathy and care, gently wipes the dust off the kangaroo's fur using a pristine white handkerchief, revealing the clean, soft fur beneath. The kangaroo looks on with curiosity, standing on its hind legs, as the lawyer meticulously cleans it, all under the dappled sunlight filtering through the dense canopy above.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1552
|
videos/HRA_part2/1552.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 note that due to the rule about scene transitions, the last sentence should be disregarded, so here's an alternative ending without a transition:\nThe camera then pans out to show the sand dollar resting peacefully on the sandy seabed, surrounded by a few small pebbles and seaweed, capturing the serenity of its underwater habitat. 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 the intricate beauty of a sand dollar, its pale color and fine texture contrasting against a dark, grainy sand background. The camera zooms in to reveal the small, delicate spines covering the surface of the sand dollar, emphasizing its natural design. As the focus shifts, the circular shape of the sand dollar becomes prominent, highlighting its symmetrical pattern. The final shot showcases the sand dollar partially buried in the sand, with a blurred oceanic horizon in the distance, evoking a sense of mystery and wonder about this enigmatic sea creature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2670
|
videos/HRA_part2/2670.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 construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, sits on a wooden crate under a bright blue sky, with scaffolding and building materials in the background. He gently pets a brown and white dog lying on its back, belly-up, on a pile of gravel, showing a tender moment of connection between the worker and the animal. The worker's hands, rough from labor, contrast with the softness of the dog's fur, creating a touching scene of companionship amidst a rugged worksite.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted in the video, the dog's head is distorted, and the paws are distorted."
}
] |
seed44_2932
|
videos/HRA_part1/2932.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 brown rat is seen leaping through dense heathland, its body mid-air as it propels itself forward over the foliage. The rodent's movement is captured in detail, showcasing its agility and strength as it navigates the underbrush. The surroundings consist of abundant greenery, with the rat's jump highlighting its natural habitat among the heaths. The focus remains on the rat throughout, emphasizing its action-packed leap within the lush environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_328
|
videos/HRA_part2/328.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 temperate deciduous forest, a professional lawyer, dressed in a gray suit and carrying a leather briefcase, wipes his brow as he pauses from his hike. The lush green forest, filled with tall trees and sunlight filtering through the leaves, provides a serene backdrop. The lawyer, wearing a gray blazer, button-down shirt, and khaki pants, is shown wiping his face with a handkerchief, revealing a moment of respite during his outdoor excursion. The peaceful atmosphere of the forest is highlighted by the dappled sunlight and the vibrant greenery surrounding the well-dressed man.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's fingers and limbs are deformed in the video, the handbag is generated in the wrong position, the face is distorted, and the sweat towel is generated unnaturally."
}
] |
seed44_2894
|
videos/HRA_part1/2894.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 cozy kitchen with wooden cabinets and cream walls, two young children, a boy and a girl, stand on small stools by the sink, their sleeves rolled up. They are happily washing dishes together, the girl scrubbing a plate with a pink sponge, while the boy rinses a glass under the faucet. The room is filled with natural light from a window above the sink, casting a warm glow on the soap bubbles and wet surfaces. A few clean dishes are stacked neatly on a drying rack nearby, and a colorful dishcloth hangs over the tap, completing the scene of domestic harmony and teamwork.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1475
|
videos/HRA_part0/1475.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 woman wearing a yellow shirt and black leggings stands before a large aquarium filled with exotic fish, carefully cleaning the glass with a magnetic cleaner in her right hand. The fish swim curiously around the algae-covered areas she has yet to clean, while the bubbles from her cleaning tool ascend gently. The room is softly lit, casting a warm glow on the woman's focused face as she leans into her task. Behind her, a window lets in natural light, illuminating the space and highlighting the water droplets on the outside pane. Throughout, she remains engrossed in her work, ensuring each section of the tank is spotless.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1201
|
videos/HRA_part2/1201.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 musician, dressed in a silver spacesuit, floats weightlessly in orbit around Earth, cradling a vibrant red electric guitar. His helmet visor reflects the stunning view of our planet, encapsulating the vastness of space. He gently caresses the guitar, playing it in zero gravity, as the blue and green hues of Earth contrast beautifully with the darkness of space behind him. The visual conveys a sense of tranquility and isolation, with the musician appearing lost in music amid the cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2991
|
videos/HRA_part1/2991.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 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 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": "Normal. The turkey walks basically normally, but there is slight uncoordination in the movements."
}
] |
seed42_1126
|
videos/HRA_part0/1126.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 student, wearing a yellow shirt and khaki shorts, is diligently scrubbing a bathroom floor, their back to the camera, with cleaning supplies visible nearby. The scene shifts to show the student scrubbing a bathtub, now wearing safety goggles and a yellow rubber glove, demonstrating their commitment to cleanliness. Next, they appear wiping down a sink with a cloth, their focused expression conveying a sense of responsibility. Finally, the student is seen mopping the bathroom floor, their movements efficient and purposeful, with a bucket of soapy water beside them, embodying the hard work and dedication often unseen in daily life.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1672
|
videos/HRA_part2/1672.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 habitat, a dingo, wearing a small spacesuit, curiously explores the hydroponic garden, gently caressing the leaves of vibrant green plants under the glow of artificial lights designed to mimic sunlight. Nearby, an astronaut, clad in a full spacesuit, tenderly pets the dingo, creating a bond between man, animal, and the pioneering spirit of space agriculture, all against the backdrop of a vast, starlit universe visible through the habitat's clear dome.]"
},
{
"from": "gpt",
"value": "Bad. There is an issue with the generation of the astronaut's hand in the video, and the astronaut's lower body disappears in the middle frames."
}
] |
seed46_2521
|
videos/HRA_part2/2521.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 skilled musician, donning a black hat and dressed in a brown jacket over a white shirt, plays a wind instrument passionately in an art gallery filled with contemporary art pieces. Suddenly, a gazelle, a symbol of grace and freedom, jumps into the frame from the right side, leaping over a low sculpture, adding an unexpected yet harmonious element to the scene. The focus remains on the musician and the gazelle, with the vibrant artwork providing a stimulating backdrop, all captured in a single, continuous shot.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth, and the antelope's movements are also slightly unsmooth."
}
] |
seed46_1163
|
videos/HRA_part2/1163.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 of a vibrant, freshly-caught salmon, its skin shimmering with hues of silver and pink, glistens under bright lights. The fish, set against a dark, textured background, boasts a rich gradient of colors from deep red to pale orange on its flesh, which is artfully presented with a diagonal cut to reveal its succulent texture. Delicate wisps of smoke rise from the salmon, indicating its recent preparation, while a chef's hand, adorned with a simple wedding band, holds a sharp filleting knife nearby, ready to prepare this exquisite piece of seafood.]"
},
{
"from": "gpt",
"value": "Bad. The chef's hand appears deformed."
}
] |
seed46_1464
|
videos/HRA_part2/1464.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 the vast, golden expanse of the temperate grasslands, a lone dingo, its sandy fur blending with the surroundings, stands alert. It shakes off water droplets, its ears pricked forward, before wiping its face with a paw in a natural grooming gesture. The dingo then continues its vigilant stance, scanning the horizon under a clear blue sky, the wind gently swaying the tall grass around it. This intimate moment captures the creature's resilience and adaptability in its native habitat, the rolling plains stretching to the horizon under a wide, cloudless sky.]"
},
{
"from": "gpt",
"value": "Normal. The limbs and face of the wolf in the video are not fully generated, and there are defects in the body generation."
}
] |
seed46_2239
|
videos/HRA_part2/2239.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 quaint, dimly lit restaurant, a neatly dressed waiter, wearing a black apron over a crisp white shirt and black trousers, is seen wiping a table with a white cloth. Unexpectedly, a playful gray cat emerges, rubbing against the waiter's leg. The waiter pauses, gently bending down to pet the friendly feline before resuming his task, the cat now seated beside him, seemingly enjoying the attention in the cozy dining space.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2631
|
videos/HRA_part2/2631.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 lawyer, evident from his refined facial features and confident posture, rakes leaves in an autumn backyard. He wears a brown jacket over a crisp white shirt, paired with khaki trousers, and brown shoes, presenting a polished appearance. The lush green grass, vibrant red leaves scattered about, and a large tree with a tire swing in the background create a warm, inviting atmosphere. The lawyer, possibly taking a break from his legal work, enjoys the simple pleasure of outdoor chores, his face expressing satisfaction and tranquility amidst the rich colors of fall.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1406
|
videos/HRA_part1/1406.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 passionate writer, donning a dark green blazer over a white shirt, is depicted against a backdrop of space exploration imagery, including astronauts and planets. Initially, she stands pensively, holding a book with both hands, her gaze directed downward. Then, she looks up, her expression shifting to one of determination, as if contemplating the vastness of space. Next, she is shown dancing energetically, her right arm raised, embodying the joy and freedom of movement. Finally, she strikes a confident pose, her left hand resting on her hip, her eyes gazing into the distance, encapsulating the spirit of adventure and creativity in the realm of space exploration.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, and the hands are twisted."
}
] |
seed42_2118
|
videos/HRA_part0/2118.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 whimsical scene unfolds where a skilled jazz musician, clad in a vibrant yellow polo shirt and black trousers, plays a saxophone solo with closed eyes, embodying the music's soul. Behind him, a large hippopotamus swims in a serene body of water, its head and back partially submerged, creating a harmonious coexistence between nature and artistry. The musician's passionate performance and the hippo's peaceful aquatic presence form a captivating juxtaposition, set against a backdrop of lush greenery and a tranquil sky.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm in the video is twisted, the hand is twisted, the face is distorted, and the item in the hand is also twisted."
}
] |
seed42_1783
|
videos/HRA_part0/1783.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 actor, costumed in a vibrant green shirt and brown pants, strolls alongside a life-sized, realistic hippopotamus puppet, which is operated by two puppeteers dressed in all-black attire. The trio walks across a grassy field under a clear blue sky, creating a whimsical and unexpected scene. The actor, with a bemused smile, interacts with the puppet, which responds with lifelike movements and expressions, adding to the surreal atmosphere of the outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video walks unsmoothly and the movements are not coordinated."
}
] |
seed44_2046
|
videos/HRA_part1/2046.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 janitor, wearing a dark green jacket over a gray shirt, tends to laundry in a busy laundromat. Surrounded by rows of washing machines and dryers, he checks the status of a load in a washer, occasionally glancing at the patrons around him. He then moves to a dryer, where he retrieves a bundle of freshly laundered linens, carefully folding them with practiced hands. Amidst the hum of machinery and the scent of detergent, the janitor continues his duties, maintaining order in the bustling environment. Throughout the scene, he remains focused and diligent, his actions highlighting the routine yet essential task of laundry care in a public space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2542
|
videos/HRA_part2/2542.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 vast, sprawling landfill under a hazy sky, three children, two boys and a girl, wearing ragged clothes and protective masks, stand together. One boy, in a red shirt, holds a large rag and wipes the grimy face of another boy, who wears a yellow shirt, while the girl, in a blue dress, watches intently. The action conveys a sense of care and support among the children in this challenging environment. Nearby, piles of discarded electronics, tires, and debris form a bleak landscape, contrasting with the children's resilience and connection.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2432
|
videos/HRA_part2/2432.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 chimpanzee, displaying strength and agility, leaps from a branch in a lush, green forest. The primate, with its dark fur and distinctive features, bounds through the air with a sense of freedom and vitality. As it lands, the chimpanzee's powerful muscles are evident, showcasing the raw energy and grace inherent in its movements. Surrounded by dense foliage and dappled sunlight, the scene captures the essence of life in the wild, focusing on the chimpanzee's leap as a symbol of untamed spirit.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2059
|
videos/HRA_part1/2059.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 doctor kneels in a lush green forest, attentively examining a small, injured deer lying on the mossy ground. The deer, with its distinctive brown coat and white underbelly, looks up at the doctor with trusting eyes. The scene is peaceful, with sunlight filtering through the trees, casting dappled shadows on the forest floor. The doctor, wearing a green field jacket and khaki pants, gently touches the deer's leg, showing care and concern. Nearby, other deer stand watch, their ears perked, observing the interaction from a safe distance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_20
|
videos/HRA_part2/20.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 female cashier with a headband, working at a checkout counter filled with various snacks and beverages, gently caresses a stuffed cheetah. The stuffed animal is placed on the counter next to a cash register, amidst a selection of candy bars. The woman looks lovingly at the toy, her hands tenderly stroking its soft fur, as if sharing a moment of affection with an imaginary companion in the midst of her daily routine.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's hand appears deformed, and the cashier suddenly disappears; the limbs of the plush cheetah also appear deformed."
}
] |
seed46_1382
|
videos/HRA_part2/1382.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 space-themed casino, a large brown bear, standing on two feet, walks with a casual gait, wearing a red shirt, blue jeans, and a gold watch. The bear is surrounded by various elements of the space casino, including a bar with neon lights, slot machines, and a large window displaying a view of the galaxy. As it strides through the casino, the bear passes by a table where alien creatures play cards, their eyes following the unexpected visitor. The atmosphere is filled with a sense of wonder and fun, as the bear continues its stroll, blending seamlessly into the otherworldly environment.]"
},
{
"from": "gpt",
"value": "Bad. The brown bear appears to have a mutation, the bear's limbs are deformed, and the red clothes suddenly disappear."
}
] |
seed46_2818
|
videos/HRA_part2/2818.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 cheerful nurse, wearing a traditional white uniform and cap, leads the dance, her movements lively and joyful. Beside her, a friendly-looking robot astronaut, complete with a shiny silver suit and helmet, follows her lead, its mechanical limbs moving surprisingly gracefully. Bringing up the rear is a hippopotamus, dressed in a tutu and ballet slippers, attempting to mimic the dance steps with its large, cumbersome body, adding a touch of humor to the ensemble. All three characters are surrounded by a vibrant, colorful stage, filled with twinkling lights and glittering confetti, creating a festive atmosphere that complements their dance.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's face, hands, and arms are distorted in the video, as well as the robot astronaut's face, hands, and arms, and the hippopotamus's body is also distorted."
}
] |
seed42_1267
|
videos/HRA_part0/1267.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 beaver, clad in a brown fedora and matching suspenders over a striped shirt, tap dances on a wooden stage under a spotlight. Behind him, a red velvet curtain provides a dramatic backdrop. He executes a series of lively dance moves, including a tap routine, a spin, and a leap, all with a joyful expression on his face. Throughout the performance, he maintains his polished appearance, complete with a vest, watch chain, and spats, as he channels the spirit of a vaudeville entertainer.]"
},
{
"from": "gpt",
"value": "Bad. Beaver's claws are twisted, face is distorted, legs are twisted."
}
] |
seed44_3139
|
videos/HRA_part1/3139.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 creative writer, dressed in a blue shirt and apron, is seen in a well-lit kitchen, preparing an evening meal. The scene opens with a close-up of her face, framed by curly hair, as she smiles warmly while chopping vegetables on a wooden cutting board. She then proceeds to sauté the ingredients in a large pan on a gas stove, the flames casting a soft glow on her face. The camera captures her stirring the contents of the pan with a wooden spoon, her focus and passion for cooking evident in every movement. As the aroma of the sizzling food fills the room, she adds spices from a set of neatly arranged jars, her actions fluid and practiced, embodying the dual talents of writing and culinary artistry.]"
},
{
"from": "gpt",
"value": "Normal. The scene does not show the woman's face, nor does it show the wooden cutting board."
}
] |
seed44_1982
|
videos/HRA_part1/1982.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 nurse wearing a blue scrub top and pants is kneeling on lush green grass in a backyard, engaging playfully with an energetic brown dog. The dog leaps into the air, attempting to catch a red ball thrown by the nurse, who looks on with delight. Both the nurse and the dog are surrounded by a vibrant garden, with colorful flowers blooming in the background, creating a joyful and lively scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1470
|
videos/HRA_part1/1470.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, walks through a dimly lit urban park with tall trees and a brick path, carrying a briefcase in his right hand. Suddenly, a hyena appears, walking alongside him, also on two legs, dressed in a brown jacket and holding a small bag. The lawyer looks surprised but composed, maintaining his stride beside the anthropomorphic hyena, who mirrors his movements, creating a surreal and unexpected duo strolling together.]"
},
{
"from": "gpt",
"value": "Bad. The walking motion is not continuous, there are sudden changes."
}
] |
seed46_1351
|
videos/HRA_part2/1351.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 vibrant young woman, clad in a traditional nurse's uniform with a crisp white dress and cap, finds herself amidst vast, rolling farmlands under a clear blue sky. With a contagious smile, she begins to dance, her movements joyful and carefree, as if the open fields and distant hills are her stage. The sun casts a warm glow over the lush greenery, highlighting her figure as she twirls and leaps, embodying a harmonious blend of professionalism and uninhibited spirit in the rural landscape.]"
},
{
"from": "gpt",
"value": "Normal. The character's body movements are not coordinated."
}
] |
seed46_2605
|
videos/HRA_part2/2605.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, brown capybara runs energetically across a grassy plain, its wet nose and alert eyes highlighting its distinctive features. It bounds forward with determination, showcasing its muscular legs and agile movements. Moments later, the capybara leaps gracefully over an obstacle, demonstrating its impressive jumping ability. Then, it sprints with focused intensity, ears perked, and nostrils flared, against a backdrop of lush vegetation and distant hills. Finally, the capybara continues its swift run, its body language conveying strength and vitality as it navigates the open landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1629
|
videos/HRA_part1/1629.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 kitchen aboard a spacecraft, a skilled chef, wearing a traditional white chef's uniform, meticulously prepares an exotic dish using ingredients mined from an asteroid. The scene is set against the backdrop of space, with stars and galaxies visible through the window. The chef, equipped with advanced tools, carefully selects and processes the raw materials, which include unusual, shimmering minerals and crystals. Meanwhile, robotic assistants crawl along the walls and ceiling, performing maintenance tasks and ensuring the smooth operation of the space station, all while the chef focuses on creating culinary masterpieces from the rare cosmic resources.]"
},
{
"from": "gpt",
"value": "Bad. The chef's hand appears deformed, and the robot's crawling motion also undergoes a mutation."
}
] |
seed44_2235
|
videos/HRA_part1/2235.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. The koala's face, claws, arms, and legs are distorted in the video."
}
] |
seed42_1658
|
videos/HRA_part0/1658.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 woman, clad in a leopard-print outfit, leaps gracefully over a series of low, wooden hurdles set against a green, grassy field, reminiscent of an athletic training montage. Her hair is tied back in a bun, and she wears minimal jewelry, allowing her fluid movements to take center stage. As she jumps, her body is captured mid-air, highlighting her strength and agility. The sunlight filters through the trees, casting dappled shadows on the ground, adding a dramatic effect to the scene. Behind her, a lush forest provides a natural backdrop, further emphasizing the wild and free spirit embodied by the leaping woman.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3139
|
videos/HRA_part2/3139.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 creative writer, dressed in a blue shirt and apron, is seen in a well-lit kitchen, preparing an evening meal. The scene opens with a close-up of her face, framed by curly hair, as she smiles warmly while chopping vegetables on a wooden cutting board. She then proceeds to sauté the ingredients in a large pan on a gas stove, the flames casting a soft glow on her face. The camera captures her stirring the contents of the pan with a wooden spoon, her focus and passion for cooking evident in every movement. As the aroma of the sizzling food fills the room, she adds spices from a set of neatly arranged jars, her actions fluid and practiced, embodying the dual talents of writing and culinary artistry.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1856
|
videos/HRA_part2/1856.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 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 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. No campus scene was generated."
}
] |
seed46_1629
|
videos/HRA_part2/1629.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 kitchen aboard a spacecraft, a skilled chef, wearing a traditional white chef's uniform, meticulously prepares an exotic dish using ingredients mined from an asteroid. The scene is set against the backdrop of space, with stars and galaxies visible through the window. The chef, equipped with advanced tools, carefully selects and processes the raw materials, which include unusual, shimmering minerals and crystals. Meanwhile, robotic assistants crawl along the walls and ceiling, performing maintenance tasks and ensuring the smooth operation of the space station, all while the chef focuses on creating culinary masterpieces from the rare cosmic resources.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2154
|
videos/HRA_part2/2154.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 charming hedgehog, adorned with a miniature top hat and a tiny pair of spectacles, pirouettes gracefully on a wooden floor, surrounded by a medley of autumn leaves. The scene is imbued with a warm, golden light, casting gentle shadows that sway in harmony with the hedgehog's dance. As the music swells, the hedgehog leaps into a joyful jig, its quills bouncing playfully with each step. In the final moments, the hedgehog pauses, bowing elegantly to an invisible audience, the leaves rustling softly in applause, all set against the backdrop of a rustic barn door.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's movements in the video are not smooth."
}
] |
seed42_257
|
videos/HRA_part0/257.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 mesmerizing cuttlefish, displaying a captivating array of color patterns, gracefully hovers in its underwater environment. It exhibits intricate skin textures and hues, from rich purples to vibrant yellows, against a dark blue ocean backdrop. Its large, expressive eyes and eight arms, adorned with suckers, are prominently featured. The cuttlefish then changes its coloration to mimic the sandy seafloor, showcasing its remarkable camouflage abilities, all within the serene, deep-sea habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_160
|
videos/HRA_part1/160.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 manta ray glides effortlessly through crystal clear waters, its vast wingspan casting a shadow on the sandy seabed below. The graceful creature is adorned with a constellation of spots and lines, unique to each individual, as it moves with a serene, almost meditative quality. Sunlight filters through the surface, creating a mesmerizing play of light around the manta ray, which occasionally flips upside down to feed on plankton near the water's surface, showcasing its acrobatic abilities in the vibrant marine environment.]"
},
{
"from": "gpt",
"value": "Bad. The manta ray's body generation in the video is incomplete."
}
] |
seed44_1970
|
videos/HRA_part1/1970.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 construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, takes a break from his laborious tasks to sketch on a piece of paper, seated on a wooden beam at a construction site bustling with activity. Amidst the backdrop of unfinished buildings and heavy machinery, he focuses intently on his art, revealing a moment of unexpected creativity in the midst of a gritty urban environment. The scene captures his dedication to both his profession and his passion, offering a glimpse into the dual nature of his daily life.]"
},
{
"from": "gpt",
"value": "Normal. The worker's actions in the video while creating on paper are basically normal, with slight inconsistencies."
}
] |
seed46_1668
|
videos/HRA_part2/1668.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 sweeping natural landscape, a large bison is rolling on the ground, seemingly wiping itself in the dirt, surrounded by tall grass and distant mountains under a clear blue sky. The bison, with its shaggy brown fur, is seen from various angles, including a close-up of its face as it looks up, showing its rugged features and expressive eyes. Another shot captures the bison from above, highlighting its massive size and the texture of its coat against the sandy ground. Lastly, the bison is shown standing, shaking off the dust, its powerful body and majestic presence commanding respect in its wild habitat.]"
},
{
"from": "gpt",
"value": "Bad. The buffalo's head is generated incorrectly when it rolls on the ground; when the buffalo stands and raises its head, there are issues with the generation of its head and hooves."
}
] |
seed46_1039
|
videos/HRA_part2/1039.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 well-dressed weasel, donning a lab coat and stethoscope, stands at the edge of a swimming pool, located in the backyard of a charming suburban house. The weasel, playing the role of a doctor, attentively examines a patient, who is resting on a floating mattress in the pool, under the shade of an umbrella. Surrounding the pool are other houses, creating a neighborhood backdrop, while the weasel-doctor continues to provide care in this unconventional setting.]"
},
{
"from": "gpt",
"value": "Bad. The patient suddenly disappears in the swimming pool."
}
] |
seed46_1013
|
videos/HRA_part2/1013.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 creative writer, dressed in a futuristic silver jumpsuit and helmet, dances joyously on a meticulously designed space movie set, surrounded by intricate control panels and glowing buttons. The set is filled with high-tech equipment and large, detailed screens displaying cosmic visuals. The writer's movements are expressive and free, conveying a sense of liberation and creativity amidst the futuristic environment. As they dance, the lights from the set illuminate their figure, highlighting their passion for storytelling in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2446
|
videos/HRA_part1/2446.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 the hazy, ethereal atmosphere of Neptune, a space-suited firefighter, equipped with a specialized breathing apparatus and protective gear, is seen wiping the visor of his helmet. A neon bat, adapted to the planet's unique environment, hangs upside-down from a rocky outcropping nearby, its vibrant wings contrasting against the dimly lit, gaseous landscape. The firefighter's actions are deliberate and methodical, emphasizing the importance of maintaining clear visibility in the challenging conditions of Neptune's alien skies.]"
},
{
"from": "gpt",
"value": "Bad. The generation of bats and the firefighter's hands in the video has problems."
}
] |
seed42_11
|
videos/HRA_part0/11.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 majestic bald eagle soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rocky terrain below. It circles gracefully, riding the thermals, with a backdrop of lush green mountains and a distant waterfall. Its piercing yellow eyes scan the landscape, searching for prey, while its sharp talons remain ready to strike. The eagle's brown and white plumage glistens in the sunlight, a symbol of freedom and strength against the stunning natural scenery.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2093
|
videos/HRA_part0/2093.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, wearing a red swim cap and goggles, swims in a clear, blue pool, her form cutting through the water with ease. Suddenly, a curious coyote appears at the edge of the pool, observing the woman with interest. The animal is depicted in fine detail, its sandy fur contrasting with the lush greenery surrounding the pool area. The woman continues her laps, seemingly unaware of the coyote's presence, while the creature watches intently from the poolside, creating an unusual yet captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The lady's swimming movements in the video are not very continuous and smooth, there is a lack of coordination."
}
] |
seed46_111
|
videos/HRA_part2/111.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 navy uniform with gold accents and a peaked cap, runs purposefully across a grand hall within a futuristic space station. The hall is lined with flags from various nations and interspersed with abstract art pieces, all illuminated by the soft glow of recessed lighting. In the distance, a large, circular window reveals the vastness of space and the distant twinkle of stars. The officer's run suggests urgency, possibly related to security matters at the ongoing political summit, where delegates from Earth and various space colonies gather to discuss interstellar policy. The polished floor reflects the officer's movement, emphasizing the gravity of the situation in this otherwise serene and majestic setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's running in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed42_2313
|
videos/HRA_part0/2313.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 golden jackal leaps gracefully over a log in the middle of a grassy savanna, its body stretched mid-air, showing agility and strength. The jackal, with its keen eyes and alert posture, exhibits a powerful jump, clearing the obstacle effortlessly. The scene captures the animal's dynamic movement against a backdrop of tall grasses swaying in the breeze, highlighting the beauty and resilience of this wild canine in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_287
|
videos/HRA_part0/287.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 nurse, wearing a classic white uniform and a colorful headscarf, is seen energetically cleaning windows in a brightly lit hospital room. She moves with purpose, using a squeegee to clear away streaks, while patients rest peacefully in beds adorned with vibrant floral sheets. Sunlight filters through the partially cleaned panes, casting a warm glow over the serene space. In the background, a bustling city skyline is visible, contrasting the calm atmosphere within the room. The nurse's dedication to her task is evident in her focused expression and the gleaming glass that reflects her hard work.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's fingers are deformed, and the patient is generated blurrier in the video."
}
] |
seed44_14
|
videos/HRA_part1/14.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 teacher, wearing a gray sweater over a button-down shirt, yawns dramatically in a classroom filled with desks, capturing a candid moment during a school day. His eyes are closed, his mouth is wide open, and his right hand is holding a red pen, while stacks of papers and books clutter the desk in front of him. The walls are adorned with educational posters, and sunlight streams in from a nearby window, illuminating the room. This intimate scene portrays the relatable, unguarded moment of a dedicated educator succumbing to a yawn amidst his daily responsibilities.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2870
|
videos/HRA_part0/2870.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 director wearing a beige jacket walks through a set resembling a forest, carrying a clapboard marked 'Quantum Leap.' He stops to observe a CGI-generated rhinoceros walking past him, its movements synchronized with the director's pace. The rhinoceros, rendered with high detail, appears to interact naturally with the forest environment, while the director watches intently, his expression conveying a mix of professionalism and wonder.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2799
|
videos/HRA_part0/2799.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 film director, dressed in a dark green jacket, beige shirt, and brown trousers, is seen on set with a weasel perched on his shoulder. The weasel, with its sleek body and curious eyes, suddenly leaps off the director's shoulder, mid-air, creating a moment of unexpected levity. The director, maintaining his composure, watches the weasel's acrobatic jump with a mix of amusement and surprise, all captured against the backdrop of a bustling movie set.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's body and head are twisted in the video."
}
] |
seed44_178
|
videos/HRA_part1/178.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 well-dressed lawyer, wearing a dark suit, finds himself unexpectedly dancing with a chimpanzee in a whimsical scene. Both appear joyful and engaged, with the lawyer maintaining eye contact, smiling, and gesturing with his hands as if leading the dance. The chimpanzee, equally enthusiastic, mirrors the lawyer's movements, wearing a small hat tilted playfully to one side. They dance against a backdrop of a bustling city street, with pedestrians passing by in the background, adding a surreal touch to the urban setting. The lawyer's polished shoes and the chimpanzee's hat become focal points as they whirl around, creating a delightful contrast between professionalism and playfulness.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, legs are twisted, the chimpanzee's body is twisted, arms are twisted, claws are twisted, legs are twisted, and face is twisted."
}
] |
seed46_3018
|
videos/HRA_part2/3018.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 student, wearing a red jacket and khaki pants, races across a grassy field with a small, bushy-tailed fox hot on their heels. The student's face is full of determination and joy, their shoes kicking up clumps of grass as they sprint. The fox, equally playful, bounds alongside, its red fur matching the student's jacket. The scene is set against a backdrop of autumn trees, their leaves turning shades of gold and orange, with the sun casting long shadows across the landscape, highlighting the energetic chase between the student and the fox.]"
},
{
"from": "gpt",
"value": "Bad. The boy's running action is discontinuous, with sudden changes."
}
] |
seed44_2908
|
videos/HRA_part1/2908.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 black puffer jacket, dark jeans, and black boots, stands on a vibrant movie set. He momentarily closes his eyes, blinking, before opening them wide again to maintain focus. As he blinks once more, the overhead lights reflect off his glasses, hinting at the intense concentration required for his role. Despite the bustling activity around him, he remains centered, pausing briefly to blink, his attire and the lively set creating a contrast between the calm director and the dynamic filmmaking environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2485
|
videos/HRA_part2/2485.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, donning a black cap and a blue flannel shirt, is seen painting an antelope on a large canvas set against a background of lush greenery. The canvas is placed on an easel, and the artist, with a concentrated look, applies vibrant orange paint to depict the animal. The antelope, depicted as running with its head turned back, is captured mid-stride, its movement and grace highlighted by the artist's brushstrokes. The setting sun casts a warm glow over the scene, illuminating the artist's silhouette and the vivid depiction of the antelope in motion.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hand is missing in the video, and the antelope in the painting is deformed."
}
] |
seed42_2030
|
videos/HRA_part0/2030.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 ibex, a type of wild mountain goat, is depicted walking steadily across a rocky terrain with snow-capped peaks in the background. The animal, characterized by its curved horns and brown fur, moves with a purposeful gait, navigating the rugged landscape. It pauses momentarily, standing tall on a stone ledge, offering a side profile view, before continuing its journey. Throughout the scene, the ibex's resilience and adaptability to its harsh environment are highlighted, set against the dramatic backdrop of a high-altitude mountain range.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the goat in the video are missing, there are issues with the generation of the horns and the face of the goat, and the tail has not been generated."
}
] |
seed46_2978
|
videos/HRA_part2/2978.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 animated, friendly-looking gray elephant with large ears and a smiling face walks through the halls of a futuristic space education center. The hallways are filled with interactive exhibits, including a large model of the solar system hanging from the ceiling. The elephant, wearing a small backpack, interacts with the exhibits, using its trunk to press buttons and explore the educational displays about planets, stars, and galaxies. Children in astronaut costumes look on in amazement as the elephant continues its journey through the center, learning about the wonders of space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2913
|
videos/HRA_part0/2913.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 navy uniform with a badge and black tactical gear, is seen in a residential backyard with green grass and trees in the background. He kneels beside a golden retriever, gently washing it with a hose and a sponge. The dog, wearing a red collar, happily shakes off water, splashing the officer who laughs good-naturedly. The scene conveys a heartwarming moment of care and connection between the officer and the dog, set against a backdrop of blue skies and lush greenery.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements while bathing the dog in the video are basically normal, with slight disharmony."
}
] |
seed46_2216
|
videos/HRA_part2/2216.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 farmer wearing a dark green jacket, blue jeans, and brown boots stands in a lush, green meadow dotted with dandelions. He looks down with a slight smile as he spots a small vole. The vole, with its distinctive round ears and brown fur, leaps from one dandelion tuft to another in the foreground, creating a playful contrast against the serene farm landscape. The farmer watches the vole's antics with amusement, his stance relaxed and his hands resting on his hips, as the rural setting provides a peaceful backdrop to this unexpected interaction.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted, the vole's body is twisted, the head is distorted, and the claws are twisted."
}
] |
seed46_128
|
videos/HRA_part2/128.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 parrotfish, distinguished by its greenish-blue body with orange highlights and yellow fins, swims gracefully among the coral reefs. Its intricate scales resemble armor, providing a unique texture. It explores its underwater world, surrounded by various corals of purple, red, and orange, creating a stunning contrast against the blue water. The fish's beak-like mouth, a characteristic feature, is clearly visible as it feeds on algae-covered rocks, demonstrating its natural behavior in its marine habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1168
|
videos/HRA_part2/1168.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 lush, verdant park, a majestic leopard, its golden eyes alert, crouches near the edge of a pristine swimming pool, surrounded by vibrant greenery and towering palm trees. The big cat, with its distinctive rosette patterns on a tawny coat, gazes intently at the clear water, contemplating a playful leap. Moments later, it leaps gracefully into the pool, its powerful body slicing through the water in a fluid motion. Emerging from the pool, the leopard shakes off droplets, revealing its muscular physique, as it strides confidently across the park, leaving behind a trail of shimmering water on the sun-drenched pavement.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2301
|
videos/HRA_part0/2301.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 man with short brown hair and glasses, wearing a green striped shirt and apron, is baking a vanilla sponge cake in a home kitchen with white cabinets and countertops. He starts by pouring milk into a bowl containing flour, sugar, eggs, and butter, mixing the ingredients together with an electric mixer. The batter is then poured into a round cake pan and placed in a preheated oven. The camera captures the cake rising and turning golden brown. Once baked, the man removes the cake from the oven, lets it cool, and proceeds to frost it with whipped cream frosting using a spatula. The final shot shows the beautifully frosted cake on a white plate, ready to be served.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand and the spatula in the video generate abnormally, with sudden scene changes in the middle frames."
}
] |
seed42_1755
|
videos/HRA_part0/1755.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, clad in a yellow safety vest and a hard hat, finds himself in a whimsical scenario where he's crawling on his hands and knees through a narrow, dimly lit tunnel. The setting is enhanced by the presence of a stuffed weasel toy, which has somehow joined him on this unusual journey, adding a touch of humor and unexpectedness to the scene. The engineer's serious expression contrasts with the playful atmosphere created by the stuffed animal, making for a unique and memorable visual.]"
},
{
"from": "gpt",
"value": "Bad. The crawling motion is not smooth, and the limbs seem somewhat uncoordinated."
}
] |
seed42_2247
|
videos/HRA_part0/2247.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 captivating scene, a janitor in a space museum is seen cleaning near a large, detailed model of the International Space Station, which is submerged in a serene indoor pool. Wearing a yellow vest, gray pants, and a white shirt, he carefully maneuvers around the underwater exhibit, highlighting his unique cleaning duties. The water around him is crystal clear, allowing viewers to appreciate the intricate details of the space station replica. As he works, the ambient lighting from above gently illuminates the water, creating a mesmerizing visual effect that blends the worlds of space exploration and aquatic tranquility.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1532
|
videos/HRA_part2/1532.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 weathered farmer wearing a brown jacket and wide-brimmed hat kneels in a lush, green field, engaging in meticulous work. Suddenly, the scene reveals that he is crawling, his focused eyes set on the task at hand, perhaps planting seeds or tending to crops. Uncommonly, a zebra stands nearby, watching the farmer with interest, its distinctive black-and-white stripes stark against the verdant landscape. The farmer continues to crawl through the rows, the zebra's presence adding an unexpected element to the pastoral setting. Throughout, the farmer's dedication to his work and the zebra's curious observation create a unique agricultural tableau.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2554
|
videos/HRA_part1/2554.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 artist, wearing a gray sweater and brown pants, is seen painting en plein air in a lush green forest. Suddenly, a squirrel scurries into the frame, running along the forest floor, its bushy tail bouncing behind it. The artist pauses, observing the squirrel's movements with fascination, capturing the essence of the woodland creature in motion on the canvas. The squirrel, now aware of the artist's presence, stops briefly to look back before continuing its hurried journey, providing a perfect subject for the artist's brushstrokes.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's movements in the video are not smooth."
}
] |
seed46_2801
|
videos/HRA_part2/2801.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 janitor, clad in a yellow vest and khaki pants, walks down a dimly lit hallway, pushing a red cleaning cart. Suddenly, a small brown mouse scurries across the floor, its movements quick and cautious. The janitor stops, observing the unexpected visitor with mild curiosity before continuing on his path, the mouse now hidden from view, leaving behind a sense of quiet solitude in the empty corridor.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions a cleaner stopping to watch a small brown rat, but this does not appear in the video."
}
] |
seed44_1512
|
videos/HRA_part1/1512.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 dynamic montage begins with a charismatic musician wearing a space-themed outfit, strumming an electric guitar under the glow of neon lights, surrounded by cosmic visuals. The scene shifts to a historic moon landing, featuring a space-suited astronaut planting a flag on the lunar surface, with the Earth visible in the distance. Lastly, we see a determined athlete sprinting across a track, the focus on their powerful legs and the intensity in their eyes, pushing towards the finish line against a backdrop of cheering spectators. Each scene is seamlessly connected through a thematic thread of human achievement and exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1084
|
videos/HRA_part1/1084.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, dressed in a navy uniform with a badge and a brown belt, is on his knees next to a brown horse, which lies on its side on a grassy surface, possibly injured or receiving care. The officer's hands are gently placed on the horse's neck, showing concern and compassion, while the animal's eyes are closed, indicating it might be resting or in a state of distress. The scene is set against a backdrop of green fields and trees, with no other people or horses visible, emphasizing the intimate connection between the officer and the horse.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_307
|
videos/HRA_part0/307.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 stark juxtaposition, a lone rhinoceros gallops across a barren landscape, its powerful form silhouetted against a backdrop of distant factories, their towering smokestacks reaching into the smoggy sky. The rhino's horn points forward determinedly as it runs, a symbol of resilience and strength in the face of industrial encroachment. Its muscular body strains against the weight of its own survival, each thundering step a testament to its enduring spirit. The factories, with their monolithic presence, stand as a reminder of the challenges faced by wildlife in an increasingly urbanized world. Yet, in this scene, the rhinoceros embodies a defiant hope, charging forward in a land where nature and industry collide.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1552
|
videos/HRA_part2/1552.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 note that due to the rule about scene transitions, the last sentence should be disregarded, so here's an alternative ending without a transition:\nThe camera then pans out to show the sand dollar resting peacefully on the sandy seabed, surrounded by a few small pebbles and seaweed, capturing the serenity of its underwater habitat. 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 the intricate beauty of a sand dollar, its pale color and fine texture contrasting against a dark, grainy sand background. The camera zooms in to reveal the small, delicate spines covering the surface of the sand dollar, emphasizing its natural design. As the focus shifts, the circular shape of the sand dollar becomes prominent, highlighting its symmetrical pattern. The final shot showcases the sand dollar partially buried in the sand, with a blurred oceanic horizon in the distance, evoking a sense of mystery and wonder about this enigmatic sea creature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1878
|
videos/HRA_part2/1878.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 charismatic man, possibly named Ray, stands in a sunlit room, wearing a stylish gray suit, white shirt, and patterned tie. He is seen from different angles, first with his back to the window, then with his profile illuminated by the sunlight, and finally facing forward, his confident expression captured in high definition. Throughout the sequence, he maintains a calm demeanor, his attire and the interplay of light and shadow creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2758
|
videos/HRA_part2/2758.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 man, donning a red plaid shirt, blue jeans, and a wide-brimmed straw hat, diligently sweeps his wooden porch with a long-handled broom, the early morning sun casting a warm glow over the rural scene. Beside him, a white dog rests lazily on the porch, enjoying the peaceful ambiance. The farmer pauses to wipe sweat from his brow, revealing a face lined with years of hard work and dedication to his land. He continues sweeping, the rhythmic sound of the broom against the wood providing a soothing soundtrack to the quiet countryside morning. Behind him, a lush green landscape stretches out, dotted with crops and farm buildings, a testament to his labor and connection to the earth.]"
},
{
"from": "gpt",
"value": "Bad. No white dog was generated lying lazily on the porch."
}
] |
seed42_1149
|
videos/HRA_part0/1149.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 vibrant coral reef ecosystem teeming with life, a pair of butterfly fish, one black and one yellow, swim gracefully among the intricate coral formations. The black butterfly fish, adorned with white polka dots and a striking yellow tail, explores a crevice in the coral. Meanwhile, the yellow butterfly fish, featuring intricate black markings, hovers nearby. The scene is illuminated by the warm sunlight filtering through the clear blue water, casting a mesmerizing play of light and shadow on the diverse marine landscape.]"
},
{
"from": "gpt",
"value": "Normal. The fish's eyes were not generated in the video."
}
] |
seed42_2580
|
videos/HRA_part0/2580.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 endearing otter, captured in high definition, is seen grooming itself by wiping its face with a flipper. The otter, with its brown fur and small, round ears, sits upright on a rocky shore, the surface speckled with white stones. The background features a lush green forest, with tall trees standing majestically against a bright sky. The otter pauses, looking directly at the camera with curious eyes, before continuing its self-cleaning ritual, creating a captivating moment in nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1559
|
videos/HRA_part2/1559.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 crisp uniform consisting of a navy blue shirt, matching trousers, and a peaked cap, is engaged in an unusual task inside a busy restaurant district. He is meticulously wiping down a row of outdoor tables, each set with white tablecloths and surrounded by patrons enjoying their meals. The backdrop features a variety of restaurants, ranging from elegant dining establishments to casual eateries, all bustling with activity. The scene captures the unexpected sight of law enforcement taking on a service role, contributing to the cleanliness and ambiance of the dining area.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the police officer in the video are missing, with hands and eyes not generated, and the faces of background characters are blurry."
}
] |
seed44_2421
|
videos/HRA_part1/2421.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 passionate female teacher, wearing a green sweater and brown hair, gently caresses a large leaf from a temperate rainforest tree during an educational field trip, her face expressing wonder and reverence for nature. Moments later, she holds a branch from a temperate rainforest, engagingly teaching her attentive students about the ecosystem. Then, she lovingly touches a moss-covered log, her actions conveying the importance of the rainforest environment, with the students looking on. Finally, she carefully strokes a fern frond, her demeanor highlighting the beauty and fragility of the temperate rainforest, all while surrounded by lush greenery and the natural world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2408
|
videos/HRA_part1/2408.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, seasoned farmer, clad in a futuristic spacesuit with a clear helmet, stands on Mars Base Camp, a sprawling, high-tech habitat amidst the planet's iconic red landscape. The domed settlement, bustling with advanced technology and greenery, contrasts starkly with the desolate Martian terrain. Inside a transparent dome, the farmer enjoys a leisurely swim in a serene pool, surrounded by lush vegetation and state-of-the-art hydroponic farming systems, showcasing the remarkable fusion of agriculture, leisure, and space exploration on the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's face is severely distorted, with facial features not fully formed, and the hands are also deformed."
}
] |
seed42_2487
|
videos/HRA_part0/2487.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, intimate dining room, a sophisticated waiter, dressed in a crisp white shirt, black vest, and tie, tenderly caresses the smooth surface of a wine bottle, as if appreciating its craftsmanship. The scene is set with elegant table settings, fine china, and crystal glasses, creating an atmosphere of luxury. The waiter's hands, adorned with a simple silver ring, move gracefully over the bottle, highlighting his connection to the art of serving. Behind him, the glow of candlelight casts warm shadows on the walls, adding to the romantic ambiance of the restaurant.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's hand generation in the video has issues."
}
] |
seed44_2545
|
videos/HRA_part1/2545.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 natural, woody setting, a man with a beard, wearing a brown jacket, sits on the ground, gently caressing a gray wolf that lies calmly beside him, its head resting on the man's lap. The wolf appears relaxed and trusting, as if sharing a moment of mutual understanding with the man, who looks on with a soft, compassionate gaze, the lush forest and tall trees providing a serene backdrop to their connection.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2390
|
videos/HRA_part2/2390.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 whimsical and unexpected scene, a waiter wearing a traditional French uniform, complete with a black vest, white shirt, black bow tie, and black pants, is shown running alongside a full-grown rhinoceros. Both are moving at a steady pace across a lush, green grassland, under a bright blue sky dotted with white clouds. The waiter maintains a focused expression, while the rhinoceros runs with its head held high, creating a surreal and comical juxtaposition of elegance and wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2775
|
videos/HRA_part2/2775.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 thoughtful-looking young man, possibly a librarian or a bookstore employee, organizes books on a shelf in a cozy library corner. He wears a mustard yellow sweater over a button-down shirt, khaki pants, and a stylish watch. The library is filled with bookshelves and has a warm, inviting atmosphere, enhanced by the wooden furniture and green plants. He carefully arranges the books, occasionally stopping to read titles or adjust their placement. The shelves are filled with various genres of literature, from classics to contemporary works, reflecting the diverse interests of the library's patrons. Throughout the scene, the man's dedication to his task is evident, as he meticulously organizes the books with a sense of purpose and care.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3207
|
videos/HRA_part0/3207.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 mongoose, recognized by its sandy brown fur, black-tipped tail, and alert demeanor, runs swiftly across a dry, grassy terrain under a clear blue sky. It bounds gracefully over small tufts of grass, its body elongating and contracting with each leap, showcasing its agility and speed. Its eyes are focused ahead, ears perked, and nose twitching, indicating high alertness as it navigates the open space. The mongoose's movement is fluid and purposeful, its feet barely touching the ground as it darts forward, leaving a slight cloud of dust in its wake.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2146
|
videos/HRA_part0/2146.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 ghost shrimp, nearly transparent with greyish-blue tones, clings to a piece of driftwood submerged in a freshwater aquarium. Its delicate antennae and legs are clearly visible, showcasing its intricate anatomy. Nearby, water bubbles softly, adding a gentle ambience to the scene. The shrimp's translucent body allows a view of its internal organs, emphasizing its unique characteristic. Surrounded by aquatic plants and gravel, the ghost shrimp appears in sharp focus against the slightly blurred environment, highlighting its presence in the tank.]"
},
{
"from": "gpt",
"value": "Normal. The ghost shrimp in the video has a deformed body and no eyes were generated."
}
] |
seed46_2530
|
videos/HRA_part2/2530.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 solitary black rhinoceros, distinguished by its squared-off lips and grayish-brown skin, wipes itself vigorously against a tree trunk in the midst of dense savanna vegetation. The action is captured in high definition, showcasing the rhino's determination and the textural contrast between its rough hide and the tree bark. The scene unfolds against a backdrop of lush greenery, highlighting the animal's natural habitat. Moments later, the rhino continues rubbing against the tree, emphasizing its commitment to the self-cleaning ritual, with the verdant foliage and distant trees framing the action in a captivating wildlife moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2557
|
videos/HRA_part1/2557.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 space station, two figures, a man and a woman, both wearing sophisticated, form-fitting silver spacesuits with intricate blue detailing, walk purposefully down a sleek corridor lit by soft, ambient blue light. They carry themselves with the poise and dignity of diplomats, their movements deliberate and confident. The man sports a neatly trimmed beard and short, dark hair, while the woman wears her long, curly hair in a high bun, adorned with small, sparkling silver clips. Both wear expressions of intense concentration, reflecting the gravity of their mission among the stars. Behind them, the corridor stretches into darkness, hinting at the vastness of space and the unknown adventures awaiting them.]"
},
{
"from": "gpt",
"value": "Good. The video shows a man and a woman walking, with basically normal movements."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.