video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1706
|
videos/HRA_part0/1706.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal landscape of Neptune's gaseous atmosphere, rendered in vivid purples and blues, a meerkat stands alert amidst floating islands of icy material. The meerkat, wearing a small spacesuit with a clear helmet, wipes its face with a tiny cloth, perhaps to clean away condensation or space dust. The contrast between the meerkat's terrestrial behavior and the alien environment creates a whimsical and unexpected scene. Behind the meerkat, the swirling clouds of Neptune provide a dramatic backdrop, emphasizing the creature's isolation and the vastness of its surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The meerkat's body is twisted, the arms are twisted, the paws are twisted, the face is twisted, and the legs are twisted."
}
] |
seed46_2870
|
videos/HRA_part2/2870.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A director wearing a beige jacket walks through a set resembling a forest, carrying a clapboard marked 'Quantum Leap.' He stops to observe a CGI-generated rhinoceros walking past him, its movements synchronized with the director's pace. The rhinoceros, rendered with high detail, appears to interact naturally with the forest environment, while the director watches intently, his expression conveying a mix of professionalism and wonder.]"
},
{
"from": "gpt",
"value": "Bad. The director's facial features and fingers were generated abnormally, and there were issues with the rhinoceros's head and limbs."
}
] |
seed46_2730
|
videos/HRA_part2/2730.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, dressed in a green vest over a gray shirt, black pants, and brown shoes, is seen tending to a garden in front of a school building. He begins by pouring water from a large green watering can onto a lush bed of flowers. Next, he plants a small sapling into the soil, wearing protective gloves and using a gardening trowel. Then, he prunes a shrub with a pair of hedge clippers, revealing his meticulous attention to detail. Finally, he sweeps the walkway with a push broom, maintaining the cleanliness of the outdoor space, all under the clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions that after the cleaner plants a small tree seedling into the soil and trims the shrubs with pruning shears, they sweep the sidewalk with a push broom; however, these actions do not appear in the video."
}
] |
seed44_2475
|
videos/HRA_part1/2475.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical 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": "Good. No obvious issues."
}
] |
seed42_2844
|
videos/HRA_part0/2844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a khaki shirt and beige pants, is seen wiping down an ancient, weathered stone structure at a historical site, with a dingo curiously observing from a distance. The engineer, wearing safety glasses and latex gloves, meticulously cleans the surface using a microfiber cloth, revealing intricate carvings and details. The dingo, standing on the lush grass nearby, watches intently with its ears perked up, adding a touch of wildlife intrigue to the scene. The historical site, featuring crumbling stone walls and archways, is bathed in warm sunlight, casting dramatic shadows and highlighting the textures and history of the location.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands show signs of deformity and mutation, and both his hands and arms have become deformed."
}
] |
seed44_2458
|
videos/HRA_part1/2458.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its dark brown coat and impressive, backward-curving horns, walks steadily across a rocky mountain landscape, offering a close-up view of its sturdy hooves gripping the stone surface. It moves with purpose, navigating the rugged terrain with ease, its alert eyes scanning the surroundings. The ibex continues its journey, the camera capturing the detail of its textured fur and the dramatic mountain scenery that serves as its habitat, highlighting the animal's resilience and adaptability in its natural environment.]"
},
{
"from": "gpt",
"value": "Normal. The goat's walking in the video is basically normal, but there is slight movement disharmony."
}
] |
seed42_1419
|
videos/HRA_part0/1419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a helmet, is sprinting with intense focus through a lush, green park. He's gripping a fire hose as he runs beside a serene lake, where ducks are seen swimming in the background. The scene conveys a sense of urgency and determination, with the firefighter's muscular physique straining against his equipment. The park is filled with vibrant greenery and tall trees, providing a stark contrast to the firefighter's urgent mission. As he races past a wooden bench and a playground, the peaceful setting underscores the potential danger lurking nearby.]"
},
{
"from": "gpt",
"value": "Bad. The running action is not continuous, there are sudden changes, and the limbs are somewhat uncoordinated, with hands and arms disappearing suddenly."
}
] |
seed44_2046
|
videos/HRA_part1/2046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a dark green jacket over a gray shirt, tends to laundry in a busy laundromat. Surrounded by rows of washing machines and dryers, he checks the status of a load in a washer, occasionally glancing at the patrons around him. He then moves to a dryer, where he retrieves a bundle of freshly laundered linens, carefully folding them with practiced hands. Amidst the hum of machinery and the scent of detergent, the janitor continues his duties, maintaining order in the bustling environment. Throughout the scene, he remains focused and diligent, his actions highlighting the routine yet essential task of laundry care in a public space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1797
|
videos/HRA_part2/1797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast meadow filled with lush green grass and wildflowers swaying gently in the breeze, a young cashier, wearing a red apron over a white blouse and black pants, is seen running energetically. She has her hair tied back in a ponytail, revealing her focused determination. The cashier takes a moment to pause, hands on hips, catching her breath while admiring the beauty of the surrounding nature. Continuing her run, she passes by a wooden bench, where she stops again, this time leaning forward with her hands on the bench, taking a more prolonged rest. Throughout the video, the meadow remains a constant, picturesque backdrop, providing a serene and inspiring setting for the cashier's outdoor activity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1402
|
videos/HRA_part1/1402.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with glasses, wearing a dark green sweater over a button-down shirt, stands on a chair to change a light bulb in a room with wooden floors and a desk filled with books and writing materials. He holds the new light bulb in his right hand while his left hand grasps the existing bulb, which is attached to a simple ceiling fixture. Behind him, a large window reveals a gray, rainy day outside. The room is dimly lit by a small lamp on the desk, illuminating the clutter of papers, notebooks, and a vintage typewriter. The writer's casual attire, including khaki pants and brown shoes, contrasts with the focused determination on his face as he completes this mundane task amidst his literary surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1390
|
videos/HRA_part1/1390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cormorant, sleek and black, emerges from the water, its dripping feathers glistening in the sunlight. Perched on a low branch near the water's edge, it spreads its broad wings to dry, revealing a flash of orange throat beneath its hooked beak. The bird's intense eyes, set in a striking face, lock onto the camera, displaying its natural curiosity. Against a backdrop of rippling water and lush green foliage, the cormorant stands tall, a testament to its aquatic lifestyle, before diving back into the depths with a powerful flap of its wings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2638
|
videos/HRA_part2/2638.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene directed with artistic flair, a bobcat, known for its secretive nature, emerges from the dense undergrowth of a temperate deciduous forest. The sunlight filters through the canopy, casting dappled shadows on the ground as the bobcat approaches a serene, crystal-clear pool. With a sudden burst of energy, it leaps into the water, its powerful muscles propelling it forward as it swims gracefully beneath the surface. Bubbles rise around it, creating an enchanting underwater ballet, before it resurfaces, shaking droplets from its fur, and returns to the safety of the forest edge, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The head and paws of the mountain cat in the video have generation issues."
}
] |
seed46_1497
|
videos/HRA_part2/1497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged male student, wearing a grey jacket and blue jeans, is crawling along a grassy path on a university campus, surrounded by trees and foliage indicative of early autumn. The scene opens with him crawling under a wooden park bench, suggesting playful or unusual behavior. Next, he crawls beneath the low-hanging branches of a tree, highlighting his determination or whimsy. Then, he crawls across a stone walkway, the textured stones providing a tactile contrast to the grass. Finally, he crawls through a tunnel formed by intersecting tree branches, the dappled sunlight creating a dynamic interplay of light and shadow on his form.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1547
|
videos/HRA_part2/1547.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, young Asian nurse wearing a white uniform and a name tag takes a break from her hospital duties to clean the large, rectangular window in the patient's room. Holding a squeegee in her right hand and a spray bottle in her left, she sprays the glass with a cleaning solution, creating a fine mist. She then wipes it down with the squeegee, leaving a clear, streak-free surface. The natural light from outside illuminates the room, casting a warm glow on the nurse as she works diligently, ensuring the window is spotless.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's fingers in the video are not fully generated, and the arm is disproportionately long."
}
] |
seed44_1234
|
videos/HRA_part1/1234.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic individual named Jay, donning a stylish gray jacket, a black turtleneck, and dark jeans, stands against a backdrop of city lights and a bridge, exuding confidence. He is captured in various poses, first looking directly at the viewer with a serious expression, then showing a side profile with a contemplative look. Jay then smiles warmly, showcasing his friendly demeanor, before striking a cool pose with his hands in his pockets, gazing into the distance. Throughout, the urban landscape behind him complements his modern style and enigmatic persona.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_311
|
videos/HRA_part0/311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 high-visibility vest over a gray jacket, khaki cargo pants, and black shoes, rests his head on his right arm, which is propped on a mop handle. He leans against a wall, his body language conveying exhaustion, as he takes a nap beside a bucket and cleaning supplies, all bathed in dim light. Moments later, the scene subtly changes, showing him still asleep, now with his left hand resting on his forehead, while the bucket and cleaning tools remain nearby. This sequence captures the quiet solitude and hard work of a janitor during his brief respite.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's face is distorted in the video."
}
] |
seed46_2754
|
videos/HRA_part2/2754.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man sits at a desk, bathed in the glow of a computer screen in a dimly lit room, his fingers poised above a black keyboard. He blinks slowly, revealing tired eyes beneath furrowed brows, hinting at the depth of concentration required for his writing task. Dressed in a white shirt with rolled-up sleeves, he exudes determination and focus, his gaze fixed on the screen as if willing the words to appear. The quiet intensity of the scene is punctuated by the soft clack of keys as he types, emphasizing the solitary nature of the creative process.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video types basically normally, but there is slight uncoordination in his movements."
}
] |
seed44_2686
|
videos/HRA_part1/2686.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female teacher, wearing a dark blue blazer over a white blouse and carrying a black handbag, walks purposefully down a wide hallway with high ceilings, resembling the interior of a university building. The walls are adorned with educational posters, and the floors are covered with brown carpeting. As she strides forward, the scene subtly transitions to reveal a large window behind her, displaying a breathtaking view of Neptune's turbulent atmosphere, filled with vivid blue and green clouds swirling majestically. This unique setting, combining the familiar environment of a school with the awe-inspiring backdrop of a distant planet, creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The generated female teacher in the video does not conform to reality."
}
] |
seed44_1498
|
videos/HRA_part1/1498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 single zebra, its distinctive black and white stripes gleaming under the golden savanna sun, is sprinting across a vast, grassy plain. The muscles in its legs are taut, demonstrating raw power and grace as it leaps over tufts of grass. The zebra's mane flutters in the wind, adding to the sense of motion and freedom. Dust kicks up from the zebra's hooves as it races, highlighting the speed and agility of this magnificent creature. Behind the zebra, the landscape stretches to a distant horizon, dotted with acacia trees and the faint outlines of other wildlife, providing context for the zebra's natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The zebra's running motion in the video is not coordinated."
}
] |
seed44_143
|
videos/HRA_part1/143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 doctor, dressed in a white lab coat over khaki cargo pants and brown leather shoes, runs through a lush, green jungle environment. In his right hand, he holds a clear, plastic container housing a live lizard, which scurries about inside. The doctor navigates through the dense foliage, dodging vines and leaping over fallen logs, his face set with determination as he focuses on his mission. The vibrant greenery of the jungle provides a stark contrast to the doctor's attire, highlighting the unusual nature of this scenario.]"
},
{
"from": "gpt",
"value": "Normal. The character's running motion is not smooth."
}
] |
seed44_3023
|
videos/HRA_part1/3023.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, wearing a dark blue jacket over a gray shirt, and gray pants, stands in a taiga landscape marked by tall coniferous trees and a dense undergrowth of shrubs. Holding a towel in his right hand, he wipes his face, perhaps after a long day of work or physical exertion. The scene is set against the backdrop of the taiga, with the engineer's attire standing out against the natural greens and browns of the forest environment. The act of wiping his face with the towel conveys a sense of relief and respite in the midst of the rugged wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1138
|
videos/HRA_part2/1138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a yellow raincoat and clutching a large sketchbook, walks through a lush botanical garden filled with vibrant greenery and colorful flowers. A curious vole scampers across the path ahead of her, its presence adding a touch of whimsy to the serene environment. The artist pauses, observing the small creature before continuing her leisurely stroll, the intricate details of the garden's foliage providing inspiration for her artwork. The scene is framed by towering trees and the sounds of nature, creating a peaceful atmosphere as the artist explores the beauty of the botanical gardens.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2599
|
videos/HRA_part2/2599.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a gray sweater, blue jeans, and black shoes, stands on a chair in a sparsely decorated room with a white ceiling and walls, checking a smoke detector with a focused expression. The room features a wooden desk with a laptop, a bookshelf filled with books, and a framed picture on the wall. The writer, with short brown hair and glasses, carefully inspects the smoke detector, ensuring it functions properly, highlighting the importance of safety in a home office setting.]"
},
{
"from": "gpt",
"value": "Normal. The writer's fingers are deformed in the video, the face and body are distorted, and the smoke alarm is problematically floating in the air."
}
] |
seed42_285
|
videos/HRA_part0/285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, dressed in a gray long-sleeved shirt and khaki pants, is seen wiping down a hippopotamus with a large cloth. The scene takes place in a spacious, well-lit room with concrete walls and floor, resembling a zoo enclosure or animal care facility. The engineer, wearing safety glasses and a name badge, approaches the docile hippopotamus with a bucket of soapy water and a sponge, carefully cleaning its skin. The hippo, appearing calm and cooperative, stands in the middle of the room, surrounded by various tools and equipment typically found in an engineering workshop, creating an unusual yet intriguing juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2285
|
videos/HRA_part1/2285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a spacesuit adorned with patches and logos, embarks on a spacewalk to repair a satellite. She glides through the cosmos, the Earth visible in the distance, her movements methodical and confident. Her gloved hands, detailed with NASA symbols, work diligently on the intricate mechanisms, a tool kit secured to her waist. The vastness of space surrounds her, stars twinkling in the dark expanse, as she focuses on her task with the precision of her legal expertise. Throughout the sequence, her spacesuit helmet reflects the celestial backdrop, encapsulating the unique juxtaposition of her profession and this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, and the hand is distorted."
}
] |
seed42_3046
|
videos/HRA_part0/3046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter dressed in a black vest, white shirt, and black pants kneels on all fours, imitating crawling, in a vast, grassy savanna. Nearby, an antelope, startled yet intrigued, observes the unusual sight, standing still amidst the natural landscape, with distant acacia trees framing the horizon. The waiter, maintaining the crawling posture, looks up at the antelope with a mix of curiosity and amusement, creating a surreal juxtaposition between human and wildlife behavior in the serene African wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The server's head moves slightly, but the video overall remains basically still."
}
] |
seed42_2020
|
videos/HRA_part0/2020.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic male musician, clad in a black shirt, performs energetically on stage under red lights, passionately singing into a microphone. Simultaneously, he wipes sweat from his forehead with his right hand, revealing a wristwatch. Behind him, a drummer in a black sleeveless shirt plays enthusiastically, and a guitarist in a black shirt strums powerfully. The stage is adorned with jaguar patterns, adding a touch of wild flair to the performance.]"
},
{
"from": "gpt",
"value": "Normal. The male musician's hands in the video have issues with generation."
}
] |
seed44_1922
|
videos/HRA_part1/1922.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic scenario, an astronaut clad in a specialized space suit, reminiscent of firefighting gear but adapted for zero gravity, performs a critical spacewalk to repair a damaged satellite. The astronaut's movements are methodical yet fluid, akin to a dance in the vastness of space, as they work against the backdrop of Earth's horizon. Their space suit, complete with a helmet visor that reflects the distant stars, is equipped with tools necessary for the repair, symbolizing a unique blend of firefighting bravery and the elegance of a dancer's precision in the cosmic ballet of space operations.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the astronaut's hand movements, which are uncoordinated."
}
] |
seed42_16
|
videos/HRA_part0/16.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ferret, wearing a red bow tie and small glasses, jumps joyfully on a miniature roller coaster car at a whimsical animal-sized amusement park. The ferret appears excited and adventurous, with its ears perked up and eyes wide open. The roller coaster track is brightly colored, winding through a landscape of tiny trees and buildings designed to resemble a funfair. Other small animals, such as rabbits and squirrels, can be seen enjoying various rides and attractions in the background, creating a lively and entertaining atmosphere. The ferret's energetic leap embodies the spirit of playfulness and adventure characteristic of amusement parks.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's body is twisted, the arms are twisted, the paws are twisted, and the face is twisted."
}
] |
seed46_3065
|
videos/HRA_part2/3065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, casually dressed in a white T-shirt and beige shorts, walks along a stone path on campus, accompanied by a small, green lizard perched on their right shoulder. The student, wearing a backpack and baseball cap, strolls under the shade of lush trees, while the reptile remains calmly positioned, seemingly enjoying the ride. The scene captures the unusual yet harmonious relationship between the student and the lizard, both navigating the campus environment together.]"
},
{
"from": "gpt",
"value": "Normal. The video shows students leisurely walking under dense tree shade; their movements are basically normal but there is some lack of coordination."
}
] |
seed44_2754
|
videos/HRA_part1/2754.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sits at a desk, bathed in the glow of a computer screen in a dimly lit room, his fingers poised above a black keyboard. He blinks slowly, revealing tired eyes beneath furrowed brows, hinting at the depth of concentration required for his writing task. Dressed in a white shirt with rolled-up sleeves, he exudes determination and focus, his gaze fixed on the screen as if willing the words to appear. The quiet intensity of the scene is punctuated by the soft clack of keys as he types, emphasizing the solitary nature of the creative process.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2525
|
videos/HRA_part0/2525.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sci-fi setting, a large moose, adorned with a futuristic, glowing harness, stands calmly beside a colossal space elevator. The moose is being gently caressed by a figure dressed in a spacesuit, creating an unexpected yet tender moment between species. The vastness of space looms overhead, with stars and distant galaxies visible, contrasting with the intimate interaction on the ground. The space-suited individual continues to stroke the moose affectionately, while the majestic animal remains serene, its eyes reflecting curiosity and trust in this otherworldly encounter.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows a pair of hands petting a moose, the actions are basically normal, but in the middle frame, the hands suddenly disappear."
}
] |
seed46_1220
|
videos/HRA_part2/1220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, donning a black baseball cap, black shirt, khaki pants, and black shoes, is shown repairing a vintage bicycle against a backdrop of lush greenery and sunlight filtering through the trees. He is engaged in fixing the bike's chain, showcasing his mechanical skills. In another shot, he carefully inspects the bicycle's frame, his face expressing concentration and expertise. He then tightens a bolt on the bike's wheel, demonstrating his proficiency in bike maintenance. Lastly, he adjusts the bicycle's seat, ensuring it is perfectly aligned, all while surrounded by the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1574
|
videos/HRA_part0/1574.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 detailed close-up, a badger with piercing eyes and sharp teeth runs through a grassy landscape, its fur textured and realistic. Behind it, the silhouette of a large power plant with cooling towers can be seen, emitting steam into the dusky sky. The badger continues its sprint across the terrain, its body language conveying determination and strength, all set against the backdrop of the industrial power plant under the twilight sky.]"
},
{
"from": "gpt",
"value": "Normal. The badger in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2799
|
videos/HRA_part0/2799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green jacket, beige shirt, and brown trousers, is seen on set with a weasel perched on his shoulder. The weasel, with its sleek body and curious eyes, suddenly leaps off the director's shoulder, mid-air, creating a moment of unexpected levity. The director, maintaining his composure, watches the weasel's acrobatic jump with a mix of amusement and surprise, all captured against the backdrop of a bustling movie set.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's movements in the video are not smooth."
}
] |
seed42_1010
|
videos/HRA_part0/1010.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a dark gray jacket and light gray shirt, sits at a desk in a space hotel room, the Earth visible through the window behind him. He wipes the screen of his laptop with a cloth, revealing the reflection of the planet. The room is illuminated by soft, ambient light, giving it a futuristic yet cozy feel. The writer's focused expression and the clean, high-tech environment convey a sense of dedication and precision in his work, all set against the backdrop of the majestic Earth, which fills the large window behind him.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers were not generated."
}
] |
seed42_3054
|
videos/HRA_part0/3054.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_2956
|
videos/HRA_part2/2956.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white tank top, denim overalls, and brown work boots, stands in a modest kitchen with white cabinets and a checkered floor. He reaches into a modern, stainless steel dishwasher, his hands strong and calloused from farm labor. Carefully, he extracts a large, white plate, placing it onto a wooden drying rack set on the counter, where other plates and utensils already rest. The scene is intimate, highlighting the unexpected domestic task of unloading the dishwasher performed by this typically outdoorsy figure.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's movements in the video are not smooth."
}
] |
seed46_1890
|
videos/HRA_part2/1890.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 green vest and khaki pants, walks purposefully down a dimly lit hallway, pushing a squeaky cleaning cart. On the wall, a badger mascot poster from a local college, Wausau Woodchucks, adds a touch of whimsy. The scene shifts slightly to reveal more of the hallway, showcasing the linoleum floor and overhead lights. The janitor continues his journey, passing a row of lockers adorned with stickers and graffiti, while the badger poster remains visible, adding a sense of character to the otherwise mundane setting. Finally, the focus is on the janitor's interaction with the environment, as he pushes the cart with determination, the badger poster serving as a silent observer in the background.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner can be clearly seen pushing the cleaning cart in the video, but the movements are not very smooth or coordinated."
}
] |
seed42_2149
|
videos/HRA_part0/2149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant display under the aurora-lit sky, several figures clad in traditional fur coats and hats, reminiscent of indigenous Siberian attire, gather around a blazing bonfire set amidst the dense taiga forest. They begin to sway in unison, their movements a harmonious blend of ancient and modern dance styles. The firelight flickers across their faces, casting dramatic shadows as they leap and twirl, their feet barely touching the snow-covered ground. The camera captures the dancers from various angles, emphasizing the connection between their lively steps and the serene, starlit wilderness that surrounds them.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_3159
|
videos/HRA_part1/3159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed man, wearing a dark gray t-shirt, sits at a wooden table in a dimly lit room with yellow walls and a red ceiling. He lifts a glass of water to his lips, pausing to drink. His gaze is directed away from the camera, towards another person sitting across from him. The atmosphere is relaxed and intimate, with the man's simple attire and the warm, homey setting creating a sense of comfort and familiarity.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the man lifting a cup of water to his lips to drink, the action is basically normal but there is some lack of coordination."
}
] |
seed46_2607
|
videos/HRA_part2/2607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint village setting, a cheerful female cashier, wearing a yellow apron over a casual outfit, dances joyfully behind the counter of a rustic wooden market stall. The stall is adorned with colorful decorations and surrounded by vibrant greenery, enhancing the festive atmosphere. She moves energetically to an unseen beat, her smile contagious, as she momentarily pauses her duties to revel in the music. The village backdrop includes traditional architecture, bustling locals, and a lively community gathering, all contributing to the sense of celebration and unity.]"
},
{
"from": "gpt",
"value": "Bad. The girl's dancing in the video is very unsmooth, and her movements are uncoordinated."
}
] |
seed44_207
|
videos/HRA_part1/207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zero gravity, a whimsical scene unfolds where a small, brown porcupine floats, performing a delightful dance. It gracefully pirouettes against a backdrop of stars and the vast cosmos, its quills gently swaying in the absence of gravity. The porcupine then leaps playfully, executing mid-air flips and twists with an infectious joy, its quills shimmering under celestial lights. Throughout the dance, the porcupine's movements are fluid and weightless, embodying the freedom and fun of dancing in space, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves are not continuous, with deformities and sudden changes in the movements."
}
] |
seed42_1356
|
videos/HRA_part0/1356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, vibrant green and iridescent, hovers in a close-up shot against a blurred background of lush vegetation. Its wings, a blur of motion, propel it as it feeds from a red salvia flower, the curved beak piercing the bloom. The bird's small size, quick movements, and the detailed feathers are highlighted, set against the rich greenery and soft, natural lighting. The scene captures the hummingbird's agility and the delicate interaction between the bird and the flower, encapsulating the beauty of nature in high definition.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's beak in the video is generated too long, and the wings are generated too large."
}
] |
seed46_2457
|
videos/HRA_part2/2457.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, smiling female musician, wearing a gray sweater, sits against a rustic wooden backdrop. She holds knitting needles and yarn in her hands, crafting a vibrant orange scarf. Her fingers, adorned with rings, skillfully manipulate the needles as she knits. Next, she wears a maroon beret and continues knitting, her eyes focused on her work. Then, she looks up from her knitting, her hazel eyes meeting the camera with a warm smile. Lastly, she proudly holds up the completed scarf, now a beautiful addition to her outfit, against the backdrop of wooden planks, showcasing her dual talents in music and knitting.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers in the video are incompletely generated, and there are missing knitting needles."
}
] |
seed42_1814
|
videos/HRA_part0/1814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a large moose, adorned with a red bow tie and a top hat, stands on a wooden boardwalk illuminated by warm, golden lights. It gracefully sways side to side, as if dancing to an invisible melody, under a starlit night sky. The boardwalk stretches into the distance, lined with quaint shops and twinkling lanterns, creating a surreal and enchanting atmosphere where reality and fantasy blend seamlessly.]"
},
{
"from": "gpt",
"value": "Normal. The moose in the video does not have a top hat."
}
] |
seed42_1739
|
videos/HRA_part0/1739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 deer, with its fur glistening under the sunlight, leaps gracefully over a cash register, which is placed in an unexpected outdoor setting. The animal's movements are fluid and effortless as it clears the register, symbolizing a moment of nature intruding upon the human world. The cash register, typically found indoors, is now situated among lush greenery, with the deer's leap adding an element of surprise and magic to the encounter.]"
},
{
"from": "gpt",
"value": "Normal. The deer's movements in the video are basically normal, with slight coordination issues."
}
] |
seed42_2815
|
videos/HRA_part0/2815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male cashier with short brown hair and glasses, wearing a gray T-shirt and black pants, is seen lifting a large box of soda cans with both hands from a shopping cart onto a checkout counter. The store is busy with customers and products, adding to the bustling atmosphere. Moments later, he lifts another box of similar size with ease, demonstrating his strength and efficiency. The action takes place under bright fluorescent lights, highlighting the cashier's focused expression and determination as he manages the physical demands of his job.]"
},
{
"from": "gpt",
"value": "Normal. The male cashier's face in the video is generated blurry, and his fingers are deformed."
}
] |
seed44_1098
|
videos/HRA_part1/1098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic, metallic silver jumpsuit performs an intricate dance routine inside a mammoth spaceship, illuminated by pulsating neon lights. The ship suddenly initiates a hyperspace jump, stars warping into elongated streaks of light in the background, adding a surreal touch to the scene. Despite the gravity fluctuations, the woman continues to dance gracefully, her movements synchronized with the electronic beats emanating from the ship's audio system. Her face, a mix of determination and joy, reflects the vibrant colors of the spaceship's interior, creating a mesmerizing spectacle as she dances amidst the cosmic chaos.]"
},
{
"from": "gpt",
"value": "Normal. The head and limbs of the person in the video are not fully displayed, with some parts missing."
}
] |
seed46_2186
|
videos/HRA_part2/2186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful gazelle, marked with distinctive black chevrons on its rump, sprints across the frame, its hooves kicking up mist from a bubbling hot spring. The background features a vast, arid savanna with distant mountains and sparse vegetation. The gazelle, its coat a sandy brown hue, bounds over the water's edge, sending plumes of steam into the air with each leap. In the foreground, the hot spring's milky, turquoise waters simmer and bubble, contrasting starkly with the dry landscape. The sky above is a vivid orange, indicating either sunrise or sunset, casting a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Bad. The gazelle in the video has a twisted body, head, feet, and legs."
}
] |
seed46_1941
|
videos/HRA_part2/1941.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy white dog with a pink collar and a polka-dot harness walks down a suburban sidewalk, its ears perked and tail wagging. It pauses to sniff a green fire hydrant, then continues its leisurely stroll. The dog then trots across a quiet street, passing by a row of neatly trimmed hedges and a red mailbox. Finally, it stops to rest under the shade of a large tree, the sunlight filtering through the leaves and casting dappled shadows on the dog's fur.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the green fire hydrant mentioned in the caption."
}
] |
seed46_2294
|
videos/HRA_part2/2294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 art gallery, illuminated by vibrant neon lights, a magnificent Bengal tiger, detailed with its distinctive orange fur and black stripes, appears to run gracefully through the aisles, its movement captured in stunning detail. The gallery walls are adorned with abstract art pieces, creating a surreal contrast to the powerful, lifelike depiction of the tiger in motion. The tiger's dynamic pose, mid-stride, conveys a sense of freedom and strength within the confined yet imaginative space of the art gallery.]"
},
{
"from": "gpt",
"value": "Bad. The tiger's body and legs show deformities."
}
] |
seed46_2767
|
videos/HRA_part2/2767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a black uniform with a red vest and a bow tie, walks across a vast, icy landscape, surrounded by towering glaciers and rugged terrain. He carries a silver tray with a glass of champagne, balancing it gracefully as he strides forward. The scene is set against a backdrop of dramatic, icy mountains, with the waiter's polished shoes and formal attire contrasting starkly with the rugged, snow-covered ground. Despite the harsh environment, he moves with poise and determination, the luxurious glass of champagne glistening under the pale arctic sun.]"
},
{
"from": "gpt",
"value": "Normal. The fingers of the waiter in the video are deformed, the legs are generated unreasonably, and there are problems with the facial features."
}
] |
seed46_180
|
videos/HRA_part2/180.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush subtropical dry forest, a director wearing a black jacket, blue jeans, and a wide-brimmed hat is seen intently choreographing a dance sequence. The dancers, dressed in flowing white garments, perform intricate steps amidst the tall, gnarled trees and dappled sunlight. The director gestures dramatically, guiding the dancers through their routine, while the vibrant green foliage and unique flora of the subtropical dry forest provide a stunning natural backdrop. Throughout the scene, the focus remains on the passionate direction and the captivating dance performance set within the enchanting forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2986
|
videos/HRA_part2/2986.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cheerful nurse wearing a green uniform jumps playfully over a fallen log in the lush rainforest, surrounded by vibrant green foliage, exotic flowers, and towering trees. She lands gracefully on the moss-covered ground, her smile conveying a sense of freedom and joy. Nearby, a small waterfall cascades into a crystal-clear pool, adding to the serene atmosphere of the tropical environment. The nurse's unexpected presence in the rainforest, combined with her playful leap, creates a captivating and memorable scene.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed44_1054
|
videos/HRA_part1/1054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room, two young siblings, a brother and sister, are getting ready for bed. The boy, wearing a blue-striped pajama set, yawns widely, his eyes half-closed, as he sits on the edge of his bed. Moments later, the girl, clad in a pink nightgown, echoes her brother's action with a delicate yawn, her hand covering her mouth, showing manners learned from family. They sit next to each other, displaying the natural bond between them, as they prepare for sleep in their cozy bedroom, the glow of the nightlight casting a warm hue over the scene.]"
},
{
"from": "gpt",
"value": "Normal. Basically normal."
}
] |
seed44_2301
|
videos/HRA_part1/2301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cheerful man with short brown hair and glasses, wearing a green striped shirt and apron, is baking a vanilla sponge cake in a home kitchen with white cabinets and countertops. He starts by pouring milk into a bowl containing flour, sugar, eggs, and butter, mixing the ingredients together with an electric mixer. The batter is then poured into a round cake pan and placed in a preheated oven. The camera captures the cake rising and turning golden brown. Once baked, the man removes the cake from the oven, lets it cool, and proceeds to frost it with whipped cream frosting using a spatula. The final shot shows the beautifully frosted cake on a white plate, ready to be served.]"
},
{
"from": "gpt",
"value": "Normal. The man's action of spreading whipped cream frosting on the cake with a spatula is basically normal, but there is slight disharmony."
}
] |
seed46_1916
|
videos/HRA_part2/1916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, possibly a writer, sits in a hotel room, wearing a brown jacket and glasses, wiping a wooden table with a cloth. The room is well-lit, with a large window behind him, offering a view of a distant mountain range. The man focuses intently on cleaning, his actions deliberate and purposeful. Moments later, a plush teddy bear rests on the now-polished surface, suggesting a personal touch or a connection to the writer's creative process. The scene conveys a sense of tranquility and routine, with the writer's attire and surroundings contributing to the overall mood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2564
|
videos/HRA_part1/2564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a dark blue shirt and wearing glasses, sits at a desk cluttered with books and papers, engrossed in typing on a laptop. Suddenly, a dazzling, intense white hole explosion occurs behind him, wiping out everything in its path except for the writer and his desk, which remain untouched. The force of the explosion is so powerful that it erases the background, leaving only a blinding white light. Despite the chaos unfolding behind him, the writer remains undisturbed, continuing to type away, seemingly oblivious to the cosmic event taking place just feet away.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1173
|
videos/HRA_part1/1173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman clad in a futuristic, form-fitting, metallic blue bodysuit sprints down the pristine, white corridor of a space-age medical facility, illuminated by soft, ambient lighting. Her athletic build and focused gaze convey urgency and determination. In the next scene, she continues her run, passing by high-tech medical equipment and digital screens displaying complex data. The sleek design of the facility, featuring curved walls and glowing lines, adds a sense of advanced technology. Finally, she reaches a critical area, marked by a large, illuminated circle on the floor, where she stops abruptly, ready to face whatever emergency awaits her.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1209
|
videos/HRA_part1/1209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, dressed in a lime green shirt and black shorts, runs through a lush, dense forest filled with tall, vibrant trees and thick foliage, the sunlight filtering through the canopy to illuminate the path. The teacher's face is visible, showing determination and focus, with the camera capturing the motion of their legs and feet as they navigate the terrain. The scenery is rich in detail, with various shades of green from the leaves and plants surrounding the runner, and the sounds of nature - birds chirping, leaves rustling - adding to the immersive experience. Throughout the video, the teacher maintains a steady pace, their form suggesting a regular runner enjoying a peaceful jog in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2308
|
videos/HRA_part0/2308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hedgehog dons a top hat and a monocle, appearing as a refined dancer against a backdrop of bustling harbors, where ships are docked under a twilight sky. The hedgehog, standing on its hind legs, elegantly moves across the foreground, while the harbor life continues in the background, complete with a lighthouse guiding the way. The hedgehog's anthropomorphic attire adds a touch of surrealism to the dancing display, all set against the serene beauty of the harbors at dusk.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's movement in the video is very unsmooth, and the actions are uncoordinated."
}
] |
seed42_2089
|
videos/HRA_part0/2089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative blend of scenes, two smiling children, a boy in a blue jacket and a girl in a pink jacket, walk alongside a life-sized zebra puppet, its distinctive black and white stripes vivid against a neutral background. The children hold hands, looking up in wonder, as the zebra puppet, operated by an unseen handler, walks alongside them. Behind them, a large, high-definition screen displays a captivating visualization of dark matter research, featuring swirling galaxies and complex data visualizations, seamlessly merging elements of nature, childhood innocence, and scientific exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1681
|
videos/HRA_part1/1681.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-covered tundra landscape, a small, furry badger emerges from its burrow, the entrance barely visible among the icy terrain. It cautiously crawls out, its round body and short legs moving slowly against the stark white backdrop. The badger, with its distinct black and white striped face, looks around with beady eyes, alert and ready to retreat at any sign of danger. Its movements are deliberate and measured as it explores the frigid environment, searching for food beneath the snow. The scene is framed by the endless expanse of the tundra, dotted with sparse, low-lying shrubs and ice formations, creating a sense of isolation and survival in the harsh wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2219
|
videos/HRA_part2/2219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, wearing a yellow shirt with a black apron, stands in a modern kitchen classroom filled with stainless steel appliances, teaching a group of attentive students how to stir-fry vegetables. She masterfully tosses vibrant bell peppers, carrots, and broccoli in a large wok over high heat, creating an engaging lesson on cooking techniques. The students, clad in matching aprons, watch intently as she demonstrates the art of stir-frying, her actions punctuated by the sizzling sounds of the hot oil and vegetables. Throughout the scene, the teacher's enthusiasm and expertise shine as she shares her culinary knowledge with her eager pupils.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed44_2990
|
videos/HRA_part1/2990.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red jacket and brown trousers, runs along the edge of a harbor, the water glistening under the bright sun. Accompanied by a large, energetic dog with a tan coat, they traverse the harbor perimeter, surrounded by lush greenery. The farmer, showing a sense of urgency, sprints with focused determination, while the dog bounds alongside, mirroring his pace. Together, they navigate the harbor's edge, the water's surface reflecting sunlight in sparkling patterns, creating a dynamic scene of movement and companionship.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's head generation in the video has problems, and the hands and feet are deformed."
}
] |
seed44_2172
|
videos/HRA_part1/2172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a live clam lying half-open on a bed of damp sand, revealing its intricate interior textures and colors. The clam's exterior is rugged and brownish-black, while the interior showcases a lustrous, pearly surface. The sandy substrate is speckled with small stones and shells, adding to the natural coastal environment. Sunlight filters through the water, casting a soft glow on the scene, highlighting the clam's delicate features and the surrounding grains of sand.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_267
|
videos/HRA_part1/267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush, green orchard, a hardworking farmer pauses from his labor, wiping sweat from his brow, while in the foreground, a mongoose is seen playfully exploring its surroundings. The farmer, dressed in a straw hat, denim overalls, and a plaid shirt, leans against a wooden fence, offering a warm smile. Nearby, the mongoose, with its slender body and bushy tail, darts between tree trunks, seemingly unbothered by the human presence. In the distance, a shimmering swimming pool, surrounded by a wooden deck and sun loungers, provides a refreshing contrast to the vibrant orchard setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2944
|
videos/HRA_part1/2944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a yellow safety vest, blue jeans, and a brown baseball cap, is seen catching a tool thrown by a colleague on a building site, with a large, unfinished structure in the background. The scene captures the moment of action, with the worker's eyes fixed on the incoming tool and his body positioned to make the catch. The atmosphere is tense yet focused, highlighting the trust and coordination between the workers in a high-stakes environment.]"
},
{
"from": "gpt",
"value": "Bad. The worker's hands and legs deform abnormally during movement, and the tools in their hands fly around randomly."
}
] |
seed44_1156
|
videos/HRA_part1/1156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, wearing a yellow swim cap and goggles, swims in an infinity pool that mirrors the celestial aesthetics of Jupiter's Great Red Spot. The pool's water color shifts between red and orange hues, mimicking the storm's appearance. Surrounded by lush greenery and under a clear blue sky, the swimmer effortlessly glides through the water, embodying the harmony between human endeavor and cosmic inspiration. The artist's swimming movements contrast beautifully with the serene environment, creating a captivating visual metaphor for exploring the universe's mysteries within the confines of our earthly existence.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2724
|
videos/HRA_part1/2724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red flannel shirt, beige pants, and brown suspenders, stands at a white sink in a rustic kitchen. He is washing dishes by hand using a sponge, with a wooden cutting board and a bowl of fruit visible nearby. The farmer, who has short brown hair and a neatly trimmed beard, demonstrates his commitment to household chores with a focused expression. The kitchen is warm and inviting, with wood-paneled walls, a white refrigerator, and a window above the sink offering a view of green fields. The farmer's strong hands, calloused from years of working the land, now deftly clean plates and utensils, showcasing the versatility of his daily tasks.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1308
|
videos/HRA_part2/1308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patient teacher, wearing a brown jacket and khaki pants, stands in a rural classroom with wooden desks and a world map on the wall. She gently caresses a small deer that has wandered inside, creating a tender moment. The deer, with its large eyes and curious demeanor, stands calmly beside the teacher, who offers a comforting presence. Both the teacher and the deer are bathed in the warm, golden light filtering through the windows, adding to the serene atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3193
|
videos/HRA_part1/3193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, distinguished by its golden fur and intricate rosette patterns, sprints across a sun-drenched savanna. Its muscles ripple powerfully beneath its coat, demonstrating raw strength and agility. The leopard's piercing green eyes remain focused ahead, indicating determination and purpose in its stride. It bounds gracefully over the landscape, leaving a trail of displaced grass in its wake, embodying the essence of wild freedom and survival instinct.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2504
|
videos/HRA_part0/2504.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated doctor, clad in a white lab coat and protective goggles, embarks on an extraordinary adventure, crawling through a meticulously detailed, space-themed diorama. This unique setting features a realistic comet in pursuit, depicted through dynamic lighting and visual effects, creating an engaging narrative. The doctor, equipped with a futuristic tool kit, exhibits determination and focus, navigating the challenging terrain with precision. The comet, represented by a meticulously crafted model, trails closely behind, adding a thrilling element to the scene. Throughout the video, the doctor's journey is portrayed with a blend of scientific curiosity and cosmic wonder, set against a backdrop of meticulous craftsmanship and vivid imagination.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1018
|
videos/HRA_part1/1018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 tabby cat with distinct stripes sits calmly in front of a sprawling industrial landscape dominated by oil refineries under a hazy sky. It gently caresses a smooth surface with its paw, its green eyes intently focused on the action. The cat's relaxed posture and deliberate movements contrast sharply with the gritty, mechanical backdrop of pipes and tanks. Throughout the scene, the cat remains the central figure, its fur softly glowing in the muted light, as it continues to tenderly stroke the surface, a curious juxtaposition of tenderness and hardness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1525
|
videos/HRA_part2/1525.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single pigeon, with feathers of gray and white, perches on a stone ledge against a clear blue sky, its head turned to the side as it observes its surroundings with one round eye. Moments later, the bird stretches its wings, revealing a span of dark and light gray feathers, before settling back into a resting position. It then preens itself, using its sharp beak to groom its feathers, maintaining its cleanliness and hygiene. Finally, the pigeon takes flight, its wings flapping powerfully against the bright sky, leaving the ledge empty as it explores its urban habitat.]"
},
{
"from": "gpt",
"value": "Normal. The pigeon's movements are not smooth."
}
] |
seed44_1685
|
videos/HRA_part1/1685.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two individuals, a man and a woman, are engaged in washing a car in a driveway, with lush green grass and a tree visible in the background. The man, wearing a white t-shirt and dark shorts, is seen using a hose to rinse the vehicle, while the woman, clad in a pink tank top and denim shorts, scrubs the car's side with a sponge. Both are focused on their task, with the man holding the hose and the woman applying soap to the car's exterior. They work together harmoniously, the man rinsing and the woman scrubbing, against a backdrop of a sunny day and a neatly kept suburban home.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are not smooth."
}
] |
seed44_1310
|
videos/HRA_part1/1310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, distinguished by its brown fur, white underbelly, and tufted ears, stealthily crawls across a sandy surface in a suburban town, near wooden fences and lush greenery. It pauses to sniff the air, displaying its sharp teeth and alert demeanor. The feline then continues its crawl, passing by a stone wall and wooden planks, indicating the proximity to human habitation. Throughout the scene, the bobcat's cautious and curious nature is evident as it explores its surroundings in the town's outskirts.]"
},
{
"from": "gpt",
"value": "Bad. The mountain cat's feet in the video are generated unreasonably."
}
] |
seed44_150
|
videos/HRA_part1/150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit room, two young children sit cross-legged on a vibrant multi-colored rug, surrounded by an array of plush toys and colorful books. The older child, wearing a yellow shirt, leans over a book, animatedly pointing at the pages as they read aloud with enthusiasm. The younger child, dressed in a blue sweater, listens intently, eyes wide with wonder and hands resting on their knees. The walls of the room are painted a calming light blue, adorned with playful artwork and educational posters, creating a nurturing environment that fosters a love for reading and learning.]"
},
{
"from": "gpt",
"value": "Bad. The older child in the video reads in an unsmooth manner, with uncoordinated movements."
}
] |
seed44_2687
|
videos/HRA_part1/2687.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a bustling metropolis, an innovative female engineer wearing safety glasses and a reflective vest runs through a construction site filled with cranes and skyscrapers under construction. Her stride is confident, highlighting her determination. She navigates around concrete pillars and rebar, demonstrating agility amidst the urban landscape. The cityscape, featuring tall buildings and bridges, serves as a backdrop, emphasizing the scale of her environment. Throughout the scene, she maintains her composure, showcasing her expertise and passion for engineering in an active urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The female engineer's running in the video is very unsmooth, and her movements are uncoordinated."
}
] |
seed44_2962
|
videos/HRA_part1/2962.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, wearing a gray T-shirt with a logo, blue jeans, and a dark cap, assembles furniture in a bright room. He focuses on tightening screws on a wooden dresser using a cordless drill, demonstrating his expertise. The room is filled with natural light, illuminating the task at hand. Moments later, he expertly aligns the dresser drawers, ensuring they fit perfectly. Lastly, he stands back to admire his completed work, a fully assembled dresser standing against a white wall, with the sunlight highlighting the wood grain and the worker's satisfaction in his craftsmanship.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_293
|
videos/HRA_part2/293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic lion, defying expectations, swims powerfully through a tranquil body of water, its golden coat glistening as it propels itself forward with muscular strokes. Its piercing gaze is fixed ahead, conveying determination and grace in this unusual aquatic setting. The lion's head remains above the waterline, mane billowing softly, while its body undulates beneath the surface, showcasing an unexpected display of strength and agility in the liquid environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3197
|
videos/HRA_part1/3197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars gracefully over a vast, shimmering ocean, its wings spread wide against a backdrop of rolling clouds and a cerulean sky. The bird's white plumage is highlighted by the golden rays of the sun, casting a serene glow over the scene. As it glides effortlessly, its keen eyes scan the waters below for signs of prey, demonstrating the harmony between creature and environment. The albatross then swoops down, its silhouette framed by the sun, before rising back into the heavens, embodying the spirit of freedom and the majesty of nature.]"
},
{
"from": "gpt",
"value": "Bad. Albatross's claws are twisted, wings are twisted, head is twisted."
}
] |
seed42_2233
|
videos/HRA_part0/2233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant, young female musician dons a futuristic silver outfit, complete with a matching helmet, as she energetically performs a dynamic concert on a space station. Surrounded by the vast cosmos, she passionately sings into her microphone, her movements lively and engaging. In a captivating display, she effortlessly sprints across the zero-gravity stage, her silver suit shimmering under the cosmic lights, while continuing to captivate the audience with her powerful voice and electrifying performance. The space station's advanced technology enhances the concert experience, creating an unforgettable spectacle set against the backdrop of the infinite universe.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a distorted body, face, feet, legs, arms, and hands."
}
] |
seed46_2952
|
videos/HRA_part2/2952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown leather jacket and dark pants, kneels on a wooden floor, engaged in a crawling motion, as he observes a live hare sitting on a white table nearby. The scene is set indoors, with a large window in the background, allowing natural light to illuminate the room. The director's intent gaze and careful movement convey a sense of focus and determination as he studies the animal, which remains calm and still, seemingly unfazed by the presence of the human.]"
},
{
"from": "gpt",
"value": "Bad. The director can be seen kneeling on the ground observing the actions, which are not continuous and smooth, and there are inconsistencies."
}
] |
seed46_1033
|
videos/HRA_part2/1033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young Asian student, wearing a yellow jacket and khaki pants, walks down a city street with a pet gerbil peeking out of his jacket pocket. The gerbil, visible from the side, has small ears and a round body, adding a touch of whimsy to the scene. The student's attire includes a dark shirt under the yellow jacket, and his pants are neatly tucked into white socks and brown shoes. The urban setting features a crosswalk and pedestrians in the background, providing context to the student's journey.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed44_2281
|
videos/HRA_part1/2281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal scene, a cosmic event unfolds as a theoretical white hole explosion is depicted with vibrant colors and swirling celestial patterns, forming an ethereal, mesmerizing spectacle in the background. In the foreground, a graceful woman, wearing a flowing white dress, gently caresses an abstract representation of the universe, symbolized by a large, luminous orb, evoking a sense of connection and reverence for the mysteries of the cosmos. The woman's serene expression and delicate touch convey a message of harmony and unity between humanity and the infinite expanse of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1912
|
videos/HRA_part2/1912.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 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, 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 musician's hands and arms appear deformed, and the wrench also becomes deformed, finally disappearing suddenly, along with the towel which also distorts."
}
] |
seed44_1937
|
videos/HRA_part1/1937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, known for his role in a space-themed reality TV series, gently caresses the smooth, metallic surface of a spacecraft console, his face illuminated by the soft glow of the control panel lights. Dressed in a futuristic silver jumpsuit with black accents, he leans over the controls, his eyes locked onto a screen displaying complex data, conveying a sense of focused intimacy with the technology. The scene is set inside a sleek, modern spaceship cabin, with large windows showing the vastness of space beyond, stars twinkling against the dark cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed42_1606
|
videos/HRA_part0/1606.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 facility with glowing blue accents, a muscular firefighter, wearing a full-body protective suit and helmet, stands against a backdrop of advanced machinery. He holds an antimatter containment device, a sleek silver sphere with intricate detailing, which emits a faint blue glow, signifying its active state. The setting shifts subtly to reveal the firefighter engaging in a lively dance, maintaining a firm grip on the containment device, now resting on his hip. The dance moves fluidly from a standing position into a crouched stance, with the firefighter's hands moving dynamically, all while keeping the device secure. Throughout the sequence, the futuristic setting, characterized by clean lines and blue accents, remains visible, adding a dramatic touch to the dancing firefighter's performance.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the 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 child's dancing in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed42_1586
|
videos/HRA_part0/1586.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station habitat, illuminated by soft, ambient lighting, a caring teacher, wearing a navy blue jumpsuit with silver accents, gently caresses the head of a young student seated at a desk. The student, dressed in a matching uniform, looks up with wide eyes, feeling comfort and support. Behind them, a large window reveals the stunning view of Earth, while various educational tools and floating objects fill the zero-gravity environment, creating an immersive learning atmosphere. The teacher's compassionate touch and the unique setting emphasize the nurturing bond between educator and pupil in this extraordinary space classroom.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_3013
|
videos/HRA_part1/3013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a white apron over a black shirt and gray pants, is seen scrubbing the bathroom floor with a green cleaning brush. The room is illuminated by overhead lights, and the chef's serious expression conveys the importance of cleanliness. In another angle, the chef, still in his chef's uniform, is shown on his knees, focused on scrubbing the bathroom tiles with determination. The video emphasizes the chef's commitment to hygiene, even in non-food-related areas, as he meticulously cleans the bathroom floor with a green cleaning brush under the bright lights.]"
},
{
"from": "gpt",
"value": "Normal. The chef's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2968
|
videos/HRA_part2/2968.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic grouse, distinguished by its brown plumage speckled with white and black, struts proudly across a lush, green meadow under a bright, sunlit sky. The bird's robust body, complete with a red wattle above its beak, is prominently displayed as it moves with regal confidence. Moments later, it's seen in profile, its intricate feather patterns and textured wings highlighted against the vibrant vegetation. Then, it turns its head, revealing piercing eyes and a sharp beak, set against the backdrop of a dense forest and clear blue sky. Lastly, the grouse is captured mid-stride, its legs moving swiftly, demonstrating the strength and agility of this woodland creature, all set against a serene natural landscape.]"
},
{
"from": "gpt",
"value": "Normal. The bird's legs are generated multiple times, and the head is not fully generated."
}
] |
seed42_3098
|
videos/HRA_part0/3098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest environment, two individuals wearing khaki safari outfits are seen running alongside a chimpanzee, engaged in playful interaction. The scene is vibrant and full of life, with the humans and the chimpanzee moving together in harmony. They dash across a dirt path, surrounded by dense vegetation, as the chimpanzee exhibits its natural agility and strength. The trio's energetic run is captured in high detail, highlighting the dynamic movement and the unique bond between humans and this primate in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_197
|
videos/HRA_part0/197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary director, wearing a dark jacket and shirt, sits in a dimly lit room with neon accents, contemplating the concept of light-speed travel. He gently caresses a futuristic, spherical object, possibly a holographic model, as he ponders the intricacies of time and space. The camera captures his focused gaze and the intimate interaction with the sphere, symbolizing the connection between human creativity and the mysteries of the universe. The scene is set against a backdrop of high-tech, sci-fi inspired visuals, enhancing the theme of exploring the unknown.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_1522
|
videos/HRA_part1/1522.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray wolf, marked by a distinct white-tipped tail, walks purposefully across a barren, rocky landscape under an alien sky filled with a Photon sail spacecraft, its large triangular sail illuminated by distant stars. The wolf, with piercing yellow eyes, continues its journey undeterred by the otherworldly sight above. The scene is set on an extraterrestrial terrain reminiscent of a moon or another planet, with the vast universe as the backdrop, highlighting the wolf's solitary trek and the intriguing presence of advanced technology in this desolate environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2071
|
videos/HRA_part0/2071.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a brown jacket, attentively wipes a gerbil, held gently in his hands, using a small towel, under the warm glow of studio lights. The gerbil, appearing relaxed and well-cared for, is nestled in the director's hands, which are meticulously cleaning it. The director's demeanor suggests a careful and nurturing approach to handling the small animal, creating a contrast between his authoritative role on set and this tender moment of care.]"
},
{
"from": "gpt",
"value": "Bad. The director's hand, the hamster's head, and paws were generated abnormally in the video."
}
] |
seed44_2130
|
videos/HRA_part1/2130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dimly lit office cluttered with books and papers, a distinguished lawyer, wearing a gray suit, sits pensively at his desk, his glasses perched on the tip of his nose as he scrutinizes documents. Unbeknownst to him, a tiny brown mouse crawls across the worn wooden surface of the desk, pausing to nibble on a crumb near a row of neatly arranged ink bottles. The lawyer's focus remains on his work, unaware of the small creature sharing his workspace, as the mouse continues its journey across the desk.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1829
|
videos/HRA_part0/1829.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, captivating squid floats in the deep sea, its body a mesmerizing blend of purples and pinks, illuminated by bioluminescent lights. The creature's eyes are large and expressive, conveying intelligence and curiosity. Its tentacles, adorned with suckers, gracefully undulate in the water, while its two feeding tentacles extend forward, ready to capture prey. The intricate patterns on its skin shift and change, creating an otherworldly display as it moves through the dark, mysterious depths of the ocean.]"
},
{
"from": "gpt",
"value": "Bad. The squid's body is twisted in the video."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.