video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_3084
|
videos/HRA_part2/3084.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, wearing a traditional white chef's uniform and black pants, stands outdoors in a garden, holding a shovel. He is surrounded by various plants, including leafy greens, carrots, and herbs like rosemary, thyme, and sage. The chef has short brown hair and a neatly trimmed beard, and he is digging into the rich soil with determination, perhaps searching for fresh ingredients for his culinary creations. The scene is set against a backdrop of wooden crates and greenery, with a hint of sunlight filtering through the trees, casting dappled shadows on the chef and his gardening endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1631
|
videos/HRA_part2/1631.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, wearing a vibrant yellow dress and a wide-brimmed sun hat, dances gracefully in the midst of a vast scrubland. The landscape is dotted with low-lying bushes and sparse trees, stretching far into the horizon under a clear blue sky. Her joyful movements contrast beautifully with the stillness of the arid environment, creating a captivating scene where education meets nature's tranquility. The teacher's animated gestures and warm smile convey a sense of freedom and connection to the rugged yet serene surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's arm is deformed, and there is also a deformity in the leg. The face is distorted."
}
] |
seed42_1095
|
videos/HRA_part0/1095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully through a clear blue sky, its sleek silhouette framed against the horizon. It dives sharply, wings tight to its body, chasing an unseen prey across the vast expanse. Its sharp eyes, focused and intense, scan the terrain below for any hint of movement. The bird then lands on a branch, its feathers ruffled by the wind, revealing a striking pattern of brown and white. It sits still, perched regally, surveying its domain with a fierce gaze, a true ruler of the skies.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1232
|
videos/HRA_part2/1232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed doctor, wearing a suit and tie, spectacles, and a stethoscope around his neck, playfully floats on a yellow inflatable raft in a clear blue swimming pool. In the background, a mammoth, standing at the edge of the pool, looks on curiously, its massive body shaded by the trees overhead. The doctor's attire remains perfectly neat despite the water, and the mammoth's presence adds an element of surrealism to the otherwise ordinary setting of a backyard pool surrounded by lush greenery.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1514
|
videos/HRA_part2/1514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, windswept grassland under a partly cloudy sky, a janitor wearing a yellow vest, blue jeans, and a white shirt is seen wiping a transparent, rectangular window that floats in front of him. The serene landscape stretches to the horizon, dotted with distant trees, while the janitor diligently cleans the window with a cloth, revealing the pristine clarity of the glass. The peaceful scene is punctuated by the gentle sway of the tall grass and the solitude of the janitor's task, emphasizing the unexpected context of maintenance in the midst of nature.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth, and the upper body actions are uncoordinated."
}
] |
seed44_2352
|
videos/HRA_part1/2352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, lush green savanna under a bright, sunny sky, a majestic Bengal tiger runs swiftly across the open grassland, its powerful muscles rippling beneath its vibrant orange coat, marked with distinctive black stripes. The tiger's piercing yellow eyes are focused ahead, conveying determination and grace in motion. The scene is framed by distant gallery-like structures, housing various wildlife exhibits, which add a unique architectural element to the natural setting. The tiger's fluid movements and the contrast between the untamed wilderness and the man-made galleries create a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The Bengal tiger's running in the video is not smooth, and the movements are uncoordinated."
}
] |
seed42_1639
|
videos/HRA_part0/1639.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with curly brown hair pulled into a bun, wearing a gray T-shirt and jeans, sits on a wooden chair in a spacious studio filled with natural light. She is engrossed in painting a large canvas with vibrant colors using a palette knife, surrounded by various art supplies like brushes, paints, and rags. The room is decorated with other colorful paintings, potted plants, and a large window letting in ample sunlight, creating a warm and inspiring atmosphere. The woman's focused expression and the splashes of paint on her clothes and hands highlight her passion and dedication to her craft.]"
},
{
"from": "gpt",
"value": "Normal. The hands of the character in the video have issues."
}
] |
seed44_1493
|
videos/HRA_part1/1493.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a vibrant red swim cap and goggles, is seen playfully interacting with a curious fox at the edge of a serene, crystal-clear pool. The scene opens with the student, wearing a blue swimsuit, diving into the water with a graceful splash, while the fox watches attentively from the side. As the student swims, the fox paces alongside the pool, its interest piqued by the water. Later, the student emerges from the pool, shaking droplets from their swim cap, and reaches out a hand to the fox, which responds with a playful nuzzle, highlighting an unusual yet heartwarming bond between human and wild animal. Throughout the scene, the lush greenery surrounding the pool provides a peaceful backdrop, contrasting with the vivid red of the swim cap and the rich orange tones of the fox's fur.]"
},
{
"from": "gpt",
"value": "Bad. The fox's head and paws, as well as the student's head and hands, were generated incorrectly."
}
] |
seed42_3119
|
videos/HRA_part0/3119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid scene, two smiling children, a boy, and a girl, wearing colorful clothes, gently caress a calm camel in a lush, subtropical wet forest. The dense vegetation, including large-leafed plants and towering trees, provides a striking contrast to the unexpected presence of the camel. The boy, dressed in a blue shirt and khaki shorts, reaches out to touch the camel's nose, while the girl, in a yellow dress, strokes its side, both displaying expressions of delight and wonder. The camel, adorned with a red and gold blanket, stands placidly among the lush greenery, its presence a captivating anomaly within the rich, biodiverse ecosystem of the forest.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the boy petting the camel, the actions are basically normal but there is some lack of coordination."
}
] |
seed46_2058
|
videos/HRA_part2/2058.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fusion of scenes, a waiter in a crisp white shirt and black trousers serves a golden, perfectly roasted chicken on a rustic wooden table set amidst the lush greenery of a temperate rainforest. Moments later, the waiter, now donning a vibrant, traditional costume, gracefully dances among the towering trees, his movements harmonious with the serene environment. The chicken, now artfully presented on a platter, sits center stage as the waiter performs a captivating dance, his attire reflecting the rich cultural heritage associated with temperate rainforests, all under the canopy of majestic, moss-covered trees.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the waiter wearing black pants."
}
] |
seed42_2922
|
videos/HRA_part0/2922.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a sea urchin reveals its intricate, spiny exterior, showcasing a variety of colors including green, purple, and brown. The spherical creature sits atop a rocky reef, surrounded by a vibrant marine environment teeming with life. Sunlight filters through the water, casting a warm glow on the sea urchin's textured surface, highlighting its natural beauty and resilience in the underwater world. Against the backdrop of the reef, the sea urchin appears both delicate and formidable, a testament to the diversity of oceanic fauna.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1901
|
videos/HRA_part0/1901.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged teacher, wearing rectangular glasses and a blue button-down shirt with a maroon sweater, sits at a desk in a classroom filled with wooden desks and chairs. She leans over to replace the batteries in a digital timer used for classroom activities, demonstrating resourcefulness and attention to detail. The room is decorated with a whiteboard covered in colorful marker scribbles and motivational posters, adding a vibrant touch to the educational environment. The teacher's focused expression and the act of replacing the batteries in the timer, which is placed next to a stack of papers, highlight her commitment to ensuring the smooth operation of classroom tools.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's actions to replace the battery of the sub-timer in the video are not very smooth and coordinated."
}
] |
seed42_1216
|
videos/HRA_part0/1216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal and imaginative scene, a compassionate nurse, clad in a crisp white uniform, tends to a gentle rhinoceros, who is swimming effortlessly in a vast, crystal-clear pool. Surrounding them, a series of industrial factories loom in the distance, their smoky chimneys juxtaposing the serenity of the water. The nurse's caring hands support the rhino's underwater navigation, creating a harmonious bond between human and animal amidst an unlikely urban landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1873
|
videos/HRA_part0/1873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape dominated by skyscrapers, a young female cashier, dressed in a black apron over a white shirt and black pants, stands behind a checkout counter in a modern, glass-walled convenience store. She gently caresses the edge of the counter with her right hand, her eyes softly closed, as if cherishing a moment of peace amidst the urban rush. The city's towering buildings loom outside the large windows behind her, contrasting with her intimate gesture.]"
},
{
"from": "gpt",
"value": "Normal. The cashier in the video closes her eyes and touches the counter with her hands, which is basically normal."
}
] |
seed46_2018
|
videos/HRA_part2/2018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a leopard print scarf, sits in a dimly lit room, engaged in caressing a small, furry creature. Behind her, a screen displays complex diagrams related to quantum entanglement experiments, adding a layer of intrigue. Her attire, which includes the eye-catching leopard print accessory, contrasts with the scientific theme of the scene. The focus is on her gentle interaction with the creature, while the backdrop hints at her intellectual pursuits, creating a compelling juxtaposition between the personal and professional aspects of her life.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand appears deformed and mutated, and the creature in her hand also undergoes a deformed mutation."
}
] |
seed42_1606
|
videos/HRA_part0/1606.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 high-tech facility with glowing blue accents, a muscular firefighter, wearing a full-body protective suit and helmet, stands against a backdrop of advanced machinery. He holds an antimatter containment device, a sleek silver sphere with intricate detailing, which emits a faint blue glow, signifying its active state. The setting shifts subtly to reveal the firefighter engaging in a lively dance, maintaining a firm grip on the containment device, now resting on his hip. The dance moves fluidly from a standing position into a crouched stance, with the firefighter's hands moving dynamically, all while keeping the device secure. Throughout the sequence, the futuristic setting, characterized by clean lines and blue accents, remains visible, adding a dramatic touch to the dancing firefighter's performance.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video is distorted, with twisted arms and legs."
}
] |
seed44_1184
|
videos/HRA_part1/1184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 human-sized hare, dressed in a worker's outfit complete with a yellow helmet, blue overalls, and a red shirt, dances gleefully in a lush green meadow. The hare performs an energetic jig, its oversized feet stomping playfully on the grass, while its long ears sway in time with the music. The background features a vibrant blue sky with fluffy white clouds, adding to the surreal yet delightful atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's face is severely distorted, and its legs are also severely twisted."
}
] |
seed42_1696
|
videos/HRA_part0/1696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a middle-aged doctor, wearing a stethoscope around his neck and a crisp white lab coat over his neatly pressed blue scrubs, finds himself unexpectedly dancing in a vast savanna. As he moves with surprising grace, a curious cheetah, intrigued by the unusual sight, approaches cautiously from the tall grass. The big cat, known for its speed and agility, mirrors the doctor's dance steps, its movements fluid and powerful. The unlikely pair continues their impromptu dance, surrounded by the vast, open landscape, creating a surreal and captivating moment captured in high-definition footage.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the doctor and the cheetah dancing in the video are not smooth and continuous."
}
] |
seed42_1782
|
videos/HRA_part0/1782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray, majestic and graceful, glides through crystal-clear waters, its body a stunning contrast of black and white. It somersaults effortlessly, performing acrobatic feats just beneath the ocean's surface, with sunlight filtering through and illuminating the scene. Schools of small fish scatter as the ray passes, highlighting the vastness of its wingspan. The ray then swims upward towards the sunlit water, creating mesmerizing patterns with its movements, before disappearing into the depths, leaving a trail of bubbles in its wake.]"
},
{
"from": "gpt",
"value": "Bad. The action of the manta ray flying in the video is not smooth and continuous; the movements are uncoordinated."
}
] |
seed44_2152
|
videos/HRA_part1/2152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 small monkey wearing a red bow tie and a golden ring on its tail is leaping from one floating bookshelf to another in a vast space library. The shelves, filled with ancient books bound in brown leather, are suspended in zero gravity, illuminated by a warm, golden light. The monkey swings its arms in excitement as it jumps, revealing a joyful, playful spirit in the cosmic setting, surrounded by stars and galaxies. The library's architecture is grand, with arches and columns made of what appears to be stardust, adding to the surreal and magical atmosphere of this extraordinary space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1370
|
videos/HRA_part0/1370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic winter scene, a person clad in a thick, dark coat and matching hat walks across a snow-covered bridge, overlooking the Mammoth Mountain Ski Area. The resort's facilities, including chairlifts and lodges, are visible in the background, nestled among the snow-dusted trees. The individual continues their stroll, passing by a small, quaint chalet with smoke billowing from its chimney, adding a touch of warmth to the frosty landscape. Finally, they pause to admire the panoramic view of the snow-capped mountains and the sprawling ski resort, all while bundled up against the cold, encapsulating the essence of a winter wonderland adventure.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_193
|
videos/HRA_part1/193.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 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 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": "Normal. The actions of the server checking the smoke detector in the video are not smooth and continuous."
}
] |
seed46_2351
|
videos/HRA_part2/2351.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a crisp white shirt and black trousers, serves a coyote who is seated at a wooden table set among the lush greenery of the woodlands. The coyote, looking surprisingly refined with a napkin tucked into its collar, enjoys a meal as if dining at a fine restaurant. Behind them, a natural pool glistens under the sunlight, inviting a sense of tranquility and relaxation, contrasting the unexpected yet harmonious interaction between the waiter and the wild coyote.]"
},
{
"from": "gpt",
"value": "Bad. The server's utensils suddenly changed and deformed while making movements, and the man's hand also became deformed."
}
] |
seed44_169
|
videos/HRA_part1/169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Shanghai, under the glow of neon signs and the hustle of the city streets, a peculiar scene unfolds. A street musician, dressed in a vibrant red jacket and dark jeans, passionately plays a saxophone, its golden finish shimmering under the streetlights. Beside him, a chimpanzee, wearing a tiny blue cap and a checkered shirt, mimics the musician's movements, adding an element of whimsy to the performance. As the music fills the air, a group of runners, clad in various sportswear and illuminated by the urban landscape, passes by, some pausing to watch the unique spectacle, while others continue their journey through the lively Shanghai night.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_110
|
videos/HRA_part2/110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a gray beanie, black jacket, and khaki pants, meticulously organizes a cluttered garage. Surrounded by shelves filled with various items, including tools, bicycles, and storage bins, the writer methodically arranges the space. They handle each object with care, revealing a passion for order amidst creativity. As they work, the writer occasionally pauses to examine an item closely, perhaps reminiscing about its story, before placing it in its designated spot. The garage, bathed in warm, natural light filtering through the windows, transforms into a well-organized sanctuary, reflecting the writer's dual nature of imagination and practicality.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1324
|
videos/HRA_part0/1324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded man with glasses and a gray beanie, wearing a dark jacket, leans into the soil with a green-handled shovel, his wedding band glinting in the light. He pauses to wipe sweat from his brow, revealing a determined look. Moments later, he is joined by another man, both digging in unison, the second man dressed in a brown jacket, jeans, and a white t-shirt. The scene transitions to the first man, now shirtless and covered in dirt, continuing to dig with intense focus, highlighting the hard labor involved. Finally, the two men stand back, shovels resting on their shoulders, surveying their deep, freshly-dug hole, a sense of accomplishment evident in their satisfied expressions. Throughout the scene, the man with the beanie remains the central figure, his actions and expressions conveying the physical and emotional demands of the task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3014
|
videos/HRA_part1/3014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its bright green body with yellow fins and a striking pink head, swims gracefully in clear blue waters. Its unique appearance is highlighted as it explores a coral reef ecosystem, surrounded by various marine life. The fish's body, featuring bold colors and patterns, contrasts beautifully with the sandy seabed and lush underwater vegetation. As it moves, the parrotfish reveals its distinctive form and coloration, making it a captivating subject in the rich tapestry of oceanic biodiversity.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2255
|
videos/HRA_part1/2255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A weathered farmer, clad in a brown jacket, gray beanie, and khaki pants, dances gleefully in a grassy field under a partly cloudy sky, with rolling hills in the background. An ibex, standing nearby, observes the farmer's antics with curiosity. The farmer, his face etched with lines from years of hard work, performs a series of playful dance moves, his boots kicking up tufts of grass. The ibex, its horns curving gracefully upward, seems to mimic the farmer's movements, creating an unexpected yet charming duet between man and animal. Throughout the scene, the farmer's joyful expressions and the ibex's inquisitive gaze capture the essence of an unlikely friendship forged in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2638
|
videos/HRA_part1/2638.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 scene directed with artistic flair, a bobcat, known for its secretive nature, emerges from the dense undergrowth of a temperate deciduous forest. The sunlight filters through the canopy, casting dappled shadows on the ground as the bobcat approaches a serene, crystal-clear pool. With a sudden burst of energy, it leaps into the water, its powerful muscles propelling it forward as it swims gracefully beneath the surface. Bubbles rise around it, creating an enchanting underwater ballet, before it resurfaces, shaking droplets from its fur, and returns to the safety of the forest edge, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2707
|
videos/HRA_part0/2707.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an otter, wearing a red apron and a name tag, stands behind a cash register in a quaint market, its paws adeptly handling coins and bills as it serves a line of patiently waiting customers. The otter, with its brown fur and friendly demeanor, expertly counts change and bags items, occasionally glancing up to greet each customer with a warm smile. Meanwhile, in the background, a group of otters can be seen walking together, their little feet padding across the wooden floor, creating a charming and unexpected sight in this otherwise ordinary store setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2599
|
videos/HRA_part1/2599.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, dressed in a gray sweater, blue jeans, and black shoes, stands on a chair in a sparsely decorated room with a white ceiling and walls, checking a smoke detector with a focused expression. The room features a wooden desk with a laptop, a bookshelf filled with books, and a framed picture on the wall. The writer, with short brown hair and glasses, carefully inspects the smoke detector, ensuring it functions properly, highlighting the importance of safety in a home office setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, hands are twisted, and arms are deformed."
}
] |
seed44_2630
|
videos/HRA_part1/2630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lustrous, red-cooked lobster is presented on a simple white plate, its large, meaty tail curled gracefully. The claws, one broken open to reveal tender, succulent flesh, are garnished with fresh, green parsley. Steam gently rises from the hot shell, hinting at its recent emergence from boiling water. The setting is a rustic wooden table, adorned with a crisp, white cloth, where the lobster takes center stage under natural lighting, casting a subtle shadow that accentuates its texture and color. A small cup of clarified butter sits nearby, ready to enhance the rich, briny flavor of the lobster meat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2799
|
videos/HRA_part2/2799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green jacket, beige shirt, and brown trousers, is seen on set with a weasel perched on his shoulder. The weasel, with its sleek body and curious eyes, suddenly leaps off the director's shoulder, mid-air, creating a moment of unexpected levity. The director, maintaining his composure, watches the weasel's acrobatic jump with a mix of amusement and surprise, all captured against the backdrop of a bustling movie set.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's jumping action in the video is deformed and uncoordinated, while the director's movements do not have obvious problems."
}
] |
seed42_2070
|
videos/HRA_part0/2070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, iridescent green and purple, hovers near a red feeder, its wings a blur of motion against a clear blue sky, set against the backdrop of a lush garden filled with various flowers and greenery. The tiny bird's red beak is extended toward the feeder, while its body remains remarkably still despite the rapid wing beats. Its vibrant feathers catch the sunlight, creating a shimmering effect as it feeds, encapsulating the beauty and agility of nature in this serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The bird's beak generation in the video has problems, the claws were not generated, and the wings were generated in the wrong position."
}
] |
seed44_1017
|
videos/HRA_part1/1017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, upscale restaurant filled with the clinking of glasses and chatter, a waiter in a crisp, black uniform expertly navigates the lively dining room. He deftly pushes a polished, stainless steel service cart laden with fine china and gleaming silverware, carefully avoiding any contact with the patrons enjoying their meals. The elegant space, adorned with hanging lights casting a warm glow and walls decorated with framed artwork, provides a sophisticated setting for this scene of seamless service execution.]"
},
{
"from": "gpt",
"value": "Normal. The actions are relatively normal."
}
] |
seed46_1146
|
videos/HRA_part2/1146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a golden spacesuit, paints an antelope with vibrant colors under a starlit sky, with a spaceship gently docking in the background, casting a futuristic glow. The artist, now wearing a silver helmet and spacesuit, gracefully dances with the antelope, which has been transformed into a holographic projection, against the backdrop of a cosmic landscape filled with nebulae and distant galaxies. The scene shifts to reveal the artist inside the spaceship, where they continue to paint while floating in zero gravity, surrounded by their art supplies and the holographic antelope, which now moves in a synchronized dance, creating a mesmerizing display of art, technology, and movement in space.]"
},
{
"from": "gpt",
"value": "Bad. The artist's fingers and feet are missing in the video, and the silver spacesuit is generated with the wrong color."
}
] |
seed46_1862
|
videos/HRA_part2/1862.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European brown hare sits upright on a grassy meadow under an overcast sky, performing a grooming behavior. It wipes its face with a paw, showcasing the natural habit of self-cleaning. The hare, with its distinctive long ears and brown fur, is shown in a close-up shot, emphasizing the details of its facial features and the texture of its fur. The background is blurred, focusing attention solely on the hare's grooming actions in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_287
|
videos/HRA_part2/287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a classic white uniform and a colorful headscarf, is seen energetically cleaning windows in a brightly lit hospital room. She moves with purpose, using a squeegee to clear away streaks, while patients rest peacefully in beds adorned with vibrant floral sheets. Sunlight filters through the partially cleaned panes, casting a warm glow over the serene space. In the background, a bustling city skyline is visible, contrasting the calm atmosphere within the room. The nurse's dedication to her task is evident in her focused expression and the gleaming glass that reflects her hard work.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's movements in the video are not smooth."
}
] |
seed46_1766
|
videos/HRA_part2/1766.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a gray turtleneck sweater and brown corduroy pants, sits at a wooden desk in a rustic cabin, surrounded by nature. Suddenly, the scene changes to reveal a graceful gazelle leaping over a wooden fence in slow motion, its muscles straining against the force of the jump. The gazelle lands softly on the ground and continues to run, its movements fluid and effortless. The writer, inspired by the sight, begins to type furiously on a vintage typewriter, capturing the essence of the gazelle's leap in a beautifully written passage. The camera zooms in on the writer's face, showing the intense concentration and inspiration on their face as they bring the scene to life through their words. Throughout the video, the focus remains on the gazelle's powerful leap and the writer's artistic interpretation of it, with no additional distractions or scene transitions.]"
},
{
"from": "gpt",
"value": "Normal. The action of one hand tapping on a vintage typewriter is basically normal but uncoordinated."
}
] |
seed42_148
|
videos/HRA_part0/148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful bison, framed against a vivid orange sunset, leaps gracefully over a wooden fence in slow motion, showcasing its muscular physique and determination. Its shaggy, dark brown fur billows in the wind as it clears the barrier with ease, highlighting the animal's surprising agility and strength. The contrast between the bison's robust form and the delicate beauty of the twilight sky creates a dramatic and captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The bison's movements in the video are basically normal, with slight coordination issues."
}
] |
seed42_2603
|
videos/HRA_part0/2603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, smoke-filled environment, a firefighter wearing full gear, including a helmet and breathing apparatus, crawls through a confined space. The setting is a high-tech facility, indicated by the presence of an antimatter containment unit, which is a large, cylindrical container with intricate machinery and glowing blue lights, seen in the background. The firefighter's movements are slow and deliberate, emphasizing the hazardous conditions and the need for caution. Despite the challenging circumstances, the firefighter's determination is evident, as they navigate the narrow passage with a flashlight in hand, illuminating the path ahead. The overall scene conveys a sense of urgency and danger, with the firefighter's mission being critical to the safety of the facility and its personnel.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_2981
|
videos/HRA_part0/2981.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a cheerful cashier, donning a green apron and a nametag, is playfully dancing with a friendly horse inside a vibrant, cartoonish grocery store. The cashier, with short brown hair and a wide smile, leads the horse in a lively jig down the aisles, filled with brightly colored products. The horse, adorned with a polka-dotted bowtie and a pair of oversized sunglasses, happily trots alongside, its hooves gently tapping the checkered floor. Shoppers look on in amused surprise, some pausing to capture the unexpected spectacle on their phones, while others continue browsing the shelves, seemingly unfazed by the unusual dance party unfolding before them.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's face generation in the video is uncoordinated, and the hands are generated with distortions."
}
] |
seed46_2658
|
videos/HRA_part2/2658.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a dark green shirt, beige shorts, and a brown belt, is seen meticulously dusting vintage furniture within a grand room filled with antique artifacts. He pauses to adjust his glasses, revealing a look of deep concentration. His gaze then shifts to a large painting hanging on the wall, as if contemplating its significance. The director continues his task, now focusing on a wooden cabinet, his movements deliberate and precise, demonstrating his attention to detail. Lastly, he inspects a polished table, his reflection visible in its gleaming surface, as he ensures every inch is free from dust, all the while remaining in the same room with its collection of cherished items.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1155
|
videos/HRA_part0/1155.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 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 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": "Bad. The character's hand is distorted, and the woven object in the character's hand is also distorted."
}
] |
seed44_3040
|
videos/HRA_part1/3040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid scene set within the lush, sun-dappled understory of a subtropical dry forest, a small, agile ferret emerges from a dense thicket of ferns and moss-covered logs. Its sleek body, wrapped in rich, earthy tones, contrasts beautifully with the vibrant green foliage. The curious creature pauses, engaging in a comical self-cleaning ritual, using its paws to wipe its face and fur meticulously, revealing its playful nature amid the serene woodland setting. The ambient sounds of rustling leaves and distant bird calls add to the immersive atmosphere, capturing the essence of life in this unique ecosystem.]"
},
{
"from": "gpt",
"value": "Bad. The ferret in the video has uncoordinated movements."
}
] |
seed44_1766
|
videos/HRA_part1/1766.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a gray turtleneck sweater and brown corduroy pants, sits at a wooden desk in a rustic cabin, surrounded by nature. Suddenly, the scene changes to reveal a graceful gazelle leaping over a wooden fence in slow motion, its muscles straining against the force of the jump. The gazelle lands softly on the ground and continues to run, its movements fluid and effortless. The writer, inspired by the sight, begins to type furiously on a vintage typewriter, capturing the essence of the gazelle's leap in a beautifully written passage. The camera zooms in on the writer's face, showing the intense concentration and inspiration on their face as they bring the scene to life through their words. Throughout the video, the focus remains on the gazelle's powerful leap and the writer's artistic interpretation of it, with no additional distractions or scene transitions.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's jumping motion is not smooth and coordinated, with sudden changes."
}
] |
seed44_284
|
videos/HRA_part1/284.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a lab coat over a collared shirt and khaki pants, gently caresses a hamster in a zero-gravity environment, suggesting space agriculture. The doctor, with neatly trimmed facial hair and spectacles, holds the hamster with care and attentiveness, floating effortlessly in a spaceship's cabin. The hamster, nestled in the palm of the doctor's hand, appears relaxed and comfortable, indicating a nurturing bond between the two. In the background, hydroponic plants grow in LED-lit chambers, emphasizing the agricultural aspect of the scene. The doctor's focus on the hamster, combined with the futuristic setting, conveys a sense of compassion and innovation in space farming.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3170
|
videos/HRA_part2/3170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a white tank top, blue denim overalls, and a wide-brimmed straw hat, sprints across a lush, green landscape dotted with ancient cemeteries. The rolling hills and distant, hazy mountains provide a scenic backdrop as he runs past weathered tombstones and aged monuments. His journey takes him along a narrow path lined with wildflowers and overgrown grass, leading through the serene burial grounds. Amidst the tranquility of the cemeteries, the farmer's vigorous run adds a dynamic element to the otherwise peaceful setting.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's running movements in the video are uncoordinated."
}
] |
seed46_1161
|
videos/HRA_part2/1161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a futuristic silver spacesuit with an American flag patch, is seen crawling across the rocky, red Martian landscape, examining the terrain closely. The scene is set under a pinkish-brown sky, with distant mountains visible on the horizon. The officer's spacesuit features NASA logos and a utility belt, and they carry a high-tech scanner, highlighting the unusual combination of law enforcement and space exploration. The camera captures this unique moment in crisp, high-definition detail, emphasizing the contrast between the traditional role of a police officer and the extraordinary setting of a distant planet.]"
},
{
"from": "gpt",
"value": "Normal. The character does not have a scanner in their hand."
}
] |
seed44_1350
|
videos/HRA_part1/1350.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 European badger, with its distinct black and white striped face and grey fur, walks purposefully across a lush, green meadow under the dappled shade of tall trees. It pauses for a moment, standing on all fours, to sniff the air with its keen sense of smell. Then, it continues its journey, moving with a slight waddle due to its sturdy build, leaving behind a trail in the soft grass. The scene is set in the peaceful serenity of nature, with the badger as the sole focus, highlighting its natural habitat and behavior.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2827
|
videos/HRA_part1/2827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, donning a white hazmat suit with a respirator mask, meticulously paints the walls of a spacious, well-lit room with vibrant orange strokes, capturing the essence of transformation. His attire, complete with protective goggles and gloves, underscores the precision and safety measures involved in the task. The room, initially a blank canvas, gradually comes alive with color, highlighting the engineer's skill and attention to detail as he revitalizes the space.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted in the video."
}
] |
seed44_2542
|
videos/HRA_part1/2542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sprawling landfill under a hazy sky, three children, two boys and a girl, wearing ragged clothes and protective masks, stand together. One boy, in a red shirt, holds a large rag and wipes the grimy face of another boy, who wears a yellow shirt, while the girl, in a blue dress, watches intently. The action conveys a sense of care and support among the children in this challenging environment. Nearby, piles of discarded electronics, tires, and debris form a bleak landscape, contrasting with the children's resilience and connection.]"
},
{
"from": "gpt",
"value": "Normal. The action of the boy in the red shirt wiping the boy in the yellow shirt is basically normal, but there is some lack of coordination."
}
] |
seed42_2352
|
videos/HRA_part0/2352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, lush green savanna under a bright, sunny sky, a majestic Bengal tiger runs swiftly across the open grassland, its powerful muscles rippling beneath its vibrant orange coat, marked with distinctive black stripes. The tiger's piercing yellow eyes are focused ahead, conveying determination and grace in motion. The scene is framed by distant gallery-like structures, housing various wildlife exhibits, which add a unique architectural element to the natural setting. The tiger's fluid movements and the contrast between the untamed wilderness and the man-made galleries create a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_124
|
videos/HRA_part2/124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 glasses and a neat beard sits at a wooden desk, intensely pushing letters on a vintage typewriter, surrounded by piles of books and papers. The room is dimly lit by a standing lamp, casting shadows that emphasize his focused expression. Wearing a green military-style jacket, he leans forward, completely absorbed in his work, as if battling to translate his thoughts into words. The cluttered environment reflects his creative process, with the typewriter positioned center-stage, highlighting the act of writing as both a physical and mental endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The video has some scenes zoomed in during the middle frames, causing the proportion between the character's hand and the typewriter to be off."
}
] |
seed44_2244
|
videos/HRA_part1/2244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 peaceful woodland setting, a small, curious badger is shown gently caressing the nose of another badger, likely its mate, with its forepaw, conveying a tender moment of connection between the two creatures. The scene is illuminated by a soft, golden light filtering through the trees, casting a warm glow on the badgers as they engage in this intimate gesture. Their fur is depicted in rich, earthy tones, and the surrounding foliage provides a lush, natural backdrop that enhances the serene atmosphere of this unique encounter.]"
},
{
"from": "gpt",
"value": "Bad. The badger's claws and mouth generation in the video have issues, and there is a problem with the right eye of the badger."
}
] |
seed42_2700
|
videos/HRA_part0/2700.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest setting, a majestic gray wolf gently caresses a smaller, white wolf with its nose, demonstrating a tender moment of affection between the two creatures. The gray wolf, with piercing yellow eyes, a thick, shaggy coat, and a muscular build, leans its head down to touch noses with the smaller white wolf, which looks up with a similar intensity. Both wolves are standing in a grassy clearing within the dense forest, surrounded by tall trees and patches of sunlight filtering through the leaves, creating a serene atmosphere for this intimate interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1730
|
videos/HRA_part2/1730.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown shirt and glasses, is seen in a unique scenario, engaging with a hyena at a public swimming pool. The director, standing at the edge of the pool, interacts with the wild animal, which is swimming in the water, creating an extraordinary juxtaposition of human and beast in an unexpected urban setting. The director's attire, complete with brown shirt and glasses, contrasts with the untamed presence of the swimming hyena, capturing a surreal and captivating moment.]"
},
{
"from": "gpt",
"value": "Normal. The hyena's swimming movements in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed44_2252
|
videos/HRA_part1/2252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a green sweater and brown trousers, kneels on a lush, grassy field as they observe a graceful gazelle. The writer, with a notebook in hand, carefully documents the gazelle's movements from a crawling position, capturing the serene atmosphere under a clear blue sky. The scene highlights the writer's dedication to their craft, as they immerse themselves in nature to gather inspiration, while the gazelle, unaware of the observer, continues its elegant grazing nearby.]"
},
{
"from": "gpt",
"value": "Bad. The movements are slightly discontinuous."
}
] |
seed46_3132
|
videos/HRA_part2/3132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, wearing a navy blue blazer, sits against a dark, textured background, nodding sagely as he listens to an off-screen voice. His salt-and-pepper hair, trimmed beard, and wire-rimmed glasses add to his sophisticated appearance. Throughout the scene, he continues to nod in agreement, his expressions conveying understanding and engagement. The focus remains tight on his face, capturing every nuanced gesture and emotion, highlighting his acting prowess in this intimate setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1122
|
videos/HRA_part2/1122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, dressed in a black vest and white button-down shirt, kneels in a lush green meadow. He gently caresses a meerkat standing on its hind legs, which is perched on a small wooden table covered with a white cloth and decorated with a single red rose in a vase. The waiter's face is filled with a warm smile, his eyes softly gazing at the meerkat as he tenderly strokes its back with his right hand. The scene is peaceful and heartwarming, with the sun casting a golden glow over the meadow and the meerkat's curious expression adding to the charm of the moment.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's limbs and the waiter's hands in the video were generated abnormally, and the vase and red roses were not generated."
}
] |
seed42_219
|
videos/HRA_part0/219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An endearing otter, with its distinct brown fur and charming face, sits on a wooden boardwalk, creating an unusual yet captivating scene. It reaches out with its paw, seemingly caressing the surface of the weathered wood, as if cherishing a familiar touch. The otter's playful demeanor and the texture of the boardwalk combine to form a narrative of unexpected encounters and gentle interactions in a natural yet built environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2236
|
videos/HRA_part1/2236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a dingo, wearing swimming goggles and a yellow life vest, playfully swims in a clear, blue pool under a cloudy sky, its joyful demeanor evident. Meanwhile, inside a small wooden cabin nearby, a young male cashier, sporting a red and white striped shirt, attentively handles transactions with a friendly smile, standing behind a counter filled with various snacks and beverages, the cash register visible beside him. The dingo occasionally glances toward the cabin, seemingly curious about the activities of the human cashier, who remains focused on his duties despite the unusual presence of a swimming dingo nearby.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2156
|
videos/HRA_part0/2156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-lit, modern clothing store, a friendly, young female cashier with brown hair tied in a bun assists a male customer. She is shown measuring the hem of a pair of beige slacks, using a measuring tape, while the man stands patiently. The pants are held up by the customer, who wears a casual outfit consisting of a blue shirt and dark pants. The cashier, dressed in a black apron over a white blouse, carefully marks the fabric with a tailor's chalk, indicating where the alteration should be made. The scene is set against the backdrop of the store, with various racks of clothes visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and there are sudden changes."
}
] |
seed42_2905
|
videos/HRA_part0/2905.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, recognizable by its black ears and eye patches, crawls on all fours across a lush, green forest floor, its fur a striking contrast against the vibrant vegetation. It moves slowly, carefully placing each paw, showcasing its strength and agility. The panda's attention is drawn to something in the distance, its ears perked, adding a layer of curiosity to its demeanor. Surrounded by bamboo plants, a staple in its diet, the panda continues its crawl, encapsulating the essence of its natural habitat in every deliberate motion.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1355
|
videos/HRA_part1/1355.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiger, showcasing its striking orange and black stripes, gently caresses a smaller, more docile white tiger cub with its large, padded paw, both set against a lush, green forest backdrop. The adult tiger displays a tender side, its piercing yellow eyes gazing softly at the cub. The cub, with its playful nature, responds by nuzzling into the larger tiger's paw, highlighting the affectionate bond between them. This intimate moment unfolds in a serene environment, with the tigers surrounded by dense foliage and sunlight filtering through the leaves, casting dappled shadows on the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1532
|
videos/HRA_part1/1532.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A weathered farmer wearing a brown jacket and wide-brimmed hat kneels in a lush, green field, engaging in meticulous work. Suddenly, the scene reveals that he is crawling, his focused eyes set on the task at hand, perhaps planting seeds or tending to crops. Uncommonly, a zebra stands nearby, watching the farmer with interest, its distinctive black-and-white stripes stark against the verdant landscape. The farmer continues to crawl through the rows, the zebra's presence adding an unexpected element to the pastoral setting. Throughout, the farmer's dedication to his work and the zebra's curious observation create a unique agricultural tableau.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1009
|
videos/HRA_part0/1009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, donning a black leather jacket, dark jeans, and a white T-shirt, is seen energetically dancing in a vast, open space, backlit by the golden hour sun. Amidst his lively moves, a tiny vole emerges from the grass, its small, curious eyes fixated on the man. The man continues to dance, oblivious to the vole's presence, his movements casting dynamic shadows across the grassy landscape. The vole watches from a safe distance, seemingly fascinated by the man's animated performance under the warm, evening light.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the dancer are generated incorrectly."
}
] |
seed46_2213
|
videos/HRA_part2/2213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a waiter wearing a black vest and white shirt gently caresses various plants in a subtropical shrubland. Surrounded by lush greenery and vibrant flowers, he tenderly touches the leaves, creating an unexpected connection between service and nature. The camera captures his delicate movements as he interacts with the environment, highlighting the peaceful coexistence of a professional figure in an unconventional natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The server's action of touching the plant in the video is not very smooth and continuous, showing some coordination issues."
}
] |
seed44_1540
|
videos/HRA_part1/1540.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, fluffy white dog runs alongside a futuristic lunar buggy as it traverses the desolate, rocky terrain of the moon's surface, illuminated by the distant Earth shining brightly in the sky. The dog, wearing a red bandana and a small backpack, bounds energetically over the rugged landscape, while the lunar buggy, equipped with large, treaded wheels and a solar panel roof, cruises steadily beside it. Inside the buggy, a figure in a spacesuit can be seen piloting the vehicle, their helmet visor reflecting the barren lunar scenery. The Earth hangs low on the horizon, casting a pale blue glow over the stark, airless environment.]"
},
{
"from": "gpt",
"value": "Bad. The dog's running motion is uncoordinated."
}
] |
seed42_1541
|
videos/HRA_part0/1541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a waiter in full uniform, complete with a white shirt, black vest, and tie, is shown running along the edge of a busy highway. The highway is filled with cars and trucks, creating a bustling urban atmosphere. The waiter's face conveys determination as he sprints, his black trousers and polished shoes moving swiftly against the gritty pavement. The scenery includes billboards and distant city buildings, providing a backdrop of urban life. Despite the unusual setting, the waiter remains focused, his gaze fixed ahead as he continues his unexpected journey along the highway.]"
},
{
"from": "gpt",
"value": "Bad. The man's running in the video is not smooth, and his movements are uncoordinated."
}
] |
seed44_2104
|
videos/HRA_part1/2104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, donning a crisp white shirt and black vest, stands in a spacious living room with hardwood floors and a large window, engaging in an unusual task. He is diligently assembling a wooden table using various tools, demonstrating unexpected handyman skills. As the scene progresses, the fully assembled table is revealed, complete with a tablecloth and set for a meal, blending elements of his professional service role with a domestic setting. The waiter then proceeds to polish the silverware, juxtaposing his traditional duties with the earlier DIY activity, all within the same elegant residential space.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed, the arm is elongated and distorted. Objects in the hand suddenly disappear and reappear."
}
] |
seed44_2870
|
videos/HRA_part1/2870.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A director wearing a beige jacket walks through a set resembling a forest, carrying a clapboard marked 'Quantum Leap.' He stops to observe a CGI-generated rhinoceros walking past him, its movements synchronized with the director's pace. The rhinoceros, rendered with high detail, appears to interact naturally with the forest environment, while the director watches intently, his expression conveying a mix of professionalism and wonder.]"
},
{
"from": "gpt",
"value": "Bad. The rhinoceros's head and legs were generated abnormally, the director's face was generated blurry, and the fingers were generated with abnormal proportions."
}
] |
seed44_1092
|
videos/HRA_part1/1092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom, a teacher with short brown hair, wearing a gray top, instructs students about space travel, using a large screen displaying a galactic police chase between a red spaceship and several blue police cruisers. The chase unfolds against a backdrop of stars, planets, and asteroids. The scene then transitions to show the teacher leading her class on a field trip to an indoor swimming pool, where they swim and play water games under her watchful eye, all while wearing swimsuits and caps in various colors. The pool area features large windows offering views of the city skyline, creating a vibrant and engaging learning environment.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's movements are uncoordinated, and while the students' movements show swimming actions, they are not fluid."
}
] |
seed46_1441
|
videos/HRA_part2/1441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, nestled in the fork of a lush eucalyptus tree, gently caresses its companion with a fuzzy paw, both enveloped in the verdant embrace of their arboreal home. The koala, with its round face and endearing expression, tenderly touches another koala, showcasing a heartwarming display of affection. Their interaction is set against the vibrant green foliage, highlighting the tenderness of their connection. As they engage in this intimate gesture, their soft fur and the intricate details of the eucalyptus leaves create a visually captivating scene. Throughout, the two koalas remain in this loving embrace, emphasizing the emotional bond between them.]"
},
{
"from": "gpt",
"value": "Normal. The koala's movements in the video are basically normal, with slight inconsistency."
}
] |
seed46_2062
|
videos/HRA_part2/2062.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars majestically across a clear blue sky, its sharp eyes scanning the terrain below for any signs of movement. Its streamlined body, covered in a mottled brown and gray plumage, cuts through the air with effortless grace. The bird's hooked beak and powerful talons are on full display as it dives suddenly, plummeting towards the earth in pursuit of prey. In a burst of speed, it snatches a small rodent from the tall grass, its sharp claws closing around the struggling creature. The sparrowhawk then rises again into the heavens, carrying its prize back to its nest, a picture of strength and agility against the vastness of the sky.]"
},
{
"from": "gpt",
"value": "Normal. The sparrowhawk's flight in the video is basically normal, with only slightly uncoordinated movements."
}
] |
seed44_3142
|
videos/HRA_part1/3142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an otherworldly ecosystem on an alien planet, a unique creature resembling Earth's beaver crawls through a dense, bioluminescent forest. Its brown fur stands out against the vibrant, glowing flora. The beaver-like being navigates the intricate terrain, its flat tail dragging slightly, as it explores the mysterious landscape filled with towering, luminescent trees and strange, colorful plant life. This extraterrestrial environment, illuminated by an eerie yet beautiful light, provides a surreal setting for the beaver's curious journey.]"
},
{
"from": "gpt",
"value": "Normal. The video only shows camera movement, with no movement from the organisms."
}
] |
seed44_3052
|
videos/HRA_part1/3052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling art gallery filled with contemporary paintings and sculptures, a distinguished film director, wearing a gray suit with a blue shirt and tie, passionately discusses a project with two colleagues. Suddenly, he breaks into an impromptu dance, spinning and moving with joyful abandon. The gallery space, illuminated by spotlights highlighting the artwork, becomes his stage, with onlookers smiling and watching his spontaneous performance. Throughout, the director's animated expressions and gestures convey his enthusiasm and creativity, all captured in high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The director's movements in the video are not smooth."
}
] |
seed42_1796
|
videos/HRA_part0/1796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a black vest, white shirt, and black trousers, crawls through a network of meerkat tunnels. The tunnels are meticulously crafted from sandy soil, with intricate pathways and chambers. The waiter, displaying a sense of adventure and playfulness, carefully navigates the tight spaces, his movements mimicking those of the meerkats that typically inhabit these underground structures. His attire remains remarkably clean and undisturbed despite the crawling, highlighting the surreal nature of the scenario.]"
},
{
"from": "gpt",
"value": "Bad. The man's face in the video is blurry, his limbs and fingers are incomplete, and his body is distorted."
}
] |
seed44_2976
|
videos/HRA_part1/2976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal space setting illuminated by cosmic lights, a brave firefighter in full gear, complete with a helmet and breathing apparatus, stands solemnly beside a wise-looking badger, both participating in a mysterious, otherworldly religious ceremony. The ceremony takes place on a floating platform surrounded by stars, galaxies, and celestial bodies. The scene then shifts underwater, where the firefighter and the badger are swimming gracefully in a clear, tranquil pool, with the firefighter's gear now adapted for aquatic environments. The pool is encircled by ancient, space-themed ruins, giving the impression of an extraterrestrial civilization. Throughout the sequence, the two characters maintain a sense of reverence, as if honoring a sacred tradition in this unique blend of terrestrial heroism, woodland wisdom, and cosmic spirituality.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2157
|
videos/HRA_part0/2157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vole, brown with white underparts, scurries along a paved path between two large apartment complexes, their exteriors a mix of brick and siding, under a partly cloudy sky. The rodent navigates the concrete walkway, dotted with cracks and weeds, passing by the base of the buildings where potted plants and bicycles are stored. It continues its journey undisturbed, weaving between the structures that tower above it, set against the backdrop of a suburban neighborhood with cars parked along the street and other apartment buildings visible in the distance.]"
},
{
"from": "gpt",
"value": "Bad. The vole's body is twisted, its head is twisted, and its claws are twisted."
}
] |
seed46_1671
|
videos/HRA_part2/1671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned farmer, clad in a brown jacket and denim overalls, rests on his hands and knees in a lush green field, engaging in a playful crawl. Beside him, a curious brown hare mimics his movements, hopping and crawling through the tall grass, creating a heartwarming scene of unexpected companionship between man and nature. The farmer's joyful expression and the hare's energetic antics set against the vibrant green landscape capture a rare moment of harmony in the countryside.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1769
|
videos/HRA_part2/1769.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow safety vest and dark pants, sprints with urgency across a wooden bridge overlooking a geyser's steamy plume in the background. The scene shifts to show the janitor running from right to left, with the geyser's eruption seen erupting behind him, emphasizing his hurried pace. Next, he is depicted dashing down a stone pathway, with the geyser's intermittent eruptions providing a dramatic backdrop. Finally, the janitor is shown sprinting on a dirt path, with the geyser's majestic plumes in the distance, highlighting his perseverance against the geothermal landscape.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are very unsmooth and uncoordinated."
}
] |
seed44_2642
|
videos/HRA_part1/2642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small hamster, with its distinctively furry cheeks and nose, energetically runs inside a clear plastic exercise ball. It scampers across a room filled with everyday objects like furniture and potted plants, providing a unique perspective on a typical living space. The hamster's movement is fluid and rapid, highlighting its determination and playful nature as it explores its surroundings within the safety of the transparent sphere.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the hamster running inside a transparent plastic exercise ball as mentioned in the caption."
}
] |
seed44_1307
|
videos/HRA_part1/1307.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chef wearing a classic white uniform and toque walks alongside a bobcat on a leash in a lush, green park. The chef, holding a large bunch of fresh herbs, interacts casually with the curious bobcat, which wears a matching chef's hat, adding a touch of humor. The two stroll past a row of vibrant red tulips, drawing attention with their unusual companionship. The chef, maintaining a professional demeanor, occasionally glances at the bobcat, ensuring its comfort during their walk. The setting, a well-manicured garden with neatly trimmed hedges, provides a picturesque backdrop for this unlikely duo.]"
},
{
"from": "gpt",
"value": "Good. There are no obvious problems."
}
] |
seed42_2370
|
videos/HRA_part0/2370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male worker, wearing a brown jacket and gray pants, stands in front of a large industrial machine in a dimly lit factory. He blinks rapidly, perhaps due to fatigue or the strain of focusing on his task. The machine, which features a large gear and various mechanical components, dominates the background, emphasizing the environment's industrial nature. The worker's expression conveys a sense of determination mixed with the physical demands of his job, highlighted by his blinking eyes.]"
},
{
"from": "gpt",
"value": "Normal. The man's face is distorted and deformed."
}
] |
seed46_3035
|
videos/HRA_part2/3035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape filled with diverse restaurants, a police officer, clad in a crisp uniform with a badge and cap, stands attentively near a cozy eatery. The scene shifts subtly to focus on the officer gently caressing the head of a loyal K9 partner, who sits attentively beside him, highlighting a tender moment of connection amidst the urban environment. The pair stands out against the backdrop of restaurant signs, patrons enjoying meals, and the vibrant life of the city, capturing a blend of duty and compassion.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_266
|
videos/HRA_part2/266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by his black-framed glasses and neat appearance, stands in a modern kitchen with a clean, white countertop and stainless steel appliances. He wears a white chef's coat over a blue shirt and dark pants, and sports a neatly trimmed beard. He focuses intently on his cooking task, holding a whisk in his right hand and stirring a mixture in a bowl with precision and care. Behind him, a window allows natural light to illuminate the space, adding to the clean and professional atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. No windows were generated."
}
] |
seed42_2226
|
videos/HRA_part0/2226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 peaked cap, kneels in a park surrounded by green grass and trees, gently caressing a small brown hare with soft, comforting strokes. The officer's compassionate expression and careful handling of the hare, which sits calmly in the palm of his hand, convey a sense of tenderness and care. The peaceful setting, with the lush vegetation and clear sky, adds to the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The officer's hand and the brown rabbit in the video were generated abnormally."
}
] |
seed46_1067
|
videos/HRA_part2/1067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman, wearing a vibrant red dress and black high heels, gracefully dances in the center of a bustling restaurant. The place is filled with the warm glow of hanging lights and lively chatter from the patrons seated at their tables. She moves with confidence and joy, her dress swirling around her as she twirls to the rhythm of the live band playing in the corner. The camera captures her expressive face, full of happiness, and the admiring glances of those around her who pause to watch her performance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1912
|
videos/HRA_part2/1912.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished, bald musician, donning a black turtleneck, focuses intently on fixing a leaky faucet in an upscale bathroom with marble countertops. Initially, he looks thoughtful, holding a wrench and examining the faucet. Moments later, he is seen tightening the faucet with the tool, his sleeves rolled up, revealing a tattoo on his arm. He then tests the faucet, turning it on and off, ensuring no leaks remain. Finally, he wipes his hands on a towel, looking satisfied with his handiwork, all set against the backdrop of a luxurious bathroom with a marble sink and countertop.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a wrench, and the towel was generated too early."
}
] |
seed42_1263
|
videos/HRA_part0/1263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nervous-looking cashier, a young man with glasses and a name tag, stands behind a checkout counter. He wears a red apron over a white collared shirt, and his fingers shake slightly as he handles a stack of cash. The scene is set in a dimly lit grocery store aisle, with products visible on shelves in the background. The man's apprehensive demeanor is evident in his furrowed brow and tense posture, as he carefully counts the money with quivering hands, the camera capturing every detail in high definition.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2421
|
videos/HRA_part0/2421.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate female teacher, wearing a green sweater and brown hair, gently caresses a large leaf from a temperate rainforest tree during an educational field trip, her face expressing wonder and reverence for nature. Moments later, she holds a branch from a temperate rainforest, engagingly teaching her attentive students about the ecosystem. Then, she lovingly touches a moss-covered log, her actions conveying the importance of the rainforest environment, with the students looking on. Finally, she carefully strokes a fern frond, her demeanor highlighting the beauty and fragility of the temperate rainforest, all while surrounded by lush greenery and the natural world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1595
|
videos/HRA_part1/1595.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, complete with a receding hairline, glasses, and a gray beard, is depicted in a series of vignettes scrubbing various surfaces in a bathroom. In the first frame, he vigorously cleans the bathtub, wearing a black turtleneck sweater, khaki pants, and black shoes, his attire contrasting with the task at hand. Next, he is seen on his knees, scrubbing the floor tiles with the same intensity, his clothing now slightly disheveled. Then, he appears focused on cleaning the toilet bowl, his attire unchanged, showcasing his determination to tackle household chores. Lastly, he is shown wiping down the sink countertop, his attire still formal despite the domestic activity, highlighting the juxtaposition of his professional persona with the mundane task of bathroom cleaning.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_174
|
videos/HRA_part0/174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush, green forest setting, a mature monkey tenderly caresses a smaller monkey, possibly its child, against a backdrop of vibrant foliage and dappled sunlight. The older monkey, with a fur color that appears dark brown or black, gently holds the smaller monkey, whose fur is lighter in color, perhaps blonde or sandy. The interaction is intimate and caring, with both monkeys seated on a branch amid the dense vegetation. This heartwarming scene captures the essence of primate affection in their natural habitat, surrounded by the rich textures and colors of the forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The faces and hands of the monkeys in the video are generated abnormally."
}
] |
seed46_2856
|
videos/HRA_part2/2856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, wearing a yellow blouse and khaki pants, is seen joyfully dancing in a classroom decorated with educational posters. On a nearby desk sits a small, curious gerbil, nibbling on a piece of wood inside its cage. The teacher's energetic movements and warm smile create a vibrant atmosphere, while the gerbil's playful antics add a touch of whimsy to the scene. The camera captures the dynamic interaction between the dancing teacher and the fascinated gerbil, highlighting the unique bond they share within the educational environment.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's facial features in the video are generated blurily, and the fingers are deformed."
}
] |
seed42_1462
|
videos/HRA_part0/1462.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform and a light brown jacket, kneels in a modest living room to feed three domesticated cats. The room features a small, cluttered table, a beige couch, and a brown coffee table. The officer demonstrates kindness and care, pouring food into a green bowl as the cats eagerly surround him. Moments later, he gently pets one of the cats, showcasing a softer side of law enforcement, with the cats nestled around the bowl and the comforting interior of the home providing a backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the action of petting a cat, but the action of feeding the cat is not smooth and continuous, with abrupt changes."
}
] |
seed44_2676
|
videos/HRA_part1/2676.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dapper musician, clad in a black suit and red tie, strolls down a gravel path in the midst of a lush forest, accompanied by a friendly moose. The pair walk side by side, the musician holding his violin case, while the moose ambles along, its large antlers brushing against the tree branches. Sunlight filters through the dense canopy overhead, casting dappled shadows on the path as the duo continues their peaceful journey together.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1000
|
videos/HRA_part2/1000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, donning a red apron over a casual outfit, is shown unclogging a drain in a break room, revealing a moment of unexpected duty. The scene opens with the cashier looking into the drain with a concerned expression, followed by her using a plunger to clear the clog, showcasing determination. Next, she inspects the plunger with a look of resolve, indicating her commitment to resolving the issue. The scene then shows her pouring a cleaning solution down the drain, wearing rubber gloves for protection, and finally, she tests the faucet, ensuring the water flows freely, a sign of success, all while maintaining her red apron emblematic of her primary role.]"
},
{
"from": "gpt",
"value": "Normal. The character's arms and fingers appear deformed."
}
] |
seed44_2928
|
videos/HRA_part1/2928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 badger, typically known for its sturdy build and earthy tones, is depicted in an unexpected scenario, engaging in a joyful dance within its natural habitat. The badger, adorned with a red bow tie and a small top hat, moves energetically to an unseen beat, surrounded by lush greenery and under the shade of towering trees. Its dance is characterized by playful twirls and energetic hops, a stark contrast to its usual demeanor, all captured in a whimsical and vibrant scene that highlights the unexpected delight of a dancing badger in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_174
|
videos/HRA_part2/174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest setting, a mature monkey tenderly caresses a smaller monkey, possibly its child, against a backdrop of vibrant foliage and dappled sunlight. The older monkey, with a fur color that appears dark brown or black, gently holds the smaller monkey, whose fur is lighter in color, perhaps blonde or sandy. The interaction is intimate and caring, with both monkeys seated on a branch amid the dense vegetation. This heartwarming scene captures the essence of primate affection in their natural habitat, surrounded by the rich textures and colors of the forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the monkeys in the video are not smooth, and the actions are uncoordinated."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.