video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1167
|
videos/HRA_part1/1167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings in the early morning light of the African savanna. Suddenly, it jumps into the air, its body stretched out horizontally, with the vast, grassy plains and distant acacia trees forming a picturesque backdrop. The meerkat lands softly on the ground, its eyes wide and alert, before quickly resuming its watchful stance, ears perked and ready for any sign of danger or activity in the wild landscape that surrounds it.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3009
|
videos/HRA_part1/3009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a police officer, clad in a high-tech suit with neon accents, runs across a rugged asteroid surface illuminated by the distant stars. The officer, equipped with a helmet and breathing apparatus, sprints past mining equipment and industrial structures, indicating an asteroid mining operation. With each stride, the officer's suit glows under the harsh lighting of the asteroid's environment, highlighting the action and determination in this dynamic scene set against the backdrop of space exploration and law enforcement.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the officer running, but the movements are not very continuous and smooth, appearing uncoordinated."
}
] |
seed44_3155
|
videos/HRA_part1/3155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, clad in a red jacket and black pants, is scaling an indoor climbing wall with intense focus, framed by a large window that bathes the scene in natural light. The gymnasium's high ceiling and climbing wall provide a spacious setting, while motivational posters and equipment add context to the environment. The climber's left hand grips a green hold, their right hand poised to grab a blue hold, and both feet are firmly planted on orange footholds, illustrating their progress up the wall. Their backpack rests on the floor, and a climbing harness and helmet ensure safety during the ascent.]"
},
{
"from": "gpt",
"value": "Bad. The student's climbing movements are not smooth."
}
] |
seed44_2046
|
videos/HRA_part1/2046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 janitor, wearing a dark green jacket over a gray shirt, tends to laundry in a busy laundromat. Surrounded by rows of washing machines and dryers, he checks the status of a load in a washer, occasionally glancing at the patrons around him. He then moves to a dryer, where he retrieves a bundle of freshly laundered linens, carefully folding them with practiced hands. Amidst the hum of machinery and the scent of detergent, the janitor continues his duties, maintaining order in the bustling environment. Throughout the scene, he remains focused and diligent, his actions highlighting the routine yet essential task of laundry care in a public space.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's hand generation in the video has issues."
}
] |
seed46_1855
|
videos/HRA_part2/1855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled female doctor in a white lab coat, adorned with colorful pins, dances energetically in a spacious, well-lit room. Her attire includes a vibrant red blouse and stylish glasses, adding to her lively appearance. In her arms, she cradles a relaxed, curious ferret, which seems unperturbed by the dancing. The pair moves in sync, the doctor's joyful expression and the ferret's inquisitive gaze capturing the essence of an unexpected yet delightful moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_286
|
videos/HRA_part0/286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a black cap, sits at a desk in a sparsely decorated room with a large window in the background, casting a grid-like pattern of light and shadow. He leans forward attentively, reading a document with a serious expression, his right elbow resting on the desk and his left hand holding the page. The room is filled with a sense of calm professionalism, with the window providing a source of natural light that illuminates the officer and the paperwork, highlighting his dedication to duty.]"
},
{
"from": "gpt",
"value": "Normal. The officer's hand in the video is deformed, and the hat is generated unnaturally."
}
] |
seed42_2264
|
videos/HRA_part0/2264.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a helmet, leaps into action from a weathered wooden pier extending over a body of water, the afternoon sunlight casting a dramatic glow. The firefighter, equipped with a life vest over his protective clothing, jumps off the end of the pier, the water shimmering beneath him as he descends. In the background, a firetruck is visible, parked on the pier, its red color contrasting against the blue sky and water, adding to the intensity of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed46_1677
|
videos/HRA_part2/1677.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman wearing a yellow shirt and denim jeans is organizing a cluttered garage, illuminated by overhead lights. She sorts through items on a wooden table, her hands moving purposefully. Nearby, a brown dog sits attentively, watching her actions. Behind her, shelves filled with various objects and tools line the walls, indicating a space dedicated to storage and projects. The atmosphere is one of industriousness, as she focuses on tidying the space, creating order from chaos.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2575
|
videos/HRA_part0/2575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young children, a boy and a girl, are energetically shoveling snow in their front yard, surrounded by a wooden fence. The boy wears a brown jacket, gray pants, and a matching hat and mittens, while the girl is dressed in a purple jacket, jeans, and a pink hat and mittens. Both are using small red shovels to clear a path through the fresh, fluffy snow, their faces showing determination and joy. The scene is set against a backdrop of a suburban house, with windows reflecting the bright, sunny day, and a green minivan parked in the driveway, partially covered in snow. The atmosphere is one of cheerful family activity on a crisp, wintry day.]"
},
{
"from": "gpt",
"value": "Normal. The children's faces and hands in the video have generation issues."
}
] |
seed46_3073
|
videos/HRA_part2/3073.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In zero gravity, a male and female astronaut, both clad in navy blue spacesuits with patches and equipped with life support backpacks, engage in a captivating dance. Their movements are fluid and graceful, defying the constraints of Earth's gravity. The man gently caresses the woman's face with his right hand, his fingers tenderly grazing her cheek, while she responds with a warm smile. The intimate moment is set against the backdrop of a space station interior, complete with computers, wires, and scientific equipment, creating a surreal and emotionally charged atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1784
|
videos/HRA_part2/1784.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, clad in a black leather jacket, a graphic tee, and dark jeans, walks his energetic, medium-sized brown dog in an urban park. The artist wears a baseball cap and sports a beard, presenting a relaxed and down-to-earth demeanor. The dog, on a leash, enthusiastically explores the grassy area, its tail wagging. In another scene, the musician, now with his acoustic guitar slung over his back, continues his leisurely stroll, his dog trotting alongside him. The pair strolls past a stone building, adding to the laid-back vibe of the day.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2844
|
videos/HRA_part0/2844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a khaki shirt and beige pants, is seen wiping down an ancient, weathered stone structure at a historical site, with a dingo curiously observing from a distance. The engineer, wearing safety glasses and latex gloves, meticulously cleans the surface using a microfiber cloth, revealing intricate carvings and details. The dingo, standing on the lush grass nearby, watches intently with its ears perked up, adding a touch of wildlife intrigue to the scene. The historical site, featuring crumbling stone walls and archways, is bathed in warm sunlight, casting dramatic shadows and highlighting the textures and history of the location.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's movements while cleaning the stone in the video are basically normal, with slight awkwardness."
}
] |
seed44_1603
|
videos/HRA_part1/1603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his chiseled jawline and dark, neatly styled hair, stands on a wooden chair in a spacious, modern living room. He wears a casual, fitted black t-shirt and dark jeans, and is engaged in the everyday task of changing a light bulb. The room is furnished with a brown leather sofa and a large flat-screen TV on the wall. The actor's focused gaze and confident posture suggest his ease in handling both dramatic roles and practical household chores. The warm, diffused lighting from other fixtures illuminates the scene, highlighting the actor's profile as he completes the relatable task with a touch of understated elegance.]"
},
{
"from": "gpt",
"value": "Bad. The face and fingers of the character in the video have issues."
}
] |
seed44_2489
|
videos/HRA_part1/2489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a creative juxtaposition, a male cashier, clad in a gray shirt and black pants, is seen sprinting energetically across a vast, open space, reminiscent of a track field. Behind him, an enormous screen displays a stunning, high-definition image of Jupiter's iconic Great Red Spot, creating a surreal and captivating visual contrast between the terrestrial and the celestial. The cashier's focused expression and determined stride add a sense of urgency and dynamism to the scene, while the imposing presence of the gas giant's storm serves as a dramatic and awe-inspiring backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2780
|
videos/HRA_part2/2780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, portraying a member of a nanobot repair crew, leaps dramatically across a futuristic, metallic platform. Dressed in a silver jumpsuit, complete with utility belts and pouches, he soars through the air with intense focus. His movements are agile and purposeful, suggesting urgency in his mission. As he lands, ready to tackle the next task, the background features complex machinery and glowing panels, immersing the viewer in a high-tech, sci-fi environment.]"
},
{
"from": "gpt",
"value": "Bad. The actor's facial features in the video are generated blurry, and the limbs are deformed. In the middle frames, the actor's limbs are twisted and distorted."
}
] |
seed42_1976
|
videos/HRA_part0/1976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, spotted leopard leaps across a mossy log in a dense, lush forest, its powerful muscles rippling under golden fur flecked with black rosettes. Towering trees with emerald canopies surround the scene, dappled sunlight filtering through the leaves, casting an ethereal glow. The big cat lands gracefully on the forest floor, strewn with ferns and fallen leaves, before bounding away into the undergrowth, demonstrating the apex predator's agility and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's legs have undergone a sudden mutation deformity."
}
] |
seed44_1725
|
videos/HRA_part1/1725.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crisp white shirt and black pants, serves a dingo seated at a table set amidst dense green thickets. The dingo, wearing a red bandana, looks expectantly at the waiter, who holds a platter of food. Nearby, a swimming pool glistens under the sun, its clear blue water contrasting with the lush vegetation surrounding it. The waiter, with a friendly smile, places the dish before the dingo, who eagerly leans forward, creating a surreal yet charming tableau.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2522
|
videos/HRA_part2/2522.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, spotted jaguar leaps powerfully across a shallow stream, its body mid-air, muscles taut and rippling beneath golden fur flecked with black rosettes. The big cat's mouth is open slightly, revealing sharp canines, and its intense gaze is fixed forward. The water shimmers under the jungle canopy, splashing up droplets that freeze in the air around the airborne predator. The scene is captured in high-definition, focusing on the jaguar's dynamic movement and the surrounding lush vegetation, creating a vivid snapshot of the animal's natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3082
|
videos/HRA_part0/3082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery illuminated by soft purple lighting, a distinguished doctor, wearing a crisp white lab coat over a button-down shirt and slacks, meticulously wipes an ancient relic. The artifact, seemingly made of obsidian, is displayed on a sleek, metallic pedestal amidst avant-garde artworks floating in zero gravity. The doctor's focused gaze and careful handling emphasize the significance of the object, while the surrounding art pieces, including abstract sculptures and vibrant paintings, add a touch of cultural richness to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's movements in the video are slightly unsmooth."
}
] |
seed44_1551
|
videos/HRA_part1/1551.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lustrous, cooked lobster is presented on a white plate, its vivid red shell contrasting beautifully against the pristine background. The lobster's body is split open to reveal tender, succulent meat, artfully garnished with fresh herbs and lemon wedges, enhancing the dish's visual appeal. Accompanied by a side of drawn butter and a sprinkle of parsley, the dish exudes elegance and promises a rich, indulgent dining experience, perfect for a gourmet feast. The steam gently rising from the plate adds a touch of warmth and freshness, inviting the viewer to savor every detail of this exquisite culinary creation.]"
},
{
"from": "gpt",
"value": "Normal. The pincers of the lobster in the video are generated abnormally."
}
] |
seed42_2998
|
videos/HRA_part0/2998.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious indoor playroom illuminated by large windows, two young children engage in a playful tug-of-war over a vibrant red toy firetruck. The room is filled with various toys scattered across the wooden floor, adding to the sense of fun and activity. The children, both wearing colorful clothing - one in a blue striped shirt and the other in a pink floral dress - display expressions of determination and joy as they pull on opposite ends of the firetruck, their feet firmly planted on the floor. The background features a wall painted with cheerful, cartoonish animal murals, enhancing the whimsical atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The child's limbs in the video are missing."
}
] |
seed46_1295
|
videos/HRA_part2/1295.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a blue plaid shirt and black pants, sits cross-legged on a wooden floor, surrounded by a variety of eager pets. The room is dimly lit, with a single lamp providing a warm glow. The musician, with a friendly smile, gently strums an acoustic guitar, creating a soothing melody that fills the cozy space. Pets of different sizes and species gather around, their attentive faces showing enjoyment of the music and anticipation of being fed. A fluffy cat perches on the musician's lap, while a small dog sits patiently by a bowl of food, and a parrot watches from its cage. The scene conveys a sense of harmony and love between the musician and the pets, all sharing a special moment together.]"
},
{
"from": "gpt",
"value": "Normal. The musician's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_214
|
videos/HRA_part0/214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young college student, casually dressed in a white T-shirt and blue jeans, diligently paints a room with bright yellow walls, focusing on a corner where two walls meet. The room is filled with natural light from a nearby window, illuminating the student's task. They wear protective goggles and a face mask, ensuring safety while working. The student is surrounded by painting supplies, including a ladder, paint cans, and brushes, indicating a thorough preparation for the project. As the camera pans out, we see the student's friends in similar attire, contributing to the painting effort, fostering a sense of camaraderie and teamwork in transforming the space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_2901
|
videos/HRA_part0/2901.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 small, agile mongoose, with its distinctive reddish-brown fur and sharp eyes, is seen crawling slowly through a dense grassland environment. It moves stealthily, its body hugging the ground, as it searches for prey or navigates its territory. The scene is set under the warm glow of the afternoon sun, casting long shadows and highlighting the mongoose's fur texture against the green backdrop. Its cautious movements and keen senses are evident as it crawls, making it appear both vulnerable and predator in the wild landscape.]"
},
{
"from": "gpt",
"value": "Normal. The mongoose in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_3126
|
videos/HRA_part1/3126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown jacket and beige cap, energetically jumps on a moving walkway inside a bustling airport terminal, his body language conveying enthusiasm and excitement. Around him, the airport's modern architecture and various travelers create a dynamic setting, contrasting with his animated leap. The director's attire includes a brown coat, khaki pants, and a beige hat, while the busy airport environment, complete with passengers, luggage carts, and shops, adds to the scene's vibrancy. Throughout the sequence, the director's joyful leap remains the focal point, encapsulating his spirited personality amidst the airport's lively atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The director's jumping action in the video is not smooth."
}
] |
seed46_3165
|
videos/HRA_part2/3165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative woman, clad in a yellow top and denim jeans, stands before a large canvas in an airy studio filled with natural light. She holds a paintbrush in her right hand, dabbing it into a vivid palette of colors, while her left hand rests on her hip. Her wavy brown hair cascades down her back as she intently focuses on her artwork, surrounded by a scattering of completed paintings and art supplies. The atmosphere is one of tranquility and inspiration, with the unfinished painting on the easel capturing the essence of her artistic process.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2468
|
videos/HRA_part0/2468.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a futuristic silver spacesuit with illuminated details, traverses the rocky, mineral-rich terrain of an asteroid under the faint light of distant stars. Carrying a high-tech pickaxe over his shoulder, he pauses to survey the alien landscape, showcasing determination and resilience in the harsh environment. As he walks, the textured surface of the asteroid and the tools strapped to his suit are clearly visible, emphasizing the challenging conditions of space mining. In the background, the vastness of space and the silhouette of a mining facility or spacecraft provide context to his solitary mission.]"
},
{
"from": "gpt",
"value": "Normal. The hand is somewhat deformed."
}
] |
seed44_1705
|
videos/HRA_part1/1705.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space casino, a distinguished chef, donning a traditional white chef's uniform with black stripes and a black necktie, walks with purpose. He carries a large, covered silver platter, its lid adorned with a golden handle. Behind him, a bustling kitchen reveals chefs in action, preparing exquisite dishes. The casino's opulent decor is visible through a glass partition, featuring patrons enjoying themselves at various gaming tables. The chef's confident stride and the casino's lively atmosphere create a captivating contrast between culinary expertise and the thrill of gambling in outer space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_233
|
videos/HRA_part1/233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, donning a plaid shirt, denim overalls, and a worn baseball cap, stands in a modern kitchen. He methodically unloads a sleek, stainless steel dishwasher, handling each plate and utensil with unexpected gentleness. The contrast between his calloused hands and the shiny, clean dishes highlights the unusual domestic task for someone more accustomed to farm chores. The kitchen is spacious and well-lit, featuring granite countertops and contemporary appliances, offering a glimpse into the farmer's home life beyond the fields.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's hand and arm appear deformed, and the plate in his hand suddenly disappears and undergoes transformation."
}
] |
seed46_265
|
videos/HRA_part2/265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit chaparral landscape, a seasoned farmer wearing a wide-brimmed straw hat, denim overalls, and a plaid shirt is seen joyfully dancing. In the background, a jackal curiously observes from a distance, standing near a weathered wooden fence. The farmer, embodying the spirit of the land, performs lively dance moves, celebrating the beauty of nature around him, with the jackal occasionally mirroring his movements in a playful manner. The chaparral vegetation, characterized by shrubs and small trees, forms a picturesque setting for this unexpected dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's limbs and facial features in the video are deformed, and the jackal is also deformed overall."
}
] |
seed44_1545
|
videos/HRA_part1/1545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray shirt and khaki pants is seen in a whimsical scene, holding a small mouse on a wheel that matches the color of his shirt. The wheel rotates rapidly as the man watches, his gaze fixed on the active rodent. The scene is set against a plain, white backdrop, with the man's casual attire and focused expression contrasting with the unusual sight of the mouse energetically running on the miniature wheel.]"
},
{
"from": "gpt",
"value": "Bad. The mouse's running in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed42_1742
|
videos/HRA_part0/1742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 aquarium filled with clear, blue water, a translucent ghost shrimp, barely visible, floats motionless near the bottom, its delicate legs folded. It then swims upward slowly, revealing its transparent body and the tiny creature inside, before coming to a stop near the surface. The shrimp hovers there, seemingly weightless, before descending again to the sandy bottom, dotted with small stones and pieces of aquatic plants, offering a glimpse into the elusive life of this ethereal crustacean.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1155
|
videos/HRA_part1/1155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse with blonde hair pulled back into a bun sits in a cozy room, knitting a vibrant red scarf with her skilled hands. Dressed in a clean, white uniform, she focuses intently on her craft, surrounded by the warm glow of soft lighting. The scene captures her in various moments, from checking her progress to pausing thoughtfully, always maintaining a serene expression. Her uniform is crisp and professional, contrasting with the homely atmosphere of the room, where a fireplace casts a warm light over her industrious figure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2169
|
videos/HRA_part1/2169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mouse walks along the edge of a weathered wooden table, its tiny feet making delicate movements against the grainy surface. The mouse pauses momentarily, its whiskers twitching as it senses the environment, before continuing its journey. Its round ears and curious demeanor are highlighted as it explores the tabletop landscape, framed by a blurred background that suggests a rustic interior setting. Throughout the scene, the mouse's agile movements and cautious behavior are captured in detail, providing a close-up view of its natural actions.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the mouse's limbs in the video has issues."
}
] |
seed46_2020
|
videos/HRA_part2/2020.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, clad in a black shirt, performs energetically on stage under red lights, passionately singing into a microphone. Simultaneously, he wipes sweat from his forehead with his right hand, revealing a wristwatch. Behind him, a drummer in a black sleeveless shirt plays enthusiastically, and a guitarist in a black shirt strums powerfully. The stage is adorned with jaguar patterns, adding a touch of wild flair to the performance.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2364
|
videos/HRA_part1/2364.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged-looking man with short, dark hair and a trimmed beard focuses intently on repairing a vintage bicycle, his body partially covering the bike's frame. Dressed in a light blue, short-sleeved shirt, khaki pants, and brown work boots, he leans over the bike, which is held upright by a repair stand. His right hand grips a wrench, while his left hand steadies the bike, both hands stained with grease. The scene is set against a backdrop of a cluttered garage filled with various tools and equipment, emphasizing the worker's expertise and dedication to his craft.]"
},
{
"from": "gpt",
"value": "Good. The character's movements in the video are basically normal."
}
] |
seed42_1430
|
videos/HRA_part0/1430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic laboratory filled with advanced scientific equipment, an artist clad in a protective suit and goggles paints a life-sized depiction of a woolly mammoth on a large canvas. The mammoth is portrayed in its natural icy habitat, with the aurora borealis illuminating the sky, symbolizing the mysteries of dark matter. Meanwhile, in the background, a group of dedicated researchers in lab coats analyze data from sophisticated machines designed to explore the enigmatic properties of dark matter. The scene is completed by a large aquarium tank filled with clear water, where a swimmer performs synchronized swimming movements, creating mesmerizing patterns that echo the cosmic dance of dark matter in the universe.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, with distorted arms and legs."
}
] |
seed42_2331
|
videos/HRA_part0/2331.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sky-blue scrubs top and pants, takes a break from her duties to enjoy the outdoors. She is raking a large pile of autumn leaves in a residential backyard, her actions revealing a playful side to her personality. She pauses to look up, smiling at the camera, her brown hair tied back in a practical ponytail. Despite her work clothes, which include a stethoscope hanging around her neck, she tackles the task with enthusiasm, her movements energetic and joyful. The sunny weather and colorful leaves provide a vibrant backdrop for this unexpected scene.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, legs, and the item in their hand are distorted in the video."
}
] |
seed42_2415
|
videos/HRA_part0/2415.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic leopard, exhibiting a rare display of gentleness, is seen affectionately caressing another leopard in a lush, verdant environment. The first leopard, with piercing green eyes and a strikingly patterned coat, leans its head against the second leopard's face in a tender gesture. Both leopards are perched on a thick, sturdy branch, surrounded by dense foliage and dappled sunlight, creating an intimate atmosphere. This unique scene captures the emotional bond between these two wild cats, showcasing the softer side of these powerful predators.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2550
|
videos/HRA_part1/2550.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow vest over a dark jacket and jeans, walks purposefully down a hospital corridor. The hall is lined with evenly spaced white doors and illuminated by overhead lights, casting a warm glow. The man holds a mop bucket in one hand, its handle adorned with a colorful cloth hanging loosely. He moves with determination, his work boots echoing softly on the linoleum floor, creating a sense of routine and responsibility in the clean, institutional environment.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's hands and feet in the video have generation issues."
}
] |
seed44_1561
|
videos/HRA_part1/1561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged astronaut, clad in a sleek silver spacesuit and helmet, leaps into the air against the backdrop of a distant galaxy, stars shimmering in the vast cosmic landscape. The astronaut's pose conveys a sense of weightlessness and freedom as he appears to float in zero gravity, with the vibrant colors of far-off celestial bodies providing a dramatic contrast to his metallic attire. The scene captures the exhilaration and mystery of interstellar exploration, with the astronaut seeming to defy the laws of physics in the boundless expanse of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2162
|
videos/HRA_part1/2162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant, otherworldly setting reminiscent of a space opera, a majestic camel, adorned with ornate, futuristic gear, leaps gracefully over an array of alien flora. The backdrop features a bustling spaceport with neon-lit structures and a variety of extraterrestrial beings. The camel's rider wears a sleek, armored suit with glowing accents, embodying a daring space adventurer. The scene is filled with dynamic energy as the camel bounds through the air, showcasing its agility against the backdrop of a technologically advanced society engaged in a grand performance.]"
},
{
"from": "gpt",
"value": "Bad. The camel and rider's walking in the video is very unsmooth, with uncoordinated movements."
}
] |
seed44_1958
|
videos/HRA_part1/1958.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station habitat, an anthropomorphic chimpanzee, clad in a silver spacesuit and helmet, performs an energetic dance against a backdrop of advanced technology and starlit windows. The chimp's movements are lively and expressive, conveying a sense of joy and freedom in the zero-gravity environment. Accompanied by upbeat music, the chimpanzee's dance includes playful jumps and twirls, highlighting its adaptability and charisma in the unique setting of a space station, where screens display vibrant colors and the vastness of outer space provides a stunning contrast to the lively performance.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed44_3128
|
videos/HRA_part1/3128.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 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 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": "Bad. The officer's face and hands are distorted in the video."
}
] |
seed42_3036
|
videos/HRA_part0/3036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage boy wearing a red jacket and khaki pants is sprinting across a grassy field, his gaze fixed ahead with determination. As he runs, a small rabbit enters the frame from the bottom right corner, bounding alongside him. The student acknowledges the rabbit with a brief glance, but both continue their run, the student maintaining his focus and the rabbit keeping pace, against the backdrop of a clear blue sky and distant green hills.]"
},
{
"from": "gpt",
"value": "Bad. The boy and the rabbit running in the video are very unsmooth, and the movements are uncoordinated."
}
] |
seed42_2714
|
videos/HRA_part0/2714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic classroom aboard a space station, a compassionate teacher, dressed in a blue jumpsuit with patches and pins adorning her chest, gently caresses the head of a curious alien student. The student, with large, expressive eyes and a small, round body, sits attentively at a desk cluttered with advanced technology and educational tools. The room is filled with natural light from a large window showing a stunning view of Earth and the vast cosmos beyond, emphasizing the peaceful diplomatic mission of education among the stars.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2131
|
videos/HRA_part2/2131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a white lab coat and safety goggles, carefully crawls across a rugged, volcanic landscape, examining a unique rock formation. Surrounded by steam vents and volcanic rocks, the doctor, complete with a backpack and protective gear, crawls through a narrow crevice, demonstrating determination and focus in the harsh environment. The scene highlights the doctor's adventurous spirit and scientific curiosity, as they navigate the challenging terrain, crawling under low-hanging rock formations, all set against the dramatic backdrop of an active volcano.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed44_1098
|
videos/HRA_part1/1098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a futuristic, metallic silver jumpsuit performs an intricate dance routine inside a mammoth spaceship, illuminated by pulsating neon lights. The ship suddenly initiates a hyperspace jump, stars warping into elongated streaks of light in the background, adding a surreal touch to the scene. Despite the gravity fluctuations, the woman continues to dance gracefully, her movements synchronized with the electronic beats emanating from the ship's audio system. Her face, a mix of determination and joy, reflects the vibrant colors of the spaceship's interior, creating a mesmerizing spectacle as she dances amidst the cosmic chaos.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2482
|
videos/HRA_part1/2482.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-groomed male doctor, wearing a white lab coat over a button-down shirt and khaki pants, is kneeling on a checkered floor in a modern bathroom. He focuses intently on unclogging a stainless steel kitchen sink drain, using a professional plumber's tool. The bathroom features contemporary fixtures, including a glass shower stall and a minimalist vanity. As he works, the doctor's sleeves are rolled up, revealing a watch and bracelet, while his wedding band glints under the bright overhead lights. Throughout the process, he maintains a serious, determined expression, highlighting his commitment to resolving the plumbing issue.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's hand and arm have become deformed and disfigured."
}
] |
seed46_1924
|
videos/HRA_part2/1924.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic room filled with advanced technology and screens displaying alien landscapes, a renowned director, dressed in a black turtleneck and jeans, sits in a swivel chair, intently observing a large screen. Suddenly, an otherworldly creature, resembling a cross between a mouse and an alien, emerges from the shadows. With a look of wonder and curiosity, the director gently extends a hand, initiating a tender caress of the creature's soft fur, highlighting a peaceful and unexpected interspecies connection. The scene is framed by high-definition visuals and enhanced by the ambient glow of the tech-filled environment, emphasizing the director's calm and respectful interaction with the unique being.]"
},
{
"from": "gpt",
"value": "Normal. The director's movements while touching the mysterious creature in the video are mostly normal but somewhat uncoordinated."
}
] |
seed42_1588
|
videos/HRA_part0/1588.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savannah, two zebras engage in a tender moment, their striped bodies gently touching as they caress each other. One zebra, with its mane flowing in the breeze, nuzzles the face of another, their bond evident in the softness of their interaction. The scene is framed by distant acacia trees and a clear blue sky, emphasizing the intimacy shared between these majestic creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The zebra appears deformed."
}
] |
seed42_193
|
videos/HRA_part0/193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, donning a crisp white shirt, black vest, and tie, is seen in an upscale restaurant, standing on a chair to check a smoke detector. The room is modern and stylish, with wooden floors, a white ceiling, and large windows. The waiter, displaying a conscientious attitude towards safety, carefully inspects the device. The scene conveys a sense of professionalism and attention to detail, as the waiter ensures the restaurant is equipped with functional safety equipment. The establishment is empty except for the waiter, emphasizing the routine nature of the task. The waiter's attire and the restaurant's decor suggest a high-end dining environment, where safety measures are taken seriously.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3054
|
videos/HRA_part0/3054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a black beret, glasses, and a striped shirt, stands in a dimly lit studio with paintings in the background. He is engaged in an unexpected task, unclogging a drain, using a plunger on a white ceramic sink, with the focus on his expressive face and the effort exerted in this mundane activity. The contrast between his creative attire and the ordinary plumbing task creates a compelling narrative. Moments later, he pauses, revealing a look of determination as he continues his efforts to clear the clogged drain, the camera capturing his every detail in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The plunger in the character's hand is deformed."
}
] |
seed42_1497
|
videos/HRA_part0/1497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged male student, wearing a grey jacket and blue jeans, is crawling along a grassy path on a university campus, surrounded by trees and foliage indicative of early autumn. The scene opens with him crawling under a wooden park bench, suggesting playful or unusual behavior. Next, he crawls beneath the low-hanging branches of a tree, highlighting his determination or whimsy. Then, he crawls across a stone walkway, the textured stones providing a tactile contrast to the grass. Finally, he crawls through a tunnel formed by intersecting tree branches, the dappled sunlight creating a dynamic interplay of light and shadow on his form.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2111
|
videos/HRA_part2/2111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young siblings, a boy and a girl, both wearing casual clothes and with distinct hairstyles, are seen in a modern kitchen with wooden floors and white cabinets. The boy, wearing a blue striped shirt and brown pants, reaches into a large, open dishwasher to unload plates, while the girl, in a pink dress and white socks, stands on tiptoe to put glasses away in a high cabinet. The kitchen features a large window with a view of greenery outside, adding a splash of natural light to the scene. The siblings work together, the boy passing items to the girl, who carefully places them in their respective spots, showcasing their teamwork and responsibility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2810
|
videos/HRA_part1/2810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a black turtleneck sweater and khaki pants, walks through a sterile, white space medical facility, illuminated by soft, ambient lighting. He carries a notebook in his right hand, occasionally jotting down notes as he observes various medical procedures taking place in the background. The facility is equipped with futuristic medical equipment, including robotic surgical arms and holographic diagnostic displays, which are visible through glass walls. The writer stops at a large window overlooking a distant planet, offering a glimpse into the vastness of space, providing inspiration for his writing. Throughout the video, the focus remains on the writer's journey through the space station, capturing his curiosity and engagement with the advanced medical technology surrounding him.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1673
|
videos/HRA_part2/1673.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 imagined scene, a majestic African lion, distinguished by its thick mane and muscular build, runs across a futuristic landscape where solar sails, vast and gleaming, catch the sunlight high above like enormous kites adrift in the sky. The lion's powerful strides and focused gaze contrast beautifully with the serene, almost surreal sight of the solar sails, which seem to float effortlessly in the still air, their surfaces shimmering with reflected light. This unlikely juxtaposition of nature and technology creates a striking and memorable visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The lion in the video has a twisted body, twisted paws, twisted face, and twisted legs."
}
] |
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 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 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": "Bad. The generation of the mouse's capture in the video is missing, with the body and head generated in a distorted manner."
}
] |
seed42_1847
|
videos/HRA_part0/1847.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a blue shirt and khaki pants, leaps into the air with arms outstretched against the vast desert landscape, showcasing his adventurous spirit. Moments later, he is captured in mid-jump, his silhouette framed by the golden hues of the dunes and the clear blue sky. Then, he lands on the sandy terrain, his posture reflecting a sense of accomplishment, with the desert's serene beauty serving as a dramatic backdrop. Finally, he jumps again, this time with a wide smile, embodying the joy of exploring the wilderness, all set against the stunning desert scenery.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has incomplete and deformed limbs and face, and his body is also deformed."
}
] |
seed44_1290
|
videos/HRA_part1/1290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man wearing a brown leather jacket and a tan hat sits on a large rock in the middle of a vast, grassy plain, writing intently in a small notebook. In the background, a majestic bison is seen grazing peacefully on the lush vegetation. Suddenly, the man lowers his book, revealing a look of awe and inspiration as he watches the bison. He then resumes writing, his posture reflecting deep concentration. The scene shifts to show the bison lying down, seemingly resting, as the man continues to write, now with a sense of urgency, capturing the essence of his experience in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are not smooth and coordinated."
}
] |
seed44_1607
|
videos/HRA_part1/1607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, open field under a clear blue sky, two young children, a boy and a girl, both wearing vibrant yellow raincoats, wide-brimmed hats, and boots, are seen walking together. They carry a large, reflective solar sail, its metallic surface shimmering in the sunlight. The sail, supported by a wooden frame they hold, catches the wind as they walk, propelling them forward playfully across the grassy landscape. Their joyful expressions and the sail's gentle movements create a whimsical scene, blending elements of childhood wonder with futuristic technology.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2132
|
videos/HRA_part0/2132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hummingbird, with iridescent green feathers and a forked tail, hovers near a red feeder, its wings a blur of motion against a clear blue sky. The bird's tiny feet dangle beneath it as it feeds, and its long, thin beak dips into the feeder's port. Suddenly, it takes flight, its wings creating an audible hum, and lands on a branch, where it preens its feathers with its curved bill. Throughout, the hummingbird's rapid wing movements and vibrant plumage are showcased against the serene backdrop of nature.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's wings and claws were generated incorrectly, and the eyes were not generated at all."
}
] |
seed44_2357
|
videos/HRA_part1/2357.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a 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 body of the wild rabbit has undergone a deformity mutation."
}
] |
seed44_2585
|
videos/HRA_part1/2585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with a full beard, wearing a straw hat and a checkered shirt, stands waist-deep in a clear blue pond, smiling at the camera. Beside him, a dingo with a red coat and a black-tipped tail swims energetically, its head held high above the water. The farmer's right arm is raised, showing a relaxed and joyful posture, while the dingo continues to swim, its eyes fixed on the farmer. The scene is set against a backdrop of lush greenery and tall trees, creating a serene and picturesque environment.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand appears deformed. The Australian wild dog's tail appears deformed."
}
] |
seed42_1844
|
videos/HRA_part0/1844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a friendly-looking cashier, wearing a red apron with a name tag, works behind a counter at an airport gift shop. Unexpectedly, a small, playful ferret emerges from the pocket of the cashier's apron, peeking its head out curiously. The background features a bustling airport terminal with passengers and luggage, emphasizing the unusual combination of elements. Moments later, the focus shifts to a clear swimming pool, where the same cashier, now in swimwear, happily swims with the ferret floating nearby on a small inflatable raft, both enjoying a break from the busy airport environment.]"
},
{
"from": "gpt",
"value": "Bad. The video does not feature any scenes of the cashier and the ferret enjoying a break in the pool as mentioned in the caption."
}
] |
seed42_1551
|
videos/HRA_part0/1551.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lustrous, cooked lobster is presented on a white plate, its vivid red shell contrasting beautifully against the pristine background. The lobster's body is split open to reveal tender, succulent meat, artfully garnished with fresh herbs and lemon wedges, enhancing the dish's visual appeal. Accompanied by a side of drawn butter and a sprinkle of parsley, the dish exudes elegance and promises a rich, indulgent dining experience, perfect for a gourmet feast. The steam gently rising from the plate adds a touch of warmth and freshness, inviting the viewer to savor every detail of this exquisite culinary creation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_189
|
videos/HRA_part1/189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a gray hoodie and blue jeans, sits cross-legged on a hardwood floor in a room with large windows, a desk with a laptop, and a bookshelf in the background. A curious cat crawls onto the student's lap, interrupting their study session. The student gently strokes the cat, which is adorned with a red collar, as it snuggles into their lap. The room is filled with natural light from the windows, creating a warm and cozy atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the student and the cat in the video are very unsmooth and uncoordinated."
}
] |
seed46_1336
|
videos/HRA_part2/1336.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman, balding with a neatly trimmed beard, sits in a cozy library filled with bookshelves, wearing a brown jacket and a yellow shirt. He speaks animatedly about his writing process, gesturing expressively with his hands. Behind him, a large window frames a view of a lush garden, providing a picturesque backdrop. The room is illuminated by warm lighting, creating an inviting atmosphere that enhances the intimacy of the conversation. As he talks, his eyes sparkle with passion, conveying his deep connection to the art of storytelling.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1752
|
videos/HRA_part0/1752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic industrial setting, a mature man with salt-and-pepper hair and a full beard, wearing a dark jacket, gray shirt, and black pants, gently touches and inspects a large turbine blade from a power plant. The blade is massive, with a metallic sheen, positioned horizontally against a backdrop of complex machinery and pipes, indicative of a hydroelectric or nuclear power facility. The man's tender gesture contrasts with the harsh environment, highlighting a personal connection or professional pride in the technology.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2825
|
videos/HRA_part2/2825.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red swimming cap and goggles is seen underwater, swimming in a clear, blue pool. Above the water, a majestic lion stands on the edge of the pool, observing the swimmer. The scene is set against the backdrop of quaint towns in the distance, their rooftops visible above the trees, creating a surreal and unexpected juxtaposition of elements. The engineer's swimming motion is smooth and deliberate, contrasting with the stillness of the lion, which adds to the dreamlike quality of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_325
|
videos/HRA_part1/325.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, distinguished by his gray beard and wearing a dark jacket, blue shirt, and khaki pants, interacts closely with a chimpanzee. The chimpanzee, positioned on a wooden structure in a spacious indoor setting, leaps energetically into the air, demonstrating its agility. The director observes intently, possibly guiding the action or assessing the performance, while standing on the same platform as the chimpanzee, which is enclosed within the large room. The scene captures the unique collaboration between human and animal in the context of filmmaking.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3151
|
videos/HRA_part2/3151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a trimmed beard, wearing a red flannel shirt, blue jeans, and a brown hat, stands in a barn filled with hay bales. He sneezes loudly, holding a pitchfork, as dust particles and shafts of sunlight fill the air around him. The barn is rustic, with wooden beams and a dirt floor, and the farmer's sneeze echoes throughout the space. Afterward, he wipes his nose with a red handkerchief, the barn's interior still visible behind him, before continuing his work with the hay.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate pitchforks."
}
] |
seed42_1471
|
videos/HRA_part0/1471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the warm glow of sunrise, an antelope stands gracefully in the midst of a subtropical desert, its coat shimmering in hues of gold and brown, perfectly camouflaged against the sandy terrain. It is being gently caressed by the soft, early morning breeze, stirring the fine hairs on its body. The landscape is dotted with sparse vegetation and rocky outcrops, emphasizing the animal's resilience in this arid environment. The antelope's alert stance and curious gaze reflect its awareness of the surroundings, creating a serene yet dynamic scene in the vast, untouched wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2056
|
videos/HRA_part1/2056.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male cashier, sporting a clean-shaven face and a neatly tucked-in red shirt, diligently organizes items on a grocery store shelf. The store is devoid of customers, allowing him to focus on restocking with precision. He carefully places a can of beans onto the shelf, surrounded by other neatly arranged cans. His hands, free of gloves, handle each item with care, ensuring they are perfectly aligned. The well-lit supermarket aisle provides a clear view of the organized products, highlighting the cashier's attention to detail in his task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3085
|
videos/HRA_part2/3085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful swan floats on a serene lake, its elegant white feathers glistening under the golden afternoon sun. The water reflects the bird and the lush green trees that surround the peaceful scene, creating a harmonious blend of nature's beauty. The swan's long, curved neck forms a gentle S-shape as it gently propels itself through the crystal-clear water, leaving a series of delicate ripples in its wake. The tranquility of the moment is punctuated by the occasional sound of the swan's wings softly brushing against the surface of the lake.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1337
|
videos/HRA_part1/1337.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, donning a navy blue polo shirt, beige shorts, and brown shoes, is organizing a cluttered garage filled with various items. Initially, he stands thoughtfully amidst the chaos, surrounded by a bike, a toolbox, and gardening equipment. He then proceeds to sort through a pile of objects, showcasing his methodical approach. Next, he is depicted lifting a heavy object, demonstrating his physical strength. Finally, he is shown proudly admiring his neatly organized garage, with shelves neatly arranged and tools hanging orderly on the walls, a testament to his hard work and attention to detail.]"
},
{
"from": "gpt",
"value": "Bad. The hands appear deformed, and the objects in front are flying."
}
] |
seed44_1898
|
videos/HRA_part1/1898.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a straw hat and blue overalls, is seen playfully splashing water at a curious jackal on the banks of a serene lake during golden hour. The farmer then dives into the water, swimming with ease, while the jackal cautiously wades in, its ears perked up and attentive. They engage in a lighthearted game, the farmer swimming and the jackal paddling near the shore, both enjoying the cool waters under the warm, golden glow of the setting sun.]"
},
{
"from": "gpt",
"value": "Bad. The hyena's head and the farmer's face generation in the video have issues."
}
] |
seed44_2219
|
videos/HRA_part1/2219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 teacher, wearing a yellow shirt with a black apron, stands in a modern kitchen classroom filled with stainless steel appliances, teaching a group of attentive students how to stir-fry vegetables. She masterfully tosses vibrant bell peppers, carrots, and broccoli in a large wok over high heat, creating an engaging lesson on cooking techniques. The students, clad in matching aprons, watch intently as she demonstrates the art of stir-frying, her actions punctuated by the sizzling sounds of the hot oil and vegetables. Throughout the scene, the teacher's enthusiasm and expertise shine as she shares her culinary knowledge with her eager pupils.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the teacher in the video are not continuous and there are abrupt changes."
}
] |
seed42_1181
|
videos/HRA_part0/1181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, showcasing its distinctive golden fur patterned with black rosettes, swims through a clear, sun-dappled body of water, its muscular body cutting through the liquid with surprising grace and strength. Its piercing eyes remain focused, and its ears are flattened against its head as it propels itself forward with powerful strokes, defying the typical terrestrial nature of its kind in this aquatic setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 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, 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. Basically correct."
}
] |
seed44_1467
|
videos/HRA_part1/1467.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 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 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": "Good. No obvious problems."
}
] |
seed46_1174
|
videos/HRA_part2/1174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dark green shirt and khaki pants, is seen wiping a wet floor with a mop, leaving behind a clean, glistening surface. Beside him, a small, fluffy white dog, possibly a Bichon Frise, looks up with curious brown eyes. The janitor pauses, resting the mop against a wall covered with inspirational posters and a fire extinguisher, before bending down to interact with the dog, who eagerly responds with a wagging tail and playful energy, creating a heartwarming moment in an otherwise mundane setting.]"
},
{
"from": "gpt",
"value": "Bad. The character only generated one arm, and the leg movement was uncoordinated. Finally, the character suddenly shrank, and the hand also became deformed."
}
] |
seed42_2484
|
videos/HRA_part0/2484.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars through a dramatic sky filled with billowing clouds, its expansive wingspan casting a shadow on the turbulent sea far below. The bird's plumage is a stunning contrast of pure white underparts and sleek, dark upperwings, accentuated by the golden hue of the setting sun. Its sharp, hooked bill and piercing eyes are focused ahead, embodying the spirit of freedom and grace as it navigates the vast, open ocean with effortless elegance. The scene is framed by the rugged coastline in the distance, highlighting the albatross's natural habitat and its role as a symbol of resilience and adaptability in the face of nature's challenges.]"
},
{
"from": "gpt",
"value": "Normal. The head of the albatross in the video has generation issues, the body is deformed, the wings are oversized and incorrectly positioned, and the claws did not generate."
}
] |
seed44_1770
|
videos/HRA_part1/1770.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistically dressed woman, adorned with face paint resembling a buffalo, performs an interpretive dance against a vibrant, textured backdrop reminiscent of theater curtains. Her ensemble includes a brown top, khaki pants, and brown shoes, complemented by the buffalo-inspired face art. She gracefully moves through a series of dance poses, her body language conveying emotion and storytelling. Behind her, the theater curtain texture adds depth and drama to the scene, encapsulating the essence of performance art.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_161
|
videos/HRA_part2/161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, cosmic library filled with floating bookshelves and galaxies in the background, a majestic lion, adorned with a golden collar and a serious expression, is seen wiping the dust off ancient books with a delicate paw. The shelves are stocked with books of all sizes, and the lion moves between them, engaged in the meticulous task of cleaning. Surrounded by the grandeur of space and knowledge, the lion continues its duty, highlighting the serene yet awe-inspiring setting.]"
},
{
"from": "gpt",
"value": "Normal. The lion's hand in the video has modeling penetration, the nose is generated unreasonably, and the fingers are not generated."
}
] |
seed44_2763
|
videos/HRA_part1/2763.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious brown monkey with a fluffy tail is seen swimming in a clear blue pool, its limbs energetically paddling through the water. It occasionally glances at the camera with a mischievous look, as if enjoying a playful moment. The monkey's facial features are expressive, conveying a sense of fun and adventure. Its body language suggests a relaxed and confident demeanor as it navigates the aquatic environment, demonstrating an unusual sight of a primate enjoying a swim.]"
},
{
"from": "gpt",
"value": "Normal. The monkey's swimming in the video is basically normal, but there are slight movements that are not quite coordinated."
}
] |
seed44_1135
|
videos/HRA_part1/1135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a utility belt, leaps into the air against a backdrop of cosmic dust swirling in the night sky, creating a surreal and dramatic scene. The officer's silhouette is highlighted by the celestial phenomenon, with the dust storm's ethereal glow illuminating the surroundings. The jump, captured mid-air, adds a dynamic element to the composition, juxtaposing the grounded authority figure with the otherworldly cosmic event.]"
},
{
"from": "gpt",
"value": "Bad. The person's fingers are deformed, and one foot is also deformed."
}
] |
seed46_1147
|
videos/HRA_part2/1147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A curious brown monkey with a tuft of hair on its head sits upright on a lush green plant, holding a white napkin in its right hand. It begins wiping its mouth gently, revealing a small smile and a twinkle in its eye. As it continues, the monkey looks directly at the camera, showcasing its playful nature. The scene is set against a vibrant jungle backdrop, with sunlight filtering through the dense foliage, highlighting the monkey's actions and its environment.]"
},
{
"from": "gpt",
"value": "Bad. The monkey's hand appears deformed and mutated, and at one point, its head also becomes deformed."
}
] |
seed44_1904
|
videos/HRA_part1/1904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed man in a white shirt and dark pants walks through a lush, green meadow dotted with vibrant wildflowers under a bright, clear blue sky. He strides purposefully, his hands clasped behind his back, exuding a sense of peace and connection with nature. The tall grass sways gently in the breeze around him, and in the distance, a range of rolling hills provides a picturesque backdrop, enhancing the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_2490
|
videos/HRA_part1/2490.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, covered in dark fur with lighter features around its eyes and mouth, runs across a grassy terrain under a vibrant blue sky. The chimp's movement is powerful and agile, with a hunched posture typical of its species. Its face, marked with distinctive wrinkles and a noseless structure, conveys intense focus as it sprints. In another moment, the chimpanzee is shown from a side view, highlighting its muscular build and the gracefulness of its stride, set against the backdrop of a lush, green environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1049
|
videos/HRA_part0/1049.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his stethoscope around his neck and wearing a white lab coat over a button-down shirt and khaki pants, is standing on a chair in a modern office space. He attentively checks a smoke detector mounted on the ceiling, demonstrating unexpected handyman skills. The room is well-lit and features a large window, a desk with a computer, and various medical posters on the walls, creating a professional yet casual atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has deformed hands and uncoordinated movements."
}
] |
seed42_1081
|
videos/HRA_part0/1081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 orchard setting, lush greenery surrounds a badger as it curiously explores its environment. The badger, with its distinctive black and white striped face, sniffs the air, then gently caresses the bark of an old apple tree with its paw. The camera captures the badger's actions in detail, focusing on the texture of the tree bark and the animal's fur. The scene is peaceful, with the soft sounds of nature providing a soothing soundtrack to the badger's gentle interaction with its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The badger's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2024
|
videos/HRA_part1/2024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, bespectacled female student sits cross-legged on a clean, white surface, diligently hemming a pair of black pants with a focused expression. She wears a grey cardigan over a white collared shirt and blue jeans, her attire casual yet neat. The environment is bright and minimalistic, with ample natural light illuminating her task. Tools of her activity, such as scissors, thread, and a needle, are neatly arranged within reach, highlighting her attention to detail and organization. The scene captures her absorbed in the sewing process, her hands skillfully manipulating the fabric, demonstrating a blend of practical skill and academic studiousness.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, but there is some lack of coordination."
}
] |
seed42_2674
|
videos/HRA_part0/2674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, dressed in a green shirt, gray jacket, and khaki pants, walks through the bustling streets of a metropolis, passing by a glass office building with a reflection of the surroundings. Moments later, he continues his journey, navigating the urban landscape near a construction site with yellow barriers. He then crosses a busy street, dodging between pedestrians, cars, and a street sweeper. Finally, he reaches a subway station entrance, marked by a red canopy and illuminated signage, ready to descend into the underground network of the city.]"
},
{
"from": "gpt",
"value": "Bad. The man's body and limbs are missing in the video, the face is generated blurily, and the background is distorted."
}
] |
seed46_1875
|
videos/HRA_part2/1875.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, dressed in a white shirt and denim overalls, stands on the edge of a serene pond, watching attentively as a rabbit swims gracefully through the clear water. The rabbit, defying expectations, moves with surprising agility, its brown fur glistening beneath the golden afternoon sunlight. The farmer, hat in hand, looks on with a mix of surprise and delight, the rolling green fields and distant barn providing a quintessential rural backdrop to this unexpected scene.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's movements in the video are very unsmooth, and its limbs are not coordinated."
}
] |
seed42_1320
|
videos/HRA_part0/1320.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic store, a cashier with a holographic display projects a swirling black hole singularity above a checkout counter, where items are being scanned and bagged. The cashier, wearing a uniform with high-tech accents, interacts with the singularity using gestures, demonstrating advanced technology integration. Nearby, a cleaning robot with a compact design moves efficiently, wiping surfaces with precision and leaving everything spotless. The cashier's movements are fluid and practiced, showing expertise in handling the cosmic phenomenon, while the robot's efficiency underscores the seamless blend of everyday tasks and extraordinary phenomena in this setting.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's movements are not smooth."
}
] |
seed46_1658
|
videos/HRA_part2/1658.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, 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 in the video has a twisted body, face, arms, legs, and hands."
}
] |
seed42_1189
|
videos/HRA_part0/1189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit room, two young girls sit on a large, colorful rug, engrossed in crocheting a vibrant patchwork blanket. One girl, with short brown hair, wears a yellow T-shirt and blue jeans, focusing intently on her work. Beside her, a girl with long blonde hair, dressed in a pink dress, stitches away with determination. The room is filled with an array of yarn balls in various colors, scattered around them, and a white wooden table stands nearby, holding a cup of crayons and a half-finished coloring book, hinting at other creative activities. The atmosphere is warm and nurturing, with the girls' concentration and the colorful surroundings creating a scene of creativity and companionship.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1878
|
videos/HRA_part0/1878.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic man, possibly named Ray, stands in a sunlit room, wearing a stylish gray suit, white shirt, and patterned tie. He is seen from different angles, first with his back to the window, then with his profile illuminated by the sunlight, and finally facing forward, his confident expression captured in high definition. Throughout the sequence, he maintains a calm demeanor, his attire and the interplay of light and shadow creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1379
|
videos/HRA_part0/1379.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned chef, donning a traditional white chef's uniform with a checkered bandana, performs a dynamic pizza toss in a bustling pizzeria kitchen. The dough stretches gracefully as it rotates in mid-air, illuminated by the warm glow of overhead lights. The chef's confident expression and practiced movements highlight his expertise, while the lively atmosphere of the kitchen, filled with the sounds of sizzling pans and cheerful chatter, adds to the vibrant scene. In the background, a row of wood-fired ovens and a team of chefs busily preparing various dishes complete the authentic pizzeria setting.]"
},
{
"from": "gpt",
"value": "Normal. The chef's pizza tossing motion in the video is not fluid, there is a sudden change."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.