video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_3041
|
videos/HRA_part2/3041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by her stethoscope and medical attire, navigates a lunar buggy across the moon's desolate surface, which is marked by craters and strewn with rocks. The buggy's wheels kick up fine lunar dust as it traverses the barren landscape. The doctor's face, visible through the helmet of her spacesuit, reflects determination and focus. In a close-up shot, a small, resilient insect-like creature crawls slowly across the moon's rocky terrain, its tiny legs moving deliberately against the stark, gray backdrop. The buggy continues its journey, passing near the crawling creature, emphasizing the contrasting scales of movement and life on the moon.]"
},
{
"from": "gpt",
"value": "Bad. The insect-like movements in the video are not smooth."
}
] |
seed46_1091
|
videos/HRA_part2/1091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical space-themed wedding set against a cosmic backdrop filled with stars and galaxies, a charming hedgehog, adorned with a tiny top hat and bow tie, serves as the ring bearer. The ceremony takes place on a floating platform amidst a zero-gravity environment. During the reception, the hedgehog enjoys a unique swimming experience in a clear, spherical water tank, effortlessly paddling with its limbs while maintaining its adorable appearance, all while the celebration continues around it.]"
},
{
"from": "gpt",
"value": "Bad. The middle frame of the video shows a scene change where the top hat and bow tie suddenly disappear, and the hedgehog's limbs are generated abnormally."
}
] |
seed44_1050
|
videos/HRA_part1/1050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dolphin breaches the surface of a turquoise ocean, its sleek gray body glistening in the sunlight, against a backdrop of a clear blue sky and calm seas. Moments later, it swims gracefully underwater, surrounded by the vibrant marine life of a coral reef, including colorful fish and swaying sea fans. Then, the dolphin leaps again, this time performing a stunning aerial maneuver with the sun illuminating its form from below, highlighting its agility and beauty. Finally, it returns to the depths, swimming alongside a school of shimmering silver fish, the underwater world coming alive around it, showcasing the dolphin's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1771
|
videos/HRA_part2/1771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, equipped with a duty belt and a radio, is seen kneeling on a polished wooden floor in a residential setting, attentively wiping the muddy paws of a large, brown dog. The officer wears a serious expression, focused on the task at hand, ensuring the canine's paws are clean. The environment is warm and welcoming, with a Christmas tree in the background, decorated with colorful ornaments and lights, adding a festive touch to the scene. The officer's careful actions and the presence of the holiday decorations create a sense of care and community during the holiday season.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's wiping motion in the video is basically normal, but the area being wiped is not the dog's paw."
}
] |
seed42_1346
|
videos/HRA_part0/1346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 woman with a glowing face, adorned in a dazzling silver spacesuit, performs at a cosmic concert under the celestial dome of twinkling stars. She begins her act crawling across a zero-gravity stage, her movements graceful and fluid in the absence of Earth's pull. The backdrop is a breathtaking galaxy panorama, with nebulae and planets adding a surreal touch to the spectacle. The atmosphere is charged with anticipation and excitement as she interacts with the floating audience, creating an unforgettable experience in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, the face is distorted, and the legs are deformed."
}
] |
seed46_2797
|
videos/HRA_part2/2797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, embodying a rugged explorer, traverses a dense tropical dry forest, wiping beads of sweat from his brow. Surrounded by towering trees with gnarled roots and sparse foliage, he navigates the arid landscape, dressed in khaki cargo pants, a beige tank top, and a wide-brimmed hat. The scene is illuminated by the golden glow of late afternoon sunlight filtering through the canopy, casting dappled shadows on the ground. The explorer pauses, wiping away perspiration with a cloth, revealing a map in his hands, hinting at his quest for hidden treasures within the unforgiving yet enchanting wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The explorer's movements in the video are not smooth."
}
] |
seed46_2885
|
videos/HRA_part2/2885.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a gray suit, white shirt, and blue tie, walks purposefully across a futuristic asteroid mining facility. The setting is a large, circular room with a high ceiling and industrial equipment, bathed in a warm orange glow. He carries a brown leather briefcase in his right hand, displaying a confident and focused demeanor. Behind him, the dimly lit interior of the asteroid can be seen, with mining machinery and workers in protective gear visible in the distance. The lawyer's strides are firm and decisive, highlighting his determination and professionalism in this unique and challenging environment.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's face and hands are distorted in the video."
}
] |
seed46_2961
|
videos/HRA_part2/2961.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow vest and hard hat, finds a moment of joy as he dances alone in the vast, sun-baked expanse of a subtropical desert. The dunes stretch endlessly under a cloudless sky, the horizon melding seamlessly into the distance. His movements, expressive and free, contrast sharply with the stillness of the arid landscape. The golden sands ripple beneath his boots, each step a fleeting imprint in the relentless expanse. As he twirls and leaps, the desert becomes his stage, the unyielding sun his spotlight, capturing a fleeting moment of uninhibited happiness in an otherwise harsh environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2340
|
videos/HRA_part1/2340.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a casual outfit of a gray t-shirt and khaki pants, takes a break from his usual duties to fix a leaky faucet. He is shown kneeling before a bathroom sink, tools in hand, with a look of determination on his face. The scene is set in a small restroom, with beige walls and a window casting natural light onto the countertop. As he works, the camera captures his focused expression and the intricate details of the plumbing, highlighting the contrast between his customer service role and his unexpected handyman task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2382
|
videos/HRA_part0/2382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and name tag, is fixing a mountain bike in a community center. The space is filled with various tools hanging from the walls, and the officer is seen working intently on the bike's rear wheel. He wears a utility belt with a radio and other equipment, emphasizing his official role. The bicycle, with its vibrant red frame, is partially disassembled, showing the officer's commitment to helping the community beyond his law enforcement duties. The scene takes place indoors, with fluorescent lights casting a warm glow on the officer and the bike, highlighting the act of service in a public space.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2113
|
videos/HRA_part1/2113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a gray jacket over a white shirt and black pants, is hard at work unclogging a drain in a dimly lit room. He kneels on the floor, his focus intense as he uses a metal tool to clear the clog. The scene is framed by pipes and machinery, emphasizing the industrial setting. His work is meticulous, as he carefully removes debris from the drain, revealing the inner workings of the pipe. Throughout, his dedication to the task is evident, as he ensures the drain is thoroughly cleared, the water now flowing freely, with the satisfaction of a job well done apparent in his demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm undergo deformity and mutation."
}
] |
seed44_1022
|
videos/HRA_part1/1022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female nurse walks briskly down a hospital corridor, her blonde hair tied back in a neat bun. She wears a sky-blue uniform, gray tights, and white shoes. A stethoscope hangs around her neck, and she carries a clipboard in her right hand. The hallway is brightly lit, with a green floor and doors lining either side. The nurse's confident stride and professional attire convey a sense of purpose and dedication to her duties within the healthcare facility.]"
},
{
"from": "gpt",
"value": "Normal. The hand and face generation of the character in the video is problematic."
}
] |
seed42_1843
|
videos/HRA_part0/1843.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 miniature town setting, an engineer, dressed in a blue jumpsuit and safety helmet, crouches next to a tiny gerbil wearing a matching miniature outfit. The scene is set against a backdrop of small, detailed town models, with the engineer gently assisting the gerbil as it explores its environment. The focus is on the interaction between the engineer and the gerbil, emphasizing the care and attention given to the small creature within the context of the meticulously crafted townscape.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the safety helmet."
}
] |
seed42_2282
|
videos/HRA_part0/2282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clad in a grey jumpsuit and safety helmet walks through a lush, green landscape, holding a clipboard. In the background, a koala casually climbs down from a eucalyptus tree, its furry body contrasting against the vibrant vegetation. The engineer stops to observe the koala, crouching down to examine it closely, while still maintaining a professional demeanor. The scene is set under a clear blue sky, with sunlight filtering through the leaves, highlighting the interaction between the human and the wildlife in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2159
|
videos/HRA_part1/2159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a classic black vest and white shirt, serves a tray of colorful cocktails to a hyena lounging poolside. The hyena, wearing sunglasses and a lei, enjoys its day off from the wild, basking in the sun. Suddenly, the hyena leaps into the swimming pool with playful abandon, while the waiter looks on, amused yet professional, maintaining his composure despite the unexpected splash. The scene captures a surreal moment of relaxation and fun, blending elements of the exotic and the everyday.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1571
|
videos/HRA_part1/1571.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara is seen swimming across a tranquil body of water, its ears and nose poking above the surface as it propels itself forward with powerful kicks from its webbed feet. The scene is set against a lush, green forest backdrop, with sunlight filtering through the trees and casting dappled shadows on the water. Peaceful ripples spread out from the capybara's movements, creating a serene and captivating view of this aquatic rodent in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2097
|
videos/HRA_part0/2097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent cheetah leaps across the golden savanna, its body stretched in mid-air with power and grace. The sun illuminates the cheetah's spotted coat, highlighting the taut muscles beneath as it propels itself forward. In the background, acacia trees stand silhouetted against the horizon, their branches reaching towards the clear blue sky. The cheetah's eyes are fixed on its target, a burst of speed and agility encapsulated in this single, awe-inspiring moment.]"
},
{
"from": "gpt",
"value": "Normal. The cheetah's limbs are missing in the video, and the head was not generated."
}
] |
seed42_1658
|
videos/HRA_part0/1658.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 leopard-print outfit, leaps gracefully over a series of low, wooden hurdles set against a green, grassy field, reminiscent of an athletic training montage. Her hair is tied back in a bun, and she wears minimal jewelry, allowing her fluid movements to take center stage. As she jumps, her body is captured mid-air, highlighting her strength and agility. The sunlight filters through the trees, casting dappled shadows on the ground, adding a dramatic effect to the scene. Behind her, a lush forest provides a natural backdrop, further emphasizing the wild and free spirit embodied by the leaping woman.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed44_1013
|
videos/HRA_part1/1013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a futuristic silver jumpsuit and helmet, dances joyously on a meticulously designed space movie set, surrounded by intricate control panels and glowing buttons. The set is filled with high-tech equipment and large, detailed screens displaying cosmic visuals. The writer's movements are expressive and free, conveying a sense of liberation and creativity amidst the futuristic environment. As they dance, the lights from the set illuminate their figure, highlighting their passion for storytelling in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's limbs generation in the video is unreasonable."
}
] |
seed42_1662
|
videos/HRA_part0/1662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant zoological park, a woman wearing a yellow jacket and khaki pants runs along a winding path surrounded by lush greenery. As she moves, her attention is drawn to an adorable hedgehog scurrying across the trail, its tiny feet moving swiftly beneath its spiky exterior. The hedgehog pauses for a moment, looking up at the woman with curious eyes before continuing on its way, blending into the underbrush. The woman, smiling at the encounter, resumes her run, passing by various enclosures housing majestic animals, all set against the backdrop of a sunny day in the sprawling park.]"
},
{
"from": "gpt",
"value": "Bad. The woman's face, hands, and feet in the video are generated abnormally, and there are issues with the hedgehog's head and feet."
}
] |
seed42_2836
|
videos/HRA_part0/2836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 surprising and whimsical scene, a small, cartoonish grey elephant, adorned with a red polka-dotted bow around its neck, is shown mid-jump, its trunk lifted playfully. Against a vivid, clear blue sky, this joyful creature leaps from a lush green meadow dotted with yellow flowers, capturing a moment of pure delight and fantasy. The elephant's large ears are spread wide, adding to the comical effect, while its tiny eyes are closed in sheer happiness, creating a charming and unforgettable visual.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1521
|
videos/HRA_part1/1521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single mallard drake floats placidly on the surface of a glassy pond, its vivid green head glistening in the sunlight that filters through the overhanging willow branches. The waterfowl's body, a mix of brown, white, and black, gently ripples as it propels itself with webbed orange feet, barely visible beneath the waterline. Its alert eyes, set in a face that is the epitome of avian grace, scan the surroundings as it navigates the serene waters, unbothered by the tranquility that envelops the scene.]"
},
{
"from": "gpt",
"value": "Normal. No orange webbed feet were generated."
}
] |
seed46_2394
|
videos/HRA_part2/2394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, anthropomorphic setting, a weasel, dressed in a white doctor's coat over a blue shirt and tie, crawls on its belly across a cluttered desk filled with medical books and instruments, its eyes intently focused on a miniature stethoscope just out of reach. The desk is awash in a warm, golden light, casting long shadows and highlighting the weasel's determination. Behind the desk, a large window frames a bustling city skyline at sunset, adding a sense of urgency and drama to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The weasel's movements in the video are not smooth."
}
] |
seed42_2753
|
videos/HRA_part0/2753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stark juxtaposition, a majestic brown horse gallops across a lush green meadow under a vibrant blue sky speckled with white clouds, the rolling hills framing the scene beautifully. Meanwhile, in the distance, smokestacks from sprawling factories loom, emitting plumes of gray smoke into the air. On the ground near the horse, a small creature crawls, its perspective offering a unique view of the vast landscape, highlighting the contrast between nature's grace and industrial might.]"
},
{
"from": "gpt",
"value": "Bad. The galloping action of the horse in the video is not very continuous, there is a lack of coordination; the crawling action of the small animal is not smooth and continuous, there are abrupt changes."
}
] |
seed44_1177
|
videos/HRA_part1/1177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest and blue jeans, playfully swings a baseball bat near a serene swimming pool, backlit by the golden hour sunlight. He pauses mid-swing, the bat held aloft, with the shimmering water and lush greenery framing the scene. The worker then leans on the bat, gazing pensively at the inviting pool, the warm glow of the setting sun casting long shadows across the tranquil water. Finally, he takes a powerful swing, the motion frozen in time, with the idyllic pool setting and the vibrant colors of nature providing a vivid contrast to his robust action.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2442
|
videos/HRA_part1/2442.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiger, drenched in sunlight, strides into a serene pond, its striped coat shimmering against the clear water. Gracefully, it begins to swim, powerful paws propelling it forward, with droplets scattering from its body. The water's surface reflects the lush greenery surrounding the pond, creating a tranquil atmosphere as the tiger continues to paddle through the calm waters, highlighting its unexpected aquatic prowess.]"
},
{
"from": "gpt",
"value": "Normal. The tiger's legs in the video have issues."
}
] |
seed42_2604
|
videos/HRA_part0/2604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown leather jacket and stylish glasses, stands confidently at the edge of a swimming pool, meticulously observing an ibex gracefully swimming underwater. The ibex, a sure-footed mountain-dwelling mammal, is shown in a surreal scene, effortlessly gliding through the clear blue water, its horns visible above its head. The director's focused gaze and the ibex's unusual aquatic activity create a captivating and thought-provoking visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The swimming movements of the bharal in the video are very discontinuous, with abrupt changes."
}
] |
seed46_2928
|
videos/HRA_part2/2928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, typically known for its sturdy build and earthy tones, is depicted in an unexpected scenario, engaging in a joyful dance within its natural habitat. The badger, adorned with a red bow tie and a small top hat, moves energetically to an unseen beat, surrounded by lush greenery and under the shade of towering trees. Its dance is characterized by playful twirls and energetic hops, a stark contrast to its usual demeanor, all captured in a whimsical and vibrant scene that highlights the unexpected delight of a dancing badger in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the badger in the video are missing, the face is deformed, and the bow tie is not fully generated."
}
] |
seed44_2572
|
videos/HRA_part1/2572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, distinguished by its large ears and tusks, is depicted swimming in a serene, reflective body of water under a starlit sky, evoking a sense of tranquility and vastness. The elephant is shown in a three-quarter view, with water droplets visible on its skin, indicating its aquatic activity. The stars above, including the prominent red dot of Mars, twinkle in the dark, clear night sky, providing a cosmic backdrop to the scene. The elephant's trunk is partially submerged, and its eyes are closed, conveying a peaceful, almost meditative state as it floats in the water, encapsulating the unique combination of stargazing and swimming.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1075
|
videos/HRA_part1/1075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, clad in a brown jacket and khaki pants, stands in a lush, green forest clearing, gently wiping mud off the antlers of a majestic deer using a soft cloth. The deer, with large, inquisitive eyes, tolerates the man's ministrations, standing still as the man carefully cleans each tine of the impressive antlers. Sunlight filters through the canopy above, casting dappled shadows on the scene below, highlighting the tender interaction between the man and the wild creature.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a third hand."
}
] |
seed46_2771
|
videos/HRA_part2/2771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary director, dressed in a classic pinstripe suit, stands in a vast, dimly lit studio, skillfully orchestrating a surreal scene. Nearby, a Robot astronaut, adorned in a sleek silver spacesuit with gleaming gold accents, follows the director's guidance as it begins to dance. The robot's movements are fluid and precise, a captivating fusion of technology and artistry, set against the backdrop of cinematic equipment and the director's watchful gaze, creating a mesmerizing spectacle where reality meets imagination.]"
},
{
"from": "gpt",
"value": "Bad. The robot's movements in the video are not smooth."
}
] |
seed42_1712
|
videos/HRA_part0/1712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, predominantly gray with distinctive black markings, perches on a stone statue in the middle of a bustling city square. It has a full, rounded body, and its wings are slightly spread, revealing a flash of green and purple iridescence near the base. Its head, adorned with a small red beak, turns to face the camera, displaying its alertness and curiosity. The bird's legs, pink and sturdy, grip the statue firmly, while its red eyes, surrounded by yellow orbital rings, watch the surroundings keenly. The pigeon is set against a backdrop of urban life, with pedestrians, buildings, and traffic providing a sense of scale and context.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1032
|
videos/HRA_part2/1032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 police officer, dressed in a navy uniform with a badge, cap, and sunglasses, stands at the edge of a zoo's flamingo enclosure, where vibrant pink birds congregate. The scene shifts slightly to reveal a clear blue pool within the zoological park, where the officer now interacts with the public, demonstrating water safety techniques. Nearby, children and families watch, some seated on benches under the shade of lush trees, while others lean on the railing, observing the swimming demonstration with interest. Throughout, the police officer remains engaged and attentive, fostering a sense of community and safety among the zoo visitors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1224
|
videos/HRA_part0/1224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue uniform and a stethoscope around her neck, is delightedly interacting with a small gerbil in a cozy living room. The gerbil, perched on a tiny platform, suddenly leaps into the air, its action frozen in mid-jump, capturing a moment of playful exuberance. The nurse, with a warm smile, watches the gerbil's antics, her caring demeanor evident in her facial expression and body language. The scene is set against a backdrop of a homely living space, with a couch, coffee table, and various household items visible in the background, creating a sense of domestic tranquility.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's fingers are deformed, the hamster's body is twisted, the claws are deformed, and the tail is twisted."
}
] |
seed44_1925
|
videos/HRA_part1/1925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature male silverback gorilla, marked by a prominent sagittal crest and large, powerful body, crawls through dense, lush vegetation in a misty, mountainous habitat. His dark fur stands out against the vibrant greenery, and his expressive face, complete with attentive eyes and a strong jawline, conveys a sense of intelligence and strength. The scene is set in a protected wildlife reserve, where the gorilla moves purposefully through the undergrowth, highlighting the beauty and resilience of these endangered primates in their natural environment.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the gorilla in the video are missing, and the nose is generated incorrectly."
}
] |
seed42_3045
|
videos/HRA_part0/3045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, exhibiting a gentle demeanor, caresses another smaller chimpanzee with its right hand, both sitting on a brown surface against a green background. The larger chimpanzee, with a caring expression, tenderly strokes the younger one, fostering a sense of intimacy and connection. This heartwarming scene captures the essence of compassion within the primate family, highlighting the nurturing bond between the two creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's movements against the smaller chimpanzee in the video are basically normal, with slight awkwardness."
}
] |
seed46_2107
|
videos/HRA_part2/2107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a casual gray t-shirt and blue jeans, is seen unloading a dishwasher in a modern kitchen with sleek, stainless steel appliances. The room is well-lit, casting a warm glow over the beige walls and brown cabinets. The student, sporting a short haircut and glasses, carefully removes dishes from the lower rack, placing them into a cabinet just above the dishwasher. With each item placed, the student's movements are deliberate and efficient, showing a routine familiarity with the task. The space is tidy and minimalistic, with a small dining table in the corner and a window letting in natural light, creating a homely atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3154
|
videos/HRA_part0/3154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful female teacher, wearing a green shirt and black pants, is seen in a classroom with a high ceiling, assembling a wooden table. The room is filled with natural light from large windows, illuminating the space. She is kneeling on the floor, carefully screwing in a leg of the table with a screwdriver, demonstrating a practical skill to her attentive students, who watch from a distance. The teacher's patience and focus are evident as she meticulously puts together the piece of furniture, providing a valuable learning experience in a bright and welcoming environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2662
|
videos/HRA_part2/2662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, wearing a yellow vest over a dark jacket and shirt, pushes a green cart filled with cleaning supplies across a wide, empty corridor. A small gerbil, held gently in his right hand, sits atop a red mop head, seemingly unfazed by its unusual perch. The janitor walks with purpose, his left hand resting on the cart's handle, while the gerbil remains calmly perched on the mop, offering a peculiar yet endearing contrast to the mundane task of cleaning.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slight disharmony."
}
] |
seed42_204
|
videos/HRA_part0/204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled woman stands in a dimly lit classroom, adorned with scientific posters and models, wearing a blue shirt, black pants, and sneakers, holding a book titled 'Dark Matter'. She speaks passionately about dark matter research, gesturing toward a whiteboard filled with complex equations and diagrams. Suddenly, she transitions into a swimming instructor, standing poolside at an indoor swimming facility. Dressed in a blue swimsuit and cap, she demonstrates proper swimming techniques, her movements fluid and confident, as students watch attentively from the water. Throughout the scene, educational elements and swimming gear are prominently displayed, blending the worlds of academia and aquatic sports seamlessly.]"
},
{
"from": "gpt",
"value": "Bad. In the swimming pool scene, the heads and hands of the middle-aged woman and the student are generated abnormally."
}
] |
seed42_1785
|
videos/HRA_part0/1785.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, wearing a casual gray shirt, is captured in high definition as he dances alone on a vast, luxurious resort balcony. The setting sun illuminates the horizon, casting a warm glow on the scene. He moves gracefully, his body language expressing pure joy and freedom. In the background, a sprawling, upscale resort with numerous balconies and lush greenery can be seen, highlighting the exotic location. The actor's movements are fluid and expressive, conveying the essence of a carefree spirit embracing the beauty of his surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2449
|
videos/HRA_part2/2449.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning male pheasant, adorned with vibrant plumage of iridescent greens and blues, struts proudly across a lush meadow filled with tall grasses and wildflowers. The sunlight filters through the canopy of towering trees, casting dappled shadows that accentuate the bird's magnificent feathers. The pheasant pauses, its sharp eyes scanning the surroundings, before letting out a distinctive call that echoes through the peaceful countryside, asserting its presence in the rich, natural habitat that surrounds it.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2686
|
videos/HRA_part0/2686.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 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 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": "Good. Basically no problem."
}
] |
seed42_2310
|
videos/HRA_part0/2310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature man, possibly a writer, wearing a brown jacket, blue shirt, and khaki pants, stands pensively on a rocky cliff overlooking a vast, stormy sea. He wipes his face with his right hand, perhaps reflecting a moment of emotional intensity or physical exertion, as he contemplates the dramatic landscape before him. The rugged terrain and turbulent waters provide a striking contrast to his thoughtful demeanor, emphasizing the solitude and grandeur of his surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the man using his right hand to wipe his face, the action is basically normal but there is some lack of coordination."
}
] |
seed46_1050
|
videos/HRA_part2/1050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dolphin breaches the surface of a turquoise ocean, its sleek gray body glistening in the sunlight, against a backdrop of a clear blue sky and calm seas. Moments later, it swims gracefully underwater, surrounded by the vibrant marine life of a coral reef, including colorful fish and swaying sea fans. Then, the dolphin leaps again, this time performing a stunning aerial maneuver with the sun illuminating its form from below, highlighting its agility and beauty. Finally, it returns to the depths, swimming alongside a school of shimmering silver fish, the underwater world coming alive around it, showcasing the dolphin's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Bad. The dolphin's movements in the video are not smooth and coordinated."
}
] |
seed46_1350
|
videos/HRA_part2/1350.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, with its distinct black and white striped face and grey fur, walks purposefully across a lush, green meadow under the dappled shade of tall trees. It pauses for a moment, standing on all fours, to sniff the air with its keen sense of smell. Then, it continues its journey, moving with a slight waddle due to its sturdy build, leaving behind a trail in the soft grass. The scene is set in the peaceful serenity of nature, with the badger as the sole focus, highlighting its natural habitat and behavior.]"
},
{
"from": "gpt",
"value": "Normal. The facial features of the European badger in the video are missing, the claws are not fully generated, and there are parts of the limbs missing."
}
] |
seed42_1401
|
videos/HRA_part0/1401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 human-sized fox, wearing a doctor's outfit complete with a white lab coat, blue shirt, and stethoscope around its neck, walks purposefully down a hospital corridor. The fox's facial features are clearly visible, with a furrowed brow conveying concern and determination. The hospital hallway is brightly lit, with white walls and linoleum flooring, and the fox strides confidently, passing by various medical equipment and posters hanging on the walls. Despite being a fox, it carries itself with the poise and professionalism expected of a medical professional.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1836
|
videos/HRA_part0/1836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room, a writer sits at a large wooden desk, adorned with a typewriter, a glass of whiskey, and a half-smoked cigar. Dressed in a brown leather jacket, black shirt, and jeans, he appears rugged and disheveled. Behind him, an open window reveals the gritty urban landscape of a city at night. Suddenly, the scene shifts to a close-up of a rhinoceros, its gray skin wrinkled and textured. The animal is being gently wiped down by a caregiver, who uses a cloth to clean its face, highlighting the creature's large size and docile nature. The juxtaposition of the writer and the rhinoceros creates a surreal and thought-provoking image.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1477
|
videos/HRA_part0/1477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating scene, a distinguished film director, clad in a black jacket, blue jeans, and brown boots, stands on a rocky outcropping, passionately directing the action. Nearby, an agile ibex leaps over a boulder with remarkable grace, its brown fur and curved horns vivid against the craggy landscape. The camera focuses on the ibex mid-jump, capturing the animal's strength and agility, while the director observes intently, his silhouette framed against the dramatic mountain scenery.]"
},
{
"from": "gpt",
"value": "Bad. The sheep shows deformities and distortions during the jump."
}
] |
seed44_3216
|
videos/HRA_part1/3216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray jacket and blue jeans, runs with a determined look across a desolate industrial landscape dominated by oil refineries. The scene opens with him striding purposefully, his gaze fixed ahead. Next, he's seen mid-stride, his right arm extended forward, the refineries' towering structures and billowing smokestacks looming behind him. Then, he's captured in motion, his left foot lifting from the ground, the industrial backdrop providing a stark contrast to his vibrant attire. Finally, the artist continues his run, his silhouette framed against the imposing oil refinery complex, embodying resilience and movement in an urban-industrial setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed42_3176
|
videos/HRA_part0/3176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, clad in a white lab coat over a blue shirt and khaki pants, stands on the starship bridge command, surrounded by high-tech equipment and screens displaying complex data. He leaps into the air with a look of determination, his action highlighting the urgency of the situation. Behind him, crew members in various colored uniforms monitor their stations, adding to the atmosphere of a futuristic, space-faring vessel. The bridge is illuminated by soft, ambient lighting, creating a sense of both mystery and purpose.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1120
|
videos/HRA_part0/1120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull, distinguished by its gray wings, white body, and yellow legs, stands prominently on a sandy beach. It faces left, capturing its silhouette against a stunning sunset. The bird's right wing is slightly raised, creating a dramatic effect. Its beak, also yellow, is curved, adding to its distinctive appearance. In another scene, the seagull takes flight, soaring above the ocean waves, its wings fully extended, against a clear blue sky. The final shot focuses on the gull's piercing eyes, accentuated by its white feathers, as it perches on a rocky outcropping, offering a compelling close-up of this resilient bird.]"
},
{
"from": "gpt",
"value": "Bad. The seagull becomes deformed, its wings detach from its body, and its head disappears at one point and then reappears."
}
] |
seed46_2324
|
videos/HRA_part2/2324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, embodying the essence of carefree summer days, walks along a pristine beach with white sand, wearing a vibrant floral shirt, khaki shorts, and brown leather sandals. He gently caresses the smooth, sun-warmed surface of a driftwood log, as the crystal-clear turquoise waters of the sea softly lap at the shore behind him. The serene beach landscape, with lush greenery and palm trees framing the horizon, complements the peaceful atmosphere. The man's relaxed posture and the idyllic beach setting evoke a sense of tranquility and connection with nature.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs in the video have generation issues, with the legs penetrating the model during walking, and the facial features are not generated."
}
] |
seed44_2356
|
videos/HRA_part1/2356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a white lab coat over a blue shirt and khaki pants, sneezes dramatically while working in a clean, well-lit laboratory filled with advanced technology and scientific equipment. The scene captures the unexpected moment as he leans over a workstation, his glasses momentarily fogging up, surrounded by computers and high-tech machinery, emphasizing the contrast between the precision of his work and the human element of a simple sneeze.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2518
|
videos/HRA_part0/2518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil woodlands setting, characterized by lush vegetation and a serene atmosphere, a herd of majestic buffalo graze peacefully. The scene focuses on a single buffalo, its massive frame gently caressed by the soft branches of a weeping willow tree. The willow's slender leaves delicately brush against the buffalo's sturdy body, creating a tender and unexpected interaction between nature and wildlife. The buffalo's calm demeanor and the gentle sway of the willow branches in the breeze convey a sense of harmony and tranquility in the midst of the dense woodland.]"
},
{
"from": "gpt",
"value": "Good. The bison's action of eating grass in the video is basically normal."
}
] |
seed42_2357
|
videos/HRA_part0/2357.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hare, donning a red apron and a name tag, works diligently as a cashier in a charming store nestled deep within a lush rainforest. The store's wooden shelves are stocked with unique items, including exotic fruits, colorful fabrics, and handmade crafts. Outside, the vibrant rainforest comes alive with the sounds of wildlife and the gentle patter of rain. Suddenly, the hare takes a break and ventures outside, where it encounters a serene natural pool, its clear waters inviting for a refreshing swim amidst the emerald greenery. The hare, now in swimming attire, joyfully splashes in the pool, surrounded by the lush foliage and the calming atmosphere of the rainforest.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2761
|
videos/HRA_part1/2761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, balding with a gray beard, wearing a dark green jacket, khaki pants, and brown work boots, is seen wiping the exterior of a car with a cloth. He moves methodically, first focusing on the hood, then the roof, and finally the trunk, ensuring every inch is clean. The car, a sleek black sedan, is parked in a dimly lit garage, with the man's cleaning efforts illuminated by a single overhead light. He then proceeds to polish the car windows, his attention to detail evident as he works diligently to remove any smudges. Throughout the scene, the man's attire remains consistent, consisting of the same dark green jacket, khaki pants, and brown work boots, as he cleans the car in the subdued environment of the garage.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2805
|
videos/HRA_part0/2805.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy blue uniform with a badge and name tag, stands tall on a bustling city sidewalk, holding a walkie-talkie in his right hand. Behind him, a busy street scene unfolds, complete with pedestrians, traffic, and urban architecture. The officer's authoritative stance and alert demeanor convey a sense of duty and readiness, embodying the role of law enforcement in the heart of the city. His left hand rests on his belt, which holds various tools of his trade, while his eyes survey the surroundings with watchful vigilance.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted in the video."
}
] |
seed42_1522
|
videos/HRA_part0/1522.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_2932
|
videos/HRA_part0/2932.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 brown rat is seen leaping through dense heathland, its body mid-air as it propels itself forward over the foliage. The rodent's movement is captured in detail, showcasing its agility and strength as it navigates the underbrush. The surroundings consist of abundant greenery, with the rat's jump highlighting its natural habitat among the heaths. The focus remains on the rat throughout, emphasizing its action-packed leap within the lush environment.]"
},
{
"from": "gpt",
"value": "Normal. The brown rat in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2805
|
videos/HRA_part0/2805.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy blue uniform with a badge and name tag, stands tall on a bustling city sidewalk, holding a walkie-talkie in his right hand. Behind him, a busy street scene unfolds, complete with pedestrians, traffic, and urban architecture. The officer's authoritative stance and alert demeanor convey a sense of duty and readiness, embodying the role of law enforcement in the heart of the city. His left hand rests on his belt, which holds various tools of his trade, while his eyes survey the surroundings with watchful vigilance.]"
},
{
"from": "gpt",
"value": "Normal. The police in the video did not move."
}
] |
seed42_2178
|
videos/HRA_part0/2178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with brown, shoulder-length hair unloads a stainless steel dishwasher in a modern kitchen with white cabinets and marble countertops. She wears a simple white T-shirt, blue jeans, and an apron, and her glasses rest on the tip of her nose as she intently organizes the dishes. The room is bright, with sunlight streaming in from a nearby window, illuminating the space and casting a warm glow on the polished floor. As she works, her movements are efficient and practiced, demonstrating her familiarity with the task.]"
},
{
"from": "gpt",
"value": "Normal. No glasses or windows were generated."
}
] |
seed44_1090
|
videos/HRA_part1/1090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, finch perches on a branch, its vibrant yellow feathers contrasting beautifully against the lush green foliage. The bird's eyes sparkle with curiosity as it tilts its head, listening to the distant sounds of nature. Its beak, perfectly shaped for cracking seeds, opens slightly as it lets out a melodic chirp, filling the air with its song. The sunlight filters through the leaves, casting dappled shadows onto the finch, highlighting the intricate patterns on its wings. In the background, the outline of a wooden cabin can be seen, nestled among the trees, adding a touch of rustic charm to the serene forest scene.]"
},
{
"from": "gpt",
"value": "Normal. The bird's beak in the video is generated unreasonably, and the claws are not fully generated."
}
] |
seed44_1264
|
videos/HRA_part1/1264.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, wearing a maroon shirt, navy vest, beige khaki pants, and brown hiking boots, pauses on a trail to gaze at a breathtaking mountain vista, his backpack leaning against a tree. Moments later, he sits on a rock, attentively examining something in his hands, perhaps a map or a natural specimen, with the stunning landscape as his backdrop. Then, he hikes uphill, trekking poles in hand, his outfit unchanged, as the lush greenery and distant mountains frame his journey. Finally, he stands at a scenic overlook, savoring the panoramic view, his maroon shirt, navy vest, beige pants, and brown boots standing out against the natural beauty.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands, feet, and face are deformed; the sitting posture is suspended in mid-air; the map and hiking stick in their hand appear suddenly."
}
] |
seed46_1457
|
videos/HRA_part2/1457.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a panda bear, donning a red apron and a name tag, stands behind a cash register in a grocery store decorated with red lanterns and Chinese New Year banners. The panda, with its distinctive black and white fur, is seen wiping the countertop meticulously, using a green cloth, while customers wait patiently in line. The scene captures the unique combination of a panda working as a cashier, diligently cleaning the service area, all within a vibrant and culturally-themed supermarket environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1384
|
videos/HRA_part2/1384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, spiky European hedgehog runs energetically across a lush, green garden, its tiny legs moving swiftly beneath it. The hedgehog, with its distinctive white-tipped spines, navigates through the foliage with determination, its snout pointed forward. In another scene, the hedgehog continues its journey, now scampering across a wooden deck, its movements quick and agile. The video captures the hedgehog's active nature, showcasing its ability to navigate various terrains with ease, all under the cover of night, as indicated by the dimly lit surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1969
|
videos/HRA_part2/1969.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow Labrador dog, wearing a red collar and tags, happily swims in a natural hot spring pool, surrounded by lush green vegetation and a wooden dock. The water, clear and inviting, gently laps at the dog's fur as it paddles with ease. The dog's joyful expression and the serene environment of the hot springs create a peaceful and picturesque scene, enhanced by the vibrant greenery and the warm, bubbling water.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_20
|
videos/HRA_part0/20.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 female cashier with a headband, working at a checkout counter filled with various snacks and beverages, gently caresses a stuffed cheetah. The stuffed animal is placed on the counter next to a cash register, amidst a selection of candy bars. The woman looks lovingly at the toy, her hands tenderly stroking its soft fur, as if sharing a moment of affection with an imaginary companion in the midst of her daily routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1520
|
videos/HRA_part0/1520.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, live chicken stands in the center of a dirt farmyard, surrounded by various farm equipment and buildings in the background. The chicken, with its brown and white feathers, yellow legs, and red comb, scratches the ground with its right foot, searching for food. It then pauses, head held high, seemingly alert to its surroundings. The camera captures a close-up of the chicken's face, highlighting its curious expression and detailed features. Finally, it shows the chicken from a distance, walking away from the camera, offering a full view of its body and movements within the rustic farm setting.]"
},
{
"from": "gpt",
"value": "Normal. The chicken's movements in the video are uncoordinated."
}
] |
seed46_2334
|
videos/HRA_part2/2334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 casual red jacket and dark pants, is seen running along a scenic harbor, the sunlight reflecting off the water. She runs with determination, passing by a variety of ships docked in the harbor, from small sailboats to large cargo vessels. Her movement is fluid and purposeful, her gaze fixed ahead, indicating her focus and drive. The harbor's activity provides a dynamic backdrop, with seagulls flying overhead and the sounds of the bustling waterway adding to the atmosphere. Despite the surroundings, the teacher maintains her pace, her stride strong and consistent as she continues her run along the harbor's edge.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1506
|
videos/HRA_part2/1506.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent tiger, mid-leap, propels itself from a large rock into a lush, green forest, its body stretched out in a powerful arc. The tiger, with its distinctive orange coat patterned with black stripes, exhibits raw strength and grace as it jumps, surrounded by dense foliage and towering trees that provide a natural habitat. The action is captured in stunning detail, focusing on the tiger's muscular form, intense concentration, and the dynamic motion of its leap, encapsulating the essence of wild freedom.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the tiger jumping."
}
] |
seed42_3182
|
videos/HRA_part0/3182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male chef, wearing a clean white chef's jacket with short sleeves, meticulously polishes silverware in a well-lit kitchen. The utensils, which include forks, knives, and spoons, gleam under the bright lights as he works. Behind him, a large window reveals a bustling city skyline during daytime, adding a touch of urban sophistication to the scene. The chef's focused expression and the contrast between the shiny silverware and the white chef's jacket create a visually appealing composition.]"
},
{
"from": "gpt",
"value": "Bad. The chef's hands and utensils in the video are deformed."
}
] |
seed46_3069
|
videos/HRA_part2/3069.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly surreal scene, a large hippopotamus floats effortlessly in a pool located inside a futuristic space station, surrounded by lush vegetation grown through advanced space agriculture techniques. The hippo, appearing relaxed and weightless in the water, is the center of attention in this extraordinary environment designed to support life in outer space. The backdrop features rows of thriving crops illuminated by artificial lights, highlighting the remarkable integration of nature and technology in this extraterrestrial setting.]"
},
{
"from": "gpt",
"value": "Bad. The hippopotamus generation in the video is abnormal."
}
] |
seed42_3023
|
videos/HRA_part0/3023.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."
}
] |
seed42_3190
|
videos/HRA_part0/3190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, pristine oyster rests on a bed of ice, its shell partially open to reveal a lustrous interior. The oyster is large and plump, with a deep cup that holds a pool of clear, briny liquid. Its exterior shell is rough and textured, with shades of gray and brown that contrast sharply with the icy base. A fork and lemon wedge are placed nearby, ready for someone to savor the fresh, oceanic flavors of this exquisite seafood delicacy, all captured under crisp, high-definition lighting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1886
|
videos/HRA_part0/1886.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, clad in rich brown fur, dashes across a lush, verdant forest floor, its bushy tail swaying energetically. The scene is captured in vibrant detail, with the beaver's small ears and alert eyes clearly visible as it navigates the underbrush. Its front paws, equipped with dexterous digits, grip the mossy ground, propelling it forward with a sense of urgency. The background features a dense thicket of trees and foliage, providing a natural habitat for the beaver's lively sprint.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's face and paws in the video are generated abnormally, with two bodies appearing in the middle frame."
}
] |
seed44_2192
|
videos/HRA_part1/2192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a gray T-shirt, blue jeans, and brown shoes, organizes his garage with determination. He begins by sorting through boxes, revealing a cluttered space filled with various items, including bicycles, tools, and old books. As he works, he meticulously arranges the contents, creating order from chaos. The garage walls, adorned with shelves and pegboards, display an array of neatly organized objects, showcasing the writer's commitment to tidiness. Throughout the process, the natural light filtering through the garage windows highlights his efforts, emphasizing the transformation of the space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1854
|
videos/HRA_part2/1854.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a brown leather jacket and jeans, walks alongside a cheetah in a natural savanna setting, both figures dwarfed by the vast, open landscape. The writer, wearing a beige hat, sunglasses, and holding a pen and notebook, looks thoughtful as they stroll together. The cheetah, sporting a tracking collar, walks parallel to the writer, its gaze forward, reflecting a sense of purpose and freedom. Together, they traverse the grassy terrain, the writer occasionally jotting down notes, while the cheetah remains vigilant, embodying the spirit of the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1936
|
videos/HRA_part2/1936.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 police officer, clad in a navy uniform and a crisp white shirt, is spotted joyfully dancing in the middle of a highway during the golden hour. The unexpected scene unfolds as a small vole curiously watches from the roadside grass, adding a touch of whimsy. The officer's movements are lively, yet controlled, drawing the attention of passing motorists who slow down to witness this unusual spectacle. Despite the gravity of his profession, the officer's spontaneous dance embodies a lighthearted moment, offering a brief respite from the monotony of highway travel.]"
},
{
"from": "gpt",
"value": "Bad. The vole mentioned in the caption does not appear in the video."
}
] |
seed46_2108
|
videos/HRA_part2/2108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an imaginative scene, a waiter, dressed in a classic black suit and tie, carefully balances a tray of cocktails above his head as he swims underwater. Surrounding him are porcupines, wearing tiny swim caps and goggles, swimming alongside in a synchronized pattern, all submerged in a vast, clear pool under soft, ambient lighting. The waiter's face, visible beneath the water, shows a mix of concentration and amusement at the unusual company he keeps during his aquatic beverage service.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2477
|
videos/HRA_part1/2477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a high-visibility jacket walks along the edge of a bustling harbor, the sunlight glinting off the water and reflecting onto his safety glasses. He carries a clipboard in one hand, attentively observing the large ships and cranes at work. The harbor is alive with activity, from the loading and unloading of cargo to the movement of tugboats guiding massive vessels. In the distance, the silhouette of a city skyline adds a touch of urbanity to the industrial scene. The engineer stops occasionally to jot down notes, his expertise evident in his confident demeanor and the precision with which he performs his duties.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is slightly distorted, and the hands are twisted."
}
] |
seed46_1383
|
videos/HRA_part2/1383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A musician, dressed in a black jacket and black jeans, is seen in a dimly lit room with a red background, wiping down a hyena that is sitting calmly on a table. The hyena, which has distinctive markings and a serious expression, is being carefully tended to by the musician, who uses a soft cloth to clean its fur. The scene conveys a sense of care and attention to detail, with the musician's focused gaze and gentle movements highlighting the bond between the two beings. Despite the unusual pairing, there is a palpable sense of trust and mutual respect between the musician and the hyena, making for a captivating and intriguing visual.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_200
|
videos/HRA_part2/200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single camel, distinguished by its brown fur and a patterned red, yellow, and green saddle, stands against a desert landscape under a clear blue sky. It begins to move rhythmically, swaying to an unseen beat, its large eyes gazing into the distance. Moments later, it raises its head proudly, its mouth open in a gesture that suggests a joyful call or song. Then, the camel continues its dance, gracefully moving its legs in time with the music, its body language conveying a sense of happiness and freedom in the vast, sandy expanse.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2202
|
videos/HRA_part0/2202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone giraffe runs across an open savanna, its distinctive patterned coat and long legs propelling it forward in a graceful stride. The scene is captured in vibrant detail, with the grassy plains stretching out behind the majestic creature. The sky is a brilliant blue, dotted with fluffy white clouds, providing a stunning contrast to the earthy tones of the giraffe's coat. As it runs, its spots seem to blur, creating a mesmerizing effect that highlights the beauty and power of this remarkable animal.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the giraffe in the video are missing, the face is generated blurry, and the tail is generated unreasonably."
}
] |
seed42_2496
|
videos/HRA_part0/2496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, green-brown jungle cobra crawls across a lush, moss-covered log in the dense rainforest undergrowth. The snake's hood is slightly raised, revealing its distinctive markings as it navigates the textured surface. Sunlight filters through the canopy, casting dappled light on the cobra, emphasizing its muscular body and smooth scales as it moves with purpose and grace in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The snake in the video moves basically normally, with slightly uncoordinated movements."
}
] |
seed42_1623
|
videos/HRA_part0/1623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, likely his cub, against the backdrop of a lush, green savannah during the golden hour. The father lion, with his thick, dark mane, displays affection and protection as he rubs his cheek against the cub's head. The cub, with its curious eyes and playful demeanor, responds with a nuzzle of its own, showcasing the intimate bond between them. This heartwarming interaction unfolds under a sky painted with warm hues of orange and pink, highlighting the emotional connection between the two lions.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1585
|
videos/HRA_part2/1585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, dressed in a costume resembling a zebra, performs an athletic jump against a background that appears to be a theater stage. The zebra outfit is detailed, featuring black and white stripes, and the actor's face is visible, showing intense concentration. The leap is captured mid-air, highlighting the actor's agility and the costume's dynamic movement, creating a dramatic and captivating scene under the spotlight.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2315
|
videos/HRA_part1/2315.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, king of the beasts, is seen in the early morning, wiping its face with its paw in the grasslands of Africa. The lion, with a full, tawny mane, is lying down, using its right paw to wipe its face, perhaps after a recent meal or simply as a grooming habit. The grassy savanna stretches out behind it, dotted with acacia trees, providing a natural habitat for this powerful creature. The sun, still low in the sky, casts a warm glow over the scene, highlighting the lion's golden fur and the textures of the grass.]"
},
{
"from": "gpt",
"value": "Normal. The lion's claws were not fully generated, and there were issues with the eyes."
}
] |
seed42_1085
|
videos/HRA_part0/1085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 short brown hair, neatly trimmed facial hair, and wearing a gray jacket over a blue shirt, tends to lush green plants in a spacious atrium. He waters the plants with a green watering can, moving methodically from one plant to another. The atrium features large windows letting in ample natural light, and the plants are arranged on multiple levels, creating a vibrant indoor garden atmosphere. The man focuses intently on his task, his actions conveying a sense of care and routine, as he nurtures the plants in this verdant environment.]"
},
{
"from": "gpt",
"value": "Normal. The water mentioned in the caption does not appear in the video."
}
] |
seed44_1162
|
videos/HRA_part1/1162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dressed in a flowing, red, full-length dress dances gracefully in the desert landscape at golden hour, with the warm, glowing sunlight illuminating her figure. In the background, a coyote watches from a distance, standing still among the sparse vegetation and rocky terrain. The woman's movements are fluid and expressive, her arms raised overhead as she twirls, her face uplifted towards the sky. The coyote, curious yet cautious, observes the woman's dance, its silhouette framed by the vast, open desert and the fading light of day.]"
},
{
"from": "gpt",
"value": "Bad. The woman's dancing in the video is very unsmooth, and her movements are not coordinated."
}
] |
seed44_284
|
videos/HRA_part1/284.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a lab coat over a collared shirt and khaki pants, gently caresses a hamster in a zero-gravity environment, suggesting space agriculture. The doctor, with neatly trimmed facial hair and spectacles, holds the hamster with care and attentiveness, floating effortlessly in a spaceship's cabin. The hamster, nestled in the palm of the doctor's hand, appears relaxed and comfortable, indicating a nurturing bond between the two. In the background, hydroponic plants grow in LED-lit chambers, emphasizing the agricultural aspect of the scene. The doctor's focus on the hamster, combined with the futuristic setting, conveys a sense of compassion and innovation in space farming.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's movements in the video are slightly unsmooth."
}
] |
seed46_1467
|
videos/HRA_part2/1467.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking beaver, clad in a miniature construction hat and suspenders, jumps enthusiastically over a series of logs arranged like hurdles, against a backdrop of lush greenery. The logs, positioned in a line, serve as obstacles for the beaver to leap over. The scene is set in a vibrant, verdant environment, with the beaver's energetic movements highlighting its industrious nature. As it clears each log, the beaver's determination and agility are evident, showcasing its ability to navigate challenges with agility and grace.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's jumping motion in the video is very unsmooth and uncoordinated."
}
] |
seed44_1812
|
videos/HRA_part1/1812.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, recognized by her messy red hair and paint-splattered white apron over a yellow dress, scrubs the bathroom floor with vigor, her face expressing determination. She uses a green scrub brush and a blue bucket filled with soapy water, set against a backdrop of white tiles. The scene conveys the juxtaposition of creativity and mundane chores, as she kneels on the floor, her hands stained with dirt and her sleeves rolled up, highlighting the physical effort involved in cleaning.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video washes the bathroom floor with basically normal movements, but there is a slight lack of coordination."
}
] |
seed42_1791
|
videos/HRA_part0/1791.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 navy blue shirt and beige trousers, gently caresses a buffalo in a rural setting. The buffalo, with its shaggy brown fur and large horns, stands calmly under a clear blue sky, with lush green grass and distant trees providing a peaceful backdrop. The engineer, showing a tender side, connects with the animal, which is often a symbol of strength and resilience, in a moment of quiet intimacy amidst the natural landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3128
|
videos/HRA_part2/3128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 police officer, clad in a navy uniform with a bulletproof vest, climbs an arduous route up a steep, rocky cliff, demonstrating determination and skill. His equipment includes a helmet, harness, and climbing gear attached to his belt, while he uses a carabiner to secure his rope. The scene is set against a rugged landscape with lush greenery and distant mountains, highlighting the officer's physical prowess and commitment to overcoming challenges. The camera captures his focused face, the intricate details of his gear, and the breathtaking scenery, emphasizing the intensity and purpose of his climb.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2196
|
videos/HRA_part1/2196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy gray cat with white paws is seen swimming in a clear blue pool, surrounded by green foliage. The cat's face shows visible effort as it paddles through the water with its front paws, displaying a unique and unexpected sight. The pool is framed by lush vegetation, creating a natural, serene environment for this unusual feline activity. The cat's determination and the vibrant greenery around the pool form a captivating contrast against the clear blue water.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_288
|
videos/HRA_part2/288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse with short, brown hair and glasses, wearing a patterned, blue medical scrub top and black pants, hangs framed pictures on the walls of a brightly lit hospital room. She stands on a small, yellow stool to reach the wall above a patient's bed, where a colorful, abstract artwork is already hung. The nurse carefully aligns a new frame next to it, creating a comforting environment for patients. She uses a level to ensure each piece is straight, revealing her attention to detail in the cozy, well-decorated space. Throughout, she maintains a warm smile, demonstrating her caring nature as she enhances the room's aesthetic with more framed prints.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1959
|
videos/HRA_part2/1959.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, wearing a gray t-shirt and black tactical pants, stands in a modern, open-plan kitchen with white cabinets and stainless steel appliances. He confidently flips a crepe on a large, round griddle, showcasing his culinary skills. The kitchen is part of a fire station, with a red fire truck visible through an arched doorway behind him. The firefighter, now donning an apron over his attire, carefully adds ingredients to the crepe, demonstrating his ability to balance the demands of firefighting with the precision required in cooking. The scene captures the unexpected yet harmonious blend of a firefighter's life-saving duties and his passion for creating delicious meals.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the hands are twisted, the arms are deformed, and the spatula in hand is also twisted."
}
] |
seed44_2494
|
videos/HRA_part1/2494.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white hare, its fur gleaming under the moonlight, crawls through a dense thicket of green foliage, navigating the intricate maze of branches and leaves with cautious precision. Its ears, erect and alert, swivel at the slightest sound, while its eyes, large and luminous, remain fixed on the path ahead. The hare's hind legs, powerful and agile, propel it forward in a series of controlled movements, each paw carefully placed to ensure silent progression through the undergrowth. The scene is set against the backdrop of a tranquil night, with the stars twinkling overhead and the distant hoots of owls punctuating the serene atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2373
|
videos/HRA_part2/2373.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying the role of an artificial intelligence pilot, performs an energetic dance within a high-tech command center. Dressed in a sleek silver metallic jumpsuit with LED lines, he moves to an unseen beat, surrounded by holographic interfaces and screens displaying futuristic data. The room is bathed in cool blue and purple lights, enhancing the sci-fi atmosphere. His expressive face, complete with augmented reality glasses, shows pure joy and freedom as he seamlessly integrates dance into his AI pilot character, creating a captivating fusion of technology and artistry.]"
},
{
"from": "gpt",
"value": "Bad. The actor's limbs are missing in the video, and the face and body generation are distorted."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.