video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1912
|
videos/HRA_part0/1912.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, bald musician, donning a black turtleneck, focuses intently on fixing a leaky faucet in an upscale bathroom with marble countertops. Initially, he looks thoughtful, holding a wrench and examining the faucet. Moments later, he is seen tightening the faucet with the tool, his sleeves rolled up, revealing a tattoo on his arm. He then tests the faucet, turning it on and off, ensuring no leaks remain. Finally, he wipes his hands on a towel, looking satisfied with his handiwork, all set against the backdrop of a luxurious bathroom with a marble sink and countertop.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1277
|
videos/HRA_part2/1277.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 space-themed sports arena, a competitive badger, donning a silver helmet and red uniform, springs into action, leaping high above a futuristic, neon-lit track. The gravity-defying jump is set against a backdrop of stars and planets, with cheering spectators, also dressed in space gear, watching from the stands. The badger's powerful legs propel it through the air, creating a sense of dynamic motion, as it aims to clear a cosmic hurdle during this intergalactic sporting event.]"
},
{
"from": "gpt",
"value": "Normal. The badger's movements in the video are not smooth."
}
] |
seed42_2061
|
videos/HRA_part0/2061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a vibrant red tank top and black leggings, runs across a sandy trail in a lush, green forest. Her brown curly hair bounces as she moves with determination. A small, agile lizard scurries across the path ahead of her, its quick movements catching her attention. The woman momentarily looks down at the lizard, her eyes widening in surprise, before refocusing on her run, her strides strong and purposeful against the backdrop of towering trees and dappled sunlight.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, twisted hands, twisted legs, twisted lizard body, twisted claws, and twisted legs."
}
] |
seed44_3188
|
videos/HRA_part1/3188.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, wearing a white chef's uniform with black stripes and a matching hat, is seen in a small, empty room with white walls and a gray floor. He stands on a brown wooden ladder, holding a paintbrush in his right hand and a white roller brush in his left. The room is illuminated by a large window to his right, casting a soft glow over the space. The chef, with a full beard and a concentrated look on his face, is in the process of painting the wall a vibrant shade of green. The scene captures his transformation of the room, as he applies the paint with precision and care, highlighting his skills beyond the kitchen.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2013
|
videos/HRA_part2/2013.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, dressed in a yellow safety vest, blue jeans, and brown work boots, stretches his body against the backdrop of a building site at sunrise. His routine begins with him bending forward, touching his toes, and then transitioning into a series of stretches that showcase his physical preparation for the day ahead. Throughout the sequence, his attire remains consistent, and the background features a partially constructed building and other workers in the distance, highlighting the early morning setting at the worksite.]"
},
{
"from": "gpt",
"value": "Normal. The worker's head and limbs in the video have generation issues."
}
] |
seed44_2912
|
videos/HRA_part1/2912.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 dimly lit diner after hours, a weary waiter, attired in a crisp white shirt, black vest, and striped tie, rests his head on his hands atop a checkered tablecloth. He has removed his shoes and his black socks are visible, adding to the sense of weariness and relaxation. His nametag reads 'Eduardo', and he appears to have fallen into a peaceful slumber, surrounded by the quiet emptiness of the restaurant. A half-drunk cup of coffee sits beside him, a testament to the long night shift he's just completed. The scene is intimate and still, capturing a rare moment of rest for a hardworking individual.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not move."
}
] |
seed42_1338
|
videos/HRA_part0/1338.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 diligent window cleaner, equipped with a squeegee and a bucket of soapy water, stands on a ladder propped against a tall, glass-paneled building. Dressed in a yellow high-visibility vest and dark pants, he methodically wipes the glass, leaving a streak-free shine. The bustling cityscape forms the backdrop, with pedestrians passing by and cars moving on the streets below. The sun casts a golden glow on the scene, highlighting the cleaner's hard work as he moves from pane to pane, ensuring crystal clarity for the occupants inside.]"
},
{
"from": "gpt",
"value": "Normal. The window cleaner in the video uses a squeegee to wipe the glass basically normally, but there are slightly uncoordinated movements."
}
] |
seed46_253
|
videos/HRA_part2/253.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 magnificent peacock, resplendent in its vivid blue and green plumage, struts regally across a lush, verdant garden, the sunlight dappling its feathers in a mesmerizing play of light and shadow. Its proud head, adorned with a striking crest, swivels gracefully as it surveys its domain. Suddenly, the peacock spreads its spectacular tail, revealing an eye-popping display of iridescent ocelli that seem to shimmer with an otherworldly glow. The air is filled with the rich, earthy scents of the foliage surrounding the bird, adding depth to this enchanting scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1683
|
videos/HRA_part0/1683.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 janitor, clad in a yellow safety vest and black pants, diligently wipes down a control panel in a modern, well-lit power plant. Surrounded by high-tech machinery and screens displaying operational data, he focuses intently on his task, ensuring every surface is clean and free of dust. The environment is pristine, with a sense of order and functionality pervading the space. The janitor's actions are methodical, emphasizing the importance of maintenance in this critical facility.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body and arms."
}
] |
seed46_1349
|
videos/HRA_part2/1349.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 costumed figure, dressed in a full-body brown bear suit, performs a lively jig atop a lush, green heathland blanketed with purple heather flowers. The dancer's movements are energetic and joyful, their bear-clad form spinning and leaping against the vibrant landscape. The heathland stretches out behind them, dotted with patches of colorful blooms and tall grasses swaying in the breeze. The sky above is a brilliant blue, with wispy clouds adding texture to the horizon. Throughout the scene, the dancing bear remains the central focus, their animated presence captivating against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Bad. The facial features and limbs of the brown bear in the video are not fully generated."
}
] |
seed44_2463
|
videos/HRA_part1/2463.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 magpie perches on a weathered wooden fence post, its striking black-and-white plumage gleaming under the natural light. Against a backdrop of lush green foliage, the bird turns its head to gaze curiously at the camera, showcasing its glossy feathers and bright eyes. Moments later, it spreads its wings, revealing intricate patterns as it prepares to take flight, the detailed texture of the wood contrasting with its vivid plumage. Finally, the magpie takes off, flying gracefully against the backdrop of verdant trees, its movements fluid and captivating in high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The magpie's wing-spreading action in the video is discontinuous and abrupt."
}
] |
seed46_2691
|
videos/HRA_part2/2691.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 jumpsuit with a tool belt, crawls through the dimly lit, narrow maintenance corridor of a spaceship, preparing for a hyperspace jump. The ship's interior is filled with pipes and wires, and the engineer's headlamp illuminates the complex machinery around him. He checks various components, ensuring everything is secure before the critical maneuver, his face a mask of concentration under the harsh, industrial lighting of the engineering section.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_325
|
videos/HRA_part2/325.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 film director, distinguished by his gray beard and wearing a dark jacket, blue shirt, and khaki pants, interacts closely with a chimpanzee. The chimpanzee, positioned on a wooden structure in a spacious indoor setting, leaps energetically into the air, demonstrating its agility. The director observes intently, possibly guiding the action or assessing the performance, while standing on the same platform as the chimpanzee, which is enclosed within the large room. The scene captures the unique collaboration between human and animal in the context of filmmaking.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1908
|
videos/HRA_part2/1908.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 sleek black panther crawls across a dry, cracked earth surface under a dense jungle canopy, its muscles rippling beneath glossy fur. The panther's piercing yellow eyes remain fixed on a distant target, conveying intense focus and determination. It moves slowly and deliberately, each paw carefully placed to ensure silent progression, embodying the essence of stealth and power in the heart of the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1330
|
videos/HRA_part1/1330.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, stands on a small green step stool. He is in the process of screwing in a light bulb into a fixture, which is attached to a pale yellow ceiling. The room is sparsely decorated, featuring a white table, a beige office chair, and a bookshelf filled with books and binders. The doctor, with short brown hair and glasses, focuses intently on the task at hand, his sleeves rolled up to his elbows. The scene is lit by other functional light fixtures in the room, casting a warm glow over the doctor and his makeshift ladder.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's action of screwing the light bulb in the video is basically normal, with slight disharmony."
}
] |
seed46_1345
|
videos/HRA_part2/1345.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 woman dances joyously at a luxurious beach resort, adorned in a flowing, patterned dress that complements her radiant smile and the tropical surroundings. With the sun setting behind her, casting a warm glow over the sandy shore, she moves gracefully, her bare feet sinking into the soft sand. Palm trees sway gently in the breeze, framing the scene as she twirls, embodying the spirit of celebration and freedom under the clear, star-studded sky.]"
},
{
"from": "gpt",
"value": "Bad. The woman's dancing in the video is very unsmooth, and her movements are not coordinated."
}
] |
seed46_2589
|
videos/HRA_part2/2589.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 chef, adorned in a traditional white uniform and tall hat, stands against the stark contrast of a landfill landscape. He gently caresses a large, ripe tomato, highlighting the irony of waste amidst sustenance. His eyes, filled with concern and determination, underscore the message of valuing food resources in a world plagued by waste. The scene is set against a backdrop of discarded goods, emphasizing the importance of responsible consumption and the role chefs play in advocating for sustainable practices.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2339
|
videos/HRA_part1/2339.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 firefighter, clad in full gear and holding a bat, begins to dance energetically in the center of a dimly lit room. The bat, typically associated with baseball, adds a playful element to the scene. The firefighter's movements are lively and expressive, contrasting with the serious nature of firefighting equipment. The room, possibly a fire station, is filled with the warm glow of yellow lights, casting shadows that enhance the dynamic atmosphere. The firefighter's dance, set against this backdrop, creates a unique and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3057
|
videos/HRA_part1/3057.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 actor, resembling Matthew McConaughey, is seen polishing silverware in a well-lit room with high-end furniture. Dressed in a white button-down shirt, brown vest, and black pants, he focuses intently on his task. The room features a wooden table, chairs, and a bookshelf filled with books and knick-knacks. A chandelier hangs overhead, casting a warm glow on the scene. The actor's serious expression and the luxurious surroundings create an atmosphere of professionalism and attention to detail.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands show signs of deformity and mutation, and the cup in his hand also becomes deformed."
}
] |
seed46_2475
|
videos/HRA_part2/2475.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 farmer wearing a straw hat and overalls stands in a lush green field, holding a golden retriever puppy in his arms. Around him, a swarm of nanobots, resembling tiny silver spheres, diligently repairs a broken-down tractor, each one equipped with miniature tools. The farmer's eyes twinkle with delight as he watches the efficient repair crew. Nearby, a sparkling blue swimming pool is nestled among the crops, where a group of people in colorful swimwear splash and play, enjoying a refreshing break from the summer heat. The juxtaposition of rural life, advanced technology, and leisure creates a unique and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's action of holding a golden retriever puppy in his arms is basically normal, but there is a slight lack of coordination."
}
] |
seed42_2678
|
videos/HRA_part0/2678.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, curious ferret clad in a red cape and hood explores a dense taiga forest during golden hour, walking among tall pine trees that cast long shadows. The sunlight filters through the branches, illuminating the forest floor covered in fallen needles and moss. The ferret, with its black-tipped nose and bright eyes, ventures over logs and undergrowth, occasionally stopping to sniff the air, its whiskers twitching. Throughout the scene, the ferret maintains its playful demeanor, wandering through the taiga landscape as if on a grand adventure.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's paws in the video have generation issues."
}
] |
seed42_3148
|
videos/HRA_part0/3148.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 weathered farmer, donning a gray beanie, blue flannel shirt, and glasses, sits on a wooden chair in a sunlit barn. He cradles a large crochet hook and works on a vibrant, multicolored blanket, surrounded by rustic details like hay bales and farm tools. The scene highlights his unexpected hobby, showcasing the rich textures of the yarn against the rough wood of the barn. The warm, golden light illuminates his focused face and the intricate pattern emerging from his skilled hands, creating a serene and surprising contrast between traditional farming life and the art of crochet.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the farmer weaving a blanket, the actions are basically normal but there is some lack of coordination."
}
] |
seed44_248
|
videos/HRA_part1/248.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 surprising juxtaposition, a majestic buffalo, with its shaggy brown fur and powerful stature, stands beneath the vibrant lights of an amusement park, visible through the trees. A carousel featuring colorful, whimsical animals spins in the background, adding to the surreal scene. Suddenly, the focus is on a young boy, perhaps five years old, wiping his hands on his jeans after enjoying a snack. Dressed in a red t-shirt and denim, he looks up with a smile, the Ferris wheel towering above him, encapsulating the essence of childhood joy and the unexpected combination of nature and entertainment.]"
},
{
"from": "gpt",
"value": "Bad. The boy suddenly appears in the scene, with his hands showing sudden mutant deformities."
}
] |
seed44_121
|
videos/HRA_part1/121.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 serene indoor scene opens with a close-up of a calm, gray tabby cat sitting on a wooden floor next to a white wall. The cat, adorned with a blue collar, gazes intently at the camera. Suddenly, a human hand enters the frame from above, gently stroking the cat's head, evoking a relaxed response. The camera then captures the affectionate interaction from various angles, showcasing the cat's contentment and the tender touch of the unseen person, all within the cozy confines of a home environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2692
|
videos/HRA_part2/2692.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast warehouse district under a cloudy sky, a worker clad in a yellow vest and hard hat operates a compact yellow Bobcat excavator. The machine crawls carefully across the concrete floor, maneuvering through the tight spaces between towering stacks of pallets filled with cardboard boxes. The excavator's bucket is raised, ready to perform its task amidst the industrial environment, while the worker remains focused, guiding the machinery with precision.]"
},
{
"from": "gpt",
"value": "Good. Basically no problems."
}
] |
seed42_2365
|
videos/HRA_part0/2365.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, adorned in hues of green, orange, and blue, swims gracefully among the coral reefs, its beak-like mouth distinctive against the colorful underwater landscape. It forages for food, nibbling on algae-covered rocks, showcasing its unique feeding behavior. The fish's body, covered in a protective layer of mucus, shimmers as it moves through the crystal-clear waters, surrounded by other marine life. Against the backdrop of the reef, the parrotfish's colors stand out, making it a captivating subject in the aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2836
|
videos/HRA_part1/2836.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 surprising and whimsical scene, a small, cartoonish grey elephant, adorned with a red polka-dotted bow around its neck, is shown mid-jump, its trunk lifted playfully. Against a vivid, clear blue sky, this joyful creature leaps from a lush green meadow dotted with yellow flowers, capturing a moment of pure delight and fantasy. The elephant's large ears are spread wide, adding to the comical effect, while its tiny eyes are closed in sheer happiness, creating a charming and unforgettable visual.]"
},
{
"from": "gpt",
"value": "Bad. The elephant's trunk and limbs in the video have generation issues, the head is deformed, and the overall appearance does not conform to reality."
}
] |
seed42_1973
|
videos/HRA_part0/1973.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 eccentric artist with a shaved head, donning a mustard yellow turtleneck sweater and khaki pants, stands on a dark green chair, changing a light bulb in his dimly lit studio. The space is filled with artistic clutter, including an easel with a half-finished painting, a large wooden table covered in art supplies, and various sculptures scattered throughout. The artist, with a hint of frustration, reaches up to screw in the new light bulb, casting dramatic shadows across his face and the surrounding objects. The scene is captured in high definition, allowing every detail of the artist's struggle and the eclectic studio to come to life.]"
},
{
"from": "gpt",
"value": "Bad. The artist's head and arm in the video are generated abnormally, and the artist's arm and the light bulb in their hand suddenly appear and disappear in the middle frames."
}
] |
seed44_1713
|
videos/HRA_part1/1713.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 dark jacket and casual attire, steps out of a modern building into the urban night, holding a black garbage bag. He approaches a large, industrial dumpster under the dim glow of streetlights, surrounded by concrete walls and parked cars. As he lifts the dumpster lid, his directorial composure contrasts with the mundane task of disposing waste. The scene captures the unexpected juxtaposition of creative leadership and everyday chores, highlighting the director's relatable human side amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1283
|
videos/HRA_part1/1283.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in casual attire, consisting of a gray t-shirt, dark pants, and brown shoes, stands on a green ladder propped against a brown house, engaged in the task of cleaning the rain gutters. He holds a white bucket in his right hand and uses his left hand to scoop out debris from the gutter. The scene is set against a clear blue sky and lush green foliage, with the man's focused expression and determined posture highlighting his commitment to completing the job. The house's exterior, featuring beige siding and brown trim, provides a backdrop for the man's efforts, emphasizing the domestic nature of the activity.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1690
|
videos/HRA_part0/1690.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 sci-fi scene, a weasel cosmonaut, clad in a full spacesuit with a helmet adorned with ears, performs meticulous maintenance aboard a spaceship. The weasel is seen wiping the control panels with a cloth, ensuring every surface is clean. The spaceship, with its sleek silver body and blue lights, is docked at a space station, which can be seen through the large, circular window behind the weasel. The space station is a complex structure with multiple levels and tubes, illuminated by various lights. The weasel continues its diligent cleaning tasks, moving methodically from panel to panel, while the spaceship remains securely docked at the space station.]"
},
{
"from": "gpt",
"value": "Bad. The towel in the hand appears and disappears from time to time. The weasel's hand also undergoes a deformity mutation."
}
] |
seed44_3049
|
videos/HRA_part1/3049.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 industrious engineer, clad in a blue checkered shirt and black pants, meticulously assembles a complex piece of furniture in a modern workshop, illuminated by bright overhead lights. His tools, including a screwdriver and measuring tape, are laid out on a clean, organized workbench. Close-up shots reveal his focused expression and skilled hands as he aligns and tightens screws, demonstrating precision and expertise. The space is filled with the ambient sounds of machinery and the occasional beep of electronic devices, creating a backdrop of industrious activity. Throughout the process, the engineer maintains a calm demeanor, pausing occasionally to consult a blueprint or adjust his glasses, embodying the essence of craftsmanship and dedication.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a screwdriver, ruler, or machine."
}
] |
seed46_2544
|
videos/HRA_part2/2544.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 courtroom under the glow of neon lights, two children, a boy in a gray t-shirt and a girl in a pink dress, engage in a mock trial, surrounded by an audience of plush toys and action figures. The boy, acting as the judge, holds a gavel, while the girl, serving as the defendant, wipes away pretend tears with a small tissue, both participants fully immersed in their roles amidst the imaginative setting. Behind them, a large window reveals the vastness of outer space, complete with stars and planets, adding to the fantastical atmosphere of this unique children's play scenario.]"
},
{
"from": "gpt",
"value": "Bad. The boy's hand undergoes a deformity mutation, and the hammer in his hand is flying and deforming, the boy's arm has been amputated."
}
] |
seed44_2570
|
videos/HRA_part1/2570.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 dimly lit theater, an elegant lawyer, attired in a black suit, white shirt, and red tie, sits pensively with his hands clasped. Beside him, a taxidermied jackal wearing a miniature lawyer outfit sits upright on a chair, adding a surreal touch. The lawyer then wipes his brow with a handkerchief, appearing relieved yet cautious, as if contemplating a significant decision. The scene maintains a consistent setting within the theater, focusing on the lawyer's expressions and the unusual presence of the costumed jackal.]"
},
{
"from": "gpt",
"value": "Bad. The movements are unsmooth."
}
] |
seed42_1801
|
videos/HRA_part0/1801.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 teenage boy, wearing a gray jacket over a blue collared shirt, sits in a classroom with a concerned look on his face. He coughs into his elbow, drawing the attention of his peers. The room is filled with natural light, highlighting the concerned expressions of his classmates who are seated at their desks. A teacher, dressed in a dark blazer and light-colored shirt, stands nearby, watching the situation with a look of care and readiness to assist. The classroom is decorated with posters and artwork, giving it a homely and educational atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the teacher watching the situation."
}
] |
seed42_3172
|
videos/HRA_part0/3172.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, donning a navy suit with a crisp white shirt and a patterned tie, sits at an opulent wooden desk. The room is richly decorated with leather-bound books and classic art pieces. He lifts a fork filled with a gourmet meal to his mouth, savoring each bite. The table is set with fine china and silverware, a half-empty glass of red wine standing beside a nearly finished plate of food, indicating a moment of leisure in his busy schedule. Soft ambient light from a nearby lamp illuminates the scene, casting warm shadows across the polished wood surface.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2553
|
videos/HRA_part0/2553.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 large, formidable goose with striking orange beak and feet stands majestically on a grassy bank, its gray and white feathers ruffled by a gentle breeze. It stretches its neck upwards, revealing its full profile against the backdrop of a serene lake, dotted with lily pads and framed by lush greenery. The bird then lowers its head to preen its feathers, maintaining its composure as it interacts with its tranquil environment. Finally, it takes a step forward, ready to wade into the water, its bold presence commanding attention in this peaceful setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2793
|
videos/HRA_part1/2793.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 distinguished doctor, wearing a crisp, white lab coat over a blue shirt and khaki pants, leaps playfully along a weathered boardwalk by the ocean, his stethoscope swinging freely. The setting sun casts a golden hue over the scene, highlighting the contrast between his professional attire and the casual, joyful activity. The boardwalk, lined with aged wooden planks, extends into the distance, offering a picturesque view of the shoreline and the sea beyond. The doctor's action, captured mid-jump, conveys a sense of freedom and happiness, juxtaposed against the typically serious context associated with medical professionals.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's fingers and stethoscope are deformed in the video, the face is generated blurry, and there are issues with the leg generation."
}
] |
seed46_2622
|
videos/HRA_part2/2622.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male chef with a neatly trimmed beard, wearing a brown jacket over his white kitchen uniform, expertly flips a crepe in a large pan over a high flame, demonstrating his culinary skills in a professional kitchen. The kitchen is modern and well-lit, with stainless steel appliances and countertops. The chef's focused expression and the sizzling sound of the cooking crepe fill the space, capturing the essence of his craft. Moments later, he carefully folds the perfectly cooked crepe, showcasing his precision and expertise in the art of cooking.]"
},
{
"from": "gpt",
"value": "Bad. The chef's brown jacket was not generated."
}
] |
seed42_1336
|
videos/HRA_part0/1336.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 gentleman, balding with a neatly trimmed beard, sits in a cozy library filled with bookshelves, wearing a brown jacket and a yellow shirt. He speaks animatedly about his writing process, gesturing expressively with his hands. Behind him, a large window frames a view of a lush garden, providing a picturesque backdrop. The room is illuminated by warm lighting, creating an inviting atmosphere that enhances the intimacy of the conversation. As he talks, his eyes sparkle with passion, conveying his deep connection to the art of storytelling.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1037
|
videos/HRA_part1/1037.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 doctor, complete with a stethoscope around his neck, dons a brown jacket, dark trousers, and black boots as he shovels snow from a walkway. Snowflakes gently fall from a gray sky, settling on the green pine tree in the background. The doctor, wearing glasses and a wedding ring, pauses to wipe his brow, revealing his determination. He continues to clear the snow, demonstrating his commitment to his duties despite the weather. Throughout the scene, the doctor's attire remains unchanged, emphasizing his professional identity even in this domestic task.]"
},
{
"from": "gpt",
"value": "Normal. The movements are a bit uncoordinated, and the left hand is flying."
}
] |
seed44_1810
|
videos/HRA_part1/1810.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 industrial engineer in a gray shirt and khaki pants stands confidently in a modern factory, surrounded by large machinery and pipes, with a swimming pool visible through a window in the background. He then walks purposefully toward the camera, passing by the heavy industrial equipment, with the pool still visible in the distance. Next, he is seen from behind, approaching a large machine with pipes, while the pool can be glimpsed outside through the window. Finally, the engineer takes a break from his work, enjoying a refreshing swim in the outdoor pool, which is now the focal point, set against the backdrop of the industrial facility.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1266
|
videos/HRA_part2/1266.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 artistic individual, donning a gray beanie, black jacket, and blue jeans, stands on the weathered wooden planks of a dock by the water's edge, with a vibrant cityscape visible across the bay. The artist leaps into the air, capturing the essence of freedom, while holding a sketchbook, which hints at their creative pursuits. The scene is bathed in golden hour sunlight, casting a warm glow over the figure and the urban landscape, creating a sense of serenity and inspiration.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1286
|
videos/HRA_part2/1286.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 in a gray jacket, black shirt, and brown pants stands before a large, unfinished painting of a space elevator, his right hand gently caressing the canvas as if feeling the texture of the depicted structure. His left hand rests on his hip, and he looks down at the artwork with a slight smile, conveying a sense of pride and connection to his creation. The studio is dimly lit, casting dramatic shadows across the room and highlighting the artist's interaction with the painting, which features the towering space elevator reaching towards the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2677
|
videos/HRA_part0/2677.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, dressed in a dark suit, white shirt, and red tie, stands on a chair in a grandiose office with high ceilings, wood-paneled walls, and large windows. He holds a light bulb with one hand, about to screw it into the socket of a chandelier hanging above his head. The room is partially lit by the sunlight filtering through the windows, casting dramatic shadows across the space. Behind him, bookshelves filled with leather-bound law books line the walls, and a large wooden desk sits to the side, cluttered with papers and legal documents. The lawyer's face is serious, focused on the task at hand, as he completes this unexpected duty in his professional environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2859
|
videos/HRA_part1/2859.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 surreal cinematic scene, a majestic buffalo leaps gracefully over a row of vintage cinema seats, its powerful muscles straining against the force of gravity. The buffalo, with its shaggy brown fur and large horns, seems unfazed by the unusual setting, focusing solely on the jump. The cinema seats, arranged neatly in rows, are old-fashioned, with red upholstery and gold accents, creating a striking contrast against the buffalo's wild nature. The room is dimly lit, casting dramatic shadows on the walls and floor, emphasizing the buffalo's impressive leap. The air is filled with tension and anticipation as the buffalo soars through the air, its hooves inches from touching the seat backs. This captivating scene combines elements of nature and culture in a way that challenges traditional boundaries and expectations.]"
},
{
"from": "gpt",
"value": "Bad. The water buffalo's movements in the video are not smooth."
}
] |
seed46_1444
|
videos/HRA_part2/1444.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 artistic scene unfolds, featuring a creative individual sitting at an easel, engrossed in painting a detailed landscape, with a curious squirrel perched on the artist's shoulder. Nearby, a tranquil pond offers a serene contrast, its glassy surface broken only by ripples as a squirrel, perhaps inspired by its surroundings, bravely ventures into the water, swimming with surprising grace. The artist, still absorbed in their work, occasionally glances at the unexpected swimmer, capturing the unique moment on canvas.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1160
|
videos/HRA_part2/1160.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 soft glow of a Martian sunset, casting an eerie red hue, two children, a boy in a blue spacesuit and a girl in a pink spacesuit, dance gleefully on the barren, rocky surface. They are accompanied by a friendly dog, also wearing a matching miniature spacesuit, which bounds alongside them. The children twirl and leap, their movements full of joy and energy, as they embrace the alien landscape. The dog, wagging its tail enthusiastically, adds to the playful atmosphere, all set against the stunning backdrop of a Martian sunset, creating a surreal and enchanting scene.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and face of the boy and girl in the video are incomplete, and the limbs and tail of the dog are also missing."
}
] |
seed42_3022
|
videos/HRA_part0/3022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing swimming trunks and a cap, playfully interacts with a live rabbit at a backyard pool party. Surrounded by friends, he gently holds the rabbit, which remains calm, near the water's edge. The scene transitions to show the student swimming in the pool, while the rabbit sits safely on a towel nearby, being petted by another person. Throughout, the atmosphere is one of carefree enjoyment, with the student and his friends laughing and splashing in the water, and the rabbit seeming content in its temporary role as a poolside companion.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, hands are twisted, arms are distorted, the rabbit's head is twisted, and the claws are deformed."
}
] |
seed46_3017
|
videos/HRA_part2/3017.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 high-tech kitchen illuminated by neon lights, a chef dressed in a white apron and cap, wearing a gas mask, carefully handles a container of antimatter, its energy subtly pulsing within a secure, futuristic device. The chef, displaying remarkable courage, begins to run through the sleek, metallic corridors of a vast space station, the antimatter safely secured in a specialized briefcase designed to withstand extreme conditions. With each stride, the urgency of the situation becomes palpable, the chef's determination evident in the focused gaze beneath the mask, as they navigate the complex towards an unknown destination.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the chef operating the antimatter container, with movements that are not continuous and smooth, and there is a lack of coordination."
}
] |
seed42_1268
|
videos/HRA_part0/1268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a brown jacket, beige pants, and carrying a sketchbook, walks through a surreal landscape inspired by a galactic nebula. The sky is a vivid swirl of cosmic colors - deep purples, electric blues, and fiery oranges, evoking the ethereal beauty of distant galaxies. Giant, floating rock formations, tinged with the same nebulous hues, tower above, while the ground beneath his feet is a shimmering, star-lit plane that reflects the celestial spectacle overhead. Despite the otherworldly setting, the artist strides purposefully, his form and clothing sharply detailed against the dreamlike backdrop, as if he's on a mission to capture the universe's wonders on paper.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1259
|
videos/HRA_part1/1259.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 museum hall with marble floors, an antelope taxidermy mount is displayed under a spotlight, its majestic form captured mid-leap. A diligent custodian wearing a green apron wipes the glass display case, ensuring the exhibit is pristine. The antelope, with its striking coat and alert posture, seems to leap over a miniature landscape within the display. The custodian, in a green uniform, carefully cleans the case, her reflection visible alongside the antelope's image. Throughout, the museum's grandeur is evident, with high ceilings, ornate moldings, and other exhibits surrounding the featured antelope.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2461
|
videos/HRA_part0/2461.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 doctor, dressed in a white lab coat, is seen on the ground, crawling on hands and knees as if examining something closely. Beside him, a giraffe, curious and gentle, bends its long neck to look down at the situation, its eyes filled with intrigue. The setting is a vivid green savanna, with tall grass swaying in the breeze and distant acacia trees dotting the horizon, creating a surreal juxtaposition of medical professionalism and the wild nature of Africa.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2872
|
videos/HRA_part2/2872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird has a sturdy, sharp beak and intense, intelligent eyes that survey the surroundings. Its wings are slightly spread, showing the intricate layering of feathers, while the background is a blur of lush green foliage and dappled light. The crow then takes flight, its powerful wingbeats propelling it through the air against the vivid backdrop of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2955
|
videos/HRA_part0/2955.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 firefighter, clad in full gear and a yellow fire-resistant jacket, is kneeling by a blocked drain on a rainy day, amidst urban surroundings. He wields a long, coiled hose and a specialized tool, methodically working to unclog the drain. His focused expression and the rain-soaked environment underscore the challenging task at hand. Moments later, he pulls the clog from the drain, revealing a mix of debris, while water begins to flow freely again, thanks to his diligent efforts. Throughout, the firefighter's protective gear and the wet cityscape provide context to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted in the video."
}
] |
seed46_110
|
videos/HRA_part2/110.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 creative writer, donning a gray beanie, black jacket, and khaki pants, meticulously organizes a cluttered garage. Surrounded by shelves filled with various items, including tools, bicycles, and storage bins, the writer methodically arranges the space. They handle each object with care, revealing a passion for order amidst creativity. As they work, the writer occasionally pauses to examine an item closely, perhaps reminiscing about its story, before placing it in its designated spot. The garage, bathed in warm, natural light filtering through the windows, transforms into a well-organized sanctuary, reflecting the writer's dual nature of imagination and practicality.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the hands are deformed, the arms are twisted, and the object in hand is warped."
}
] |
seed42_2824
|
videos/HRA_part0/2824.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, dressed in a navy uniform with a badge and gun holster, leaps over a hurdle set up in a dark matter research facility. The background is filled with high-tech equipment and scientists in lab coats observing the unusual training session. The officer's face is focused, showing determination as they navigate the obstacle course designed to test agility in low-light conditions. The scene highlights the unique intersection of law enforcement training and cutting-edge scientific research.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's hands and feet are deformed, the scientists' facial features are blurry, and the fingers are deformed."
}
] |
seed42_1573
|
videos/HRA_part0/1573.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 firefighter, clad in full gear and a helmet, digs vigorously with a shovel in hand, surrounded by charred debris and ash under a smoke-filled sky. The scene is set in the aftermath of a fierce fire, with the firefighter's muscular arm raised high, illustrating the strenuous nature of the task. His face is obscured by a breathing apparatus, emphasizing the hazardous conditions. Nearby, another firefighter, also in full protective clothing, aids in the excavation, both working tirelessly amidst the ruins of a burned-out structure, their actions highlighting the determination and bravery required in their line of duty.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, and the hand is distorted."
}
] |
seed46_2339
|
videos/HRA_part2/2339.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 firefighter, clad in full gear and holding a bat, begins to dance energetically in the center of a dimly lit room. The bat, typically associated with baseball, adds a playful element to the scene. The firefighter's movements are lively and expressive, contrasting with the serious nature of firefighting equipment. The room, possibly a fire station, is filled with the warm glow of yellow lights, casting shadows that enhance the dynamic atmosphere. The firefighter's dance, set against this backdrop, creates a unique and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, head, and legs of the person in the video are twisted."
}
] |
seed42_299
|
videos/HRA_part0/299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man, resembling a timber wolf with his scruffy beard and wild eyes, leaps through the air in a dramatic display of strength and agility. Dressed in a blue plaid shirt, black pants, and brown work boots, he soars over a pile of logs in a forest clearing. The scene is reminiscent of a werewolf transformation, with the man's intense gaze and powerful muscles highlighting his primal nature. The action takes place under a full moon, casting an eerie glow over the landscape and emphasizing the supernatural theme.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1817
|
videos/HRA_part1/1817.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 falcon soars through a cloud-filled sky, its piercing eyes and hooked beak sharply defined against the light. It dives gracefully, wings tucked, chasing an unseen prey over lush green fields dotted with wildflowers. The bird, adorned with a leather hood and jesses, lands on a gloved hand, presenting its fierce gaze and powerful talons. Its plumage, a mix of brown, white, and black, contrasts beautifully with the serene landscape, creating a stunning portrait of nature's hunter against a backdrop of rolling hills and a clear blue horizon.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2491
|
videos/HRA_part1/2491.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 male chef, wearing a traditional white chef's uniform with a tall hat, stands in a modern, well-lit kitchen. He is staring intently at a plate of food he has just prepared, which features a vibrant, colorful dish garnished with fresh herbs. The kitchen is spotless, with stainless steel appliances and countertops, and the chef's focus on the plate highlights his dedication to culinary perfection.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed42_1293
|
videos/HRA_part0/1293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, dressed in a pristine white uniform and wearing a red bandana, walks across a rocky Martian landscape under a starlit sky. Holding a large, clear bowl that reflects the celestial beauty above, the chef pauses to gaze upwards, captivated by the distant stars. With the vast Martian terrain spread out behind, the scene conveys a sense of wonder and exploration, as the chef embarks on a unique stargazing experience on the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The hands and legs are deformed, and the face is not fully generated."
}
] |
seed44_2834
|
videos/HRA_part1/2834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded musician, clad in a black leather jacket and jeans, performs an intense, passionate crawling motion across a vast, icy glacier landscape, his electric guitar amplifying the dramatic scene. The stark, snow-covered mountains and glaciers provide a breathtaking, icy backdrop, contrasting with the musician's raw energy. Throughout the sequence, he continues to crawl, his body language conveying determination and struggle, while the icy wilderness remains a constant, awe-inspiring presence.]"
},
{
"from": "gpt",
"value": "Bad. The musician's movements in the video are not smooth."
}
] |
seed44_2040
|
videos/HRA_part1/2040.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 gentleman named Martin, donning a gray coat, leans against a brick wall in a pensive pose, his right hand resting on his chin. The background is adorned with vibrant graffiti art, adding a splash of color to the urban setting. Martin's attire also includes black pants, a brown belt, and black shoes, complementing his sophisticated appearance. His facial hair, well-groomed and salt-and-pepper in color, frames his thoughtful expression. The scene captures Martin's contemplative nature amidst the lively backdrop of street art.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1174
|
videos/HRA_part1/1174.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 dark green shirt and khaki pants, is seen wiping a wet floor with a mop, leaving behind a clean, glistening surface. Beside him, a small, fluffy white dog, possibly a Bichon Frise, looks up with curious brown eyes. The janitor pauses, resting the mop against a wall covered with inspirational posters and a fire extinguisher, before bending down to interact with the dog, who eagerly responds with a wagging tail and playful energy, creating a heartwarming moment in an otherwise mundane setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2768
|
videos/HRA_part2/2768.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 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 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": "Good. Basically correct."
}
] |
seed46_2667
|
videos/HRA_part2/2667.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 musician, wearing a black jacket and blue jeans, gently caresses the head of a bison, which is lying down on a grassy field under a cloudy sky. The musician's left hand rests on the bison's snout, while the animal's eye is closed in apparent comfort. Both figures are set against a backdrop of green fields and distant mountains, with the bison's body partially obscured by the tall grass. The musician's right hand holds a harmonica, which hangs loosely by its strap, adding a musical element to the scene of connection between human and animal.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2942
|
videos/HRA_part0/2942.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 strong, focused woman wearing a red helmet and climbing gear scales a towering rock face, the texture of the stone rough under her hands and feet. The camera captures her intense concentration, the strain in her muscles, and the determination in her eyes. Sunlight filters through wispy clouds, casting dramatic shadows on the cliffside as she ascends higher, leaving the green valley far below. The scene is framed by rugged terrain, emphasizing her solitary endeavor against the vast, natural landscape.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, with slight coordination issues."
}
] |
seed42_1583
|
videos/HRA_part0/1583.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, neon-lit diner from another dimension, a badger, dressed in a crisp waiter's outfit complete with a bow tie and apron, is seen energetically tap dancing. The animated badger performs intricate dance steps on a checkered floor, surrounded by surreal, cosmic decor, creating an otherworldly atmosphere. This captivating scene is enhanced by the vibrant, pulsating lights that illuminate the peculiar space, giving it an electrifying, interdimensional vibe. The badger's expressive face and lively movements convey a sense of joy and wonder in this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Bad. The badger in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed44_2216
|
videos/HRA_part1/2216.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 little field mouse's body becomes deformed when making movements. The man's arm and hand also undergo mutations."
}
] |
seed42_2320
|
videos/HRA_part0/2320.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 wearing a yellow high-visibility vest and khaki pants walks purposefully down a dimly lit tunnel, holding a flashlight that illuminates the way ahead. The tunnel walls, painted a dull gray, are lined with pipes and electrical conduits, providing a gritty industrial backdrop. Shadows cast by the janitor's flashlight dance on the walls, adding a sense of depth and mystery to the scene. The janitor's steps echo in the confined space, punctuating the otherwise silent atmosphere of the tunnel system.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_1569
|
videos/HRA_part0/1569.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 lone dingo, exhibiting a lean build and a reddish-brown coat, walks purposefully across a barren, rocky terrain under an overcast sky, highlighting its wild nature. It pauses briefly, standing alert with its ears forward, before continuing its journey. The dingo's movement is deliberate, showcasing its survival instincts in the vast, arid landscape, where sparse vegetation and distant mountains provide a stark, natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The dog's limbs in the video have missing parts, and the paws are not generated."
}
] |
seed44_2971
|
videos/HRA_part1/2971.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 dramatic scene, a distinguished actor, with short brown hair and wearing a black leather jacket, gazes intently into the camera, his face reflecting awe and concern. Behind him, a massive explosion of a white hole illuminates the dark cosmos, its brilliant light casting an ethereal glow on his features. In the next frame, he gently caresses the cheek of another character, his touch conveying deep emotion and connection, set against the backdrop of the universe's raw power. The contrast between the intimate gesture and the cosmic event underscores the intensity of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2113
|
videos/HRA_part0/2113.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 janitor, clad in a gray jacket over a white shirt and black pants, is hard at work unclogging a drain in a dimly lit room. He kneels on the floor, his focus intense as he uses a metal tool to clear the clog. The scene is framed by pipes and machinery, emphasizing the industrial setting. His work is meticulous, as he carefully removes debris from the drain, revealing the inner workings of the pipe. Throughout, his dedication to the task is evident, as he ensures the drain is thoroughly cleared, the water now flowing freely, with the satisfaction of a job well done apparent in his demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm undergo deformity and mutation."
}
] |
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 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 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": "Bad. The meerkat can be seen running on the grass in the video, but the movements are not continuous and smooth, showing a lack of coordination."
}
] |
seed46_2014
|
videos/HRA_part2/2014.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 vivid close-up of a sea urchin reveals its intricate, symmetrical structure as it clings to a rocky surface underwater. Sunlight filters through the clear, blue water, casting a soft glow on the urchin's spines, which are a striking contrast to the dark rocks. The camera captures the water gently swaying the urchin, emphasizing its resilience in the marine environment. The scene is framed by the rocky crevices of the seabed, highlighting the creature's natural habitat, while the muted colors of the rocks and sand provide a serene backdrop for the brightly colored sea urchin.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_276
|
videos/HRA_part0/276.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 scene, two people clad in sportswear run side by side down a vibrant street, passing by towering skyscrapers that glisten under the bright sunlight. The runners, a man in a red shirt and black shorts, and a woman in a purple tank top and gray leggings, navigate through the urban landscape with ease. Pedestrians, some in business attire and others casually dressed, walk alongside them, creating a dynamic atmosphere. The towering buildings, adorned with reflective glass, cast long shadows across the street, adding depth and contrast to the urban setting. Throughout the video, the runners maintain their pace, their determination evident as they weave through the crowd and continue their journey among the impressive cityscape.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm and leg are twisted in the video."
}
] |
seed44_2486
|
videos/HRA_part1/2486.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 engineer with short brown hair, wearing a gray shirt, sits at a desk in a modern office, illuminated by overhead lights. He holds a silver pen in his right hand, scribbling intently on a sheet of graph paper. His glasses catch the light as he leans over the paper, which is filled with complex diagrams and equations. Behind him, a large window displays a view of a city skyline, reflecting the time of day as late afternoon, with the sun casting a warm glow into the room. On the desk, next to the engineer's elbow, rests a half-empty coffee mug, a reminder of his dedication to his work.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand is deformed, and the pen in his hand is slightly distorted."
}
] |
seed46_2473
|
videos/HRA_part2/2473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a panther costume, complete with a black leotard, detailed spots, and a lifelike mask, crawls on all fours across a dimly lit stage. The setting is enhanced by a spotlight illuminating her figure, emphasizing the fluidity and grace of her movements, akin to a real panther. The background remains shadowy, drawing attention to her performance as she embodies the essence of the wild animal through her crawling motion.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands, arms, and legs are distorted in the video."
}
] |
seed42_2505
|
videos/HRA_part0/2505.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 endearing elephant, adorned with vibrant red and gold patterns on its body, stands on one leg with its trunk gracefully curved upwards, embodying a joyful dance move. Against a rich, textured green jungle backdrop, the elephant's eyes sparkle with delight, its large ears slightly flared, and its tusks gleaming in the sunlight. Accompanied by smaller elephants in the background, also decorated in red and gold, the scene radiates a festive atmosphere, capturing the essence of an elephantine dance party in the lush, verdant surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The elephant's movements in the video are not smooth."
}
] |
seed44_2298
|
videos/HRA_part1/2298.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, industrial warehouse space filled with rows of neatly stacked boxes, a doctor, identifiable by her stethoscope draped around her neck and wearing a white lab coat over a blue shirt, performs an unexpected action. She leaps into the air with an expression of pure joy, her feet leaving the ground, and her arms spread wide, capturing a moment of uninhibited happiness amidst the sterile environment. The high-definition shot captures the contrast between the clinical setting and the doctor's spontaneous act of exuberance.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's face and limbs, as well as the stethoscope, are distorted in the video, with the doctor's limbs twisting, deforming, or disappearing in the middle frames."
}
] |
seed44_1052
|
videos/HRA_part1/1052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid outdoor scene, three young children sprint across a vast, sunlit chaparral landscape, their movements captured in slow motion to emphasize their carefree joy. Dressed in a red shirt, blue shorts, and black shoes, one child leads the pack, arms outstretched like wings. Another child, wearing a yellow top, green shorts, and brown sandals, follows closely behind, laughing gleefully. Trailing just behind, a third child in a purple dress and pink sneakers completes the trio, their faces alight with excitement as they race beneath the clear blue sky. The chaparral vegetation, with its rugged shrubs and distant mountain backdrop, provides a natural, textured setting for their energetic play.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2385
|
videos/HRA_part1/2385.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 man dressed in a yellow shirt, green vest, and brown shorts leaps into the air with his arms extended above his head, against a backdrop of dense subtropical forest. The lush green foliage, including palm fronds and ferns, provides a vibrant setting. In another frame, he jumps again, this time with his arms wide open, wearing a white cap, dark sunglasses, and a smile, against a similar background of rich, verdant trees. Throughout the sequence, the man's joyful expressions and dynamic poses capture the essence of his energetic exploration within the vibrant subtropical woodland environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_254
|
videos/HRA_part1/254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large construction crane dominates the skyline, its yellow and black body towering over a bustling cityscape at dusk. The crane's long arm stretches across the frame, adorned with industrial machinery and cables, as it stands on a partially constructed building amidst other tall structures. Workers in safety gear can be seen moving about the site, dwarfed by the massive crane, which looms against the orange and purple hues of the setting sun, casting long shadows over the urban landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2839
|
videos/HRA_part1/2839.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair and glasses, wearing a gray T-shirt, stands in a modern laundry room with gray walls and white cabinets, meticulously ironing a white shirt. He pauses to adjust the garment, showcasing his attention to detail. The room is well-lit, highlighting his focused expression and the neat arrangement of laundry supplies in the background. Throughout the scene, he continues to press the iron over the fabric, demonstrating his expertise in maintaining a sharp appearance, all set against the backdrop of a contemporary, organized laundry space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2038
|
videos/HRA_part2/2038.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 albatross soars gracefully over a vast, shimmering ocean, its expansive wingspan casting a shadow on the water below. The bird's plumage, a stunning blend of white and dark feathers, contrasts beautifully against the blue sky. As it glides through the air, its sharp eyes scan the sea for signs of prey. In the background, the silhouette of an island can be seen, adding depth and scale to the scene. The albatross, a symbol of freedom and endurance, continues its flight, the wind gently ruffling its feathers, embodying the spirit of the open sea.]"
},
{
"from": "gpt",
"value": "Bad. The albatross's flying movements in the video are uncoordinated."
}
] |
seed46_1901
|
videos/HRA_part2/1901.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 teacher, wearing rectangular glasses and a blue button-down shirt with a maroon sweater, sits at a desk in a classroom filled with wooden desks and chairs. She leans over to replace the batteries in a digital timer used for classroom activities, demonstrating resourcefulness and attention to detail. The room is decorated with a whiteboard covered in colorful marker scribbles and motivational posters, adding a vibrant touch to the educational environment. The teacher's focused expression and the act of replacing the batteries in the timer, which is placed next to a stack of papers, highlight her commitment to ensuring the smooth operation of classroom tools.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2314
|
videos/HRA_part2/2314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, clad in a brown jacket and wide-brimmed hat, traverses the icy terrain of a vast glacier, crawling on all fours to navigate the challenging landscape. Against a backdrop of towering ice formations, he crawls over the frosty surface, his form contrasting starkly with the pristine white expanse. The farmer's methodical movements and determined expression convey his resilience and connection to the harsh yet awe-inspiring environment. Throughout the scene, he continues to crawl across the glacier, his actions emphasizing the human spirit's perseverance in the face of nature's grandeur.]"
},
{
"from": "gpt",
"value": "Bad. The man's crawling in the video is very unsmooth, and his movements are uncoordinated."
}
] |
seed42_233
|
videos/HRA_part0/233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, donning a plaid shirt, denim overalls, and a worn baseball cap, stands in a modern kitchen. He methodically unloads a sleek, stainless steel dishwasher, handling each plate and utensil with unexpected gentleness. The contrast between his calloused hands and the shiny, clean dishes highlights the unusual domestic task for someone more accustomed to farm chores. The kitchen is spacious and well-lit, featuring granite countertops and contemporary appliances, offering a glimpse into the farmer's home life beyond the fields.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's hand and arm appear deformed, the plate in his hand suddenly disappears, and undergoes deformation."
}
] |
seed46_2654
|
videos/HRA_part2/2654.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 film director, wearing a black jacket, jeans, and a gray shirt, stands on a bustling movie set under bright lights. Holding a megaphone in one hand and gesturing emphatically with the other, he directs actors and crew members with passion and precision. The set is filled with vintage cars from the 1950s, indicating a period drama, while the director's focused gaze and expressive body language convey his dedication to capturing the perfect shot. Surrounded by a diverse cast and crew, he moves with purpose, demonstrating his leadership and vision in the dynamic environment of a film production.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2557
|
videos/HRA_part0/2557.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, 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. No obvious issues."
}
] |
seed42_1909
|
videos/HRA_part0/1909.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 suit, tie, and leather briefcase, walks through lush wetlands filled with tall grasses and cattails, accompanied by a koala casually perched on their shoulder. The lawyer, with a determined look, strides forward on a narrow wooden boardwalk that winds through the wetland habitat. The koala, seemingly unfazed by its unusual companion, clings comfortably to the lawyer's shoulder, occasionally glancing around at the surrounding environment. The pair moves purposefully through the scenic wetlands, with the lawyer's polished shoes and professional attire contrasting sharply with the natural surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_1994
|
videos/HRA_part2/1994.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, middle-aged female nurse sits on a wooden chair in a cozy, softly lit room, wearing a light blue scrubs top and black pants. She crochets a vibrant, multicolored blanket with yellow, orange, and red hues, her hands moving skillfully as she focuses on her craft. The room is filled with the warm glow of a standing lamp, casting a gentle light on the scene. Behind her, a large window reveals a lush, green outdoor landscape, providing a serene backdrop for her meditative activity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2334
|
videos/HRA_part1/2334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 teacher, dressed in a casual red jacket and dark pants, is seen running along a scenic harbor, the sunlight reflecting off the water. She runs with determination, passing by a variety of ships docked in the harbor, from small sailboats to large cargo vessels. Her movement is fluid and purposeful, her gaze fixed ahead, indicating her focus and drive. The harbor's activity provides a dynamic backdrop, with seagulls flying overhead and the sounds of the bustling waterway adding to the atmosphere. Despite the surroundings, the teacher maintains her pace, her stride strong and consistent as she continues her run along the harbor's edge.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's legs and arms show abnormal deformities when running."
}
] |
seed42_1527
|
videos/HRA_part0/1527.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 musician, dressed in a formal black suit, white shirt, and red bow tie, is seen walking side by side with a kangaroo in an urban cityscape. Both figures move with purpose down the street, the musician holding his violin case, while the kangaroo carries a small backpack. They navigate past various city elements, including fire hydrants, street signs, and a yellow cab, blending into the urban environment with an air of normalcy. The scene is framed by a cloudy sky and the tops of buildings, creating a surreal yet harmonious image of these unlikely companions on their shared journey.]"
},
{
"from": "gpt",
"value": "Bad. No small backpack or fire hydrant was generated."
}
] |
seed42_235
|
videos/HRA_part0/235.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, sun-soaked scrublands, a juvenile giraffe with a sandy coat engages in an unusual behavior, moving slowly across the dry, cracked earth. Its spots blend into the arid landscape, and it crawls with a curious determination, perhaps exploring its environment or searching for food amidst the sparse vegetation. The scene is intimate, focusing solely on the giraffe's unique actions in the desolate yet beautiful wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe's limbs are missing in the video, and there are problems with the generation of its face and tail, as well as deformities in the body."
}
] |
seed44_2426
|
videos/HRA_part1/2426.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown jacket, blue jeans, and a green shirt, takes a break from his usual endeavors to tackle an autumn chore. He rakes leaves in a residential backyard, surrounded by lush greenery and tall trees. The scene opens with him standing confidently, holding a rake, and looking intently at the camera. Next, he begins raking piles of golden leaves, his focused expression and body language conveying his determination. The camera then captures him pausing to rest, leaning on the rake, and smiling contentedly at his progress. Finally, he returns to work, skillfully maneuvering the rake to gather the last of the fallen foliage, all while the warm, natural tones of autumn provide a picturesque backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The director's sweeping in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed46_3054
|
videos/HRA_part2/3054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a black beret, glasses, and a striped shirt, stands in a dimly lit studio with paintings in the background. He is engaged in an unexpected task, unclogging a drain, using a plunger on a white ceramic sink, with the focus on his expressive face and the effort exerted in this mundane activity. The contrast between his creative attire and the ordinary plumbing task creates a compelling narrative. Moments later, he pauses, revealing a look of determination as he continues his efforts to clear the clogged drain, the camera capturing his every detail in high definition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2977
|
videos/HRA_part2/2977.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 seasoned worker, donning a brown jacket and blue jeans, leads a strong, brown horse by a red halter, walking together in unison on a dirt path. The pair moves at a steady pace, the man guiding the horse with care and respect. The horse, with its muscular build and glossy coat, follows obediently, the two sharing a bond reflective of their partnership. The setting is a rural landscape, with distant hills and trees providing a serene backdrop to their peaceful walk.]"
},
{
"from": "gpt",
"value": "Bad. The worker's fingers and legs are poorly generated, the face is blurry, and there are issues with the horse's legs."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.