video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2754
|
videos/HRA_part2/2754.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 sits at a desk, bathed in the glow of a computer screen in a dimly lit room, his fingers poised above a black keyboard. He blinks slowly, revealing tired eyes beneath furrowed brows, hinting at the depth of concentration required for his writing task. Dressed in a white shirt with rolled-up sleeves, he exudes determination and focus, his gaze fixed on the screen as if willing the words to appear. The quiet intensity of the scene is punctuated by the soft clack of keys as he types, emphasizing the solitary nature of the creative process.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are deformed, and there are issues with the glasses."
}
] |
seed46_1682
|
videos/HRA_part2/1682.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European badger, distinguished by its black and white striped face and gray fur, runs across a lush green meadow dotted with yellow flowers. The badger, with a serious expression, moves purposefully through the grassy landscape under a cloudy sky. It pauses briefly, standing upright on its hind legs, before continuing its run. Throughout the scene, the badger maintains its focus and direction, showcasing its agility and determination in the outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The European badger in the video runs on the grass not smoothly, with uncoordinated movements."
}
] |
seed44_2731
|
videos/HRA_part1/2731.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda, garbed in a miniature spacesuit reminiscent of a classic NASA design from the Apollo era, embarks on a space diplomatic mission. It walks purposefully across a simulated lunar landscape, the textured surface and stark, airless environment highlighted by the distant Earth shining brightly in the background. This unique scene combines elements of science fiction, diplomacy, and conservation, featuring the panda as a symbol of peace and goodwill among the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2146
|
videos/HRA_part0/2146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ghost shrimp, nearly transparent with greyish-blue tones, clings to a piece of driftwood submerged in a freshwater aquarium. Its delicate antennae and legs are clearly visible, showcasing its intricate anatomy. Nearby, water bubbles softly, adding a gentle ambience to the scene. The shrimp's translucent body allows a view of its internal organs, emphasizing its unique characteristic. Surrounded by aquatic plants and gravel, the ghost shrimp appears in sharp focus against the slightly blurred environment, highlighting its presence in the tank.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_123
|
videos/HRA_part1/123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of college students, clad in swimsuits and casual wear, gather at a secluded hot spring in a lush, green forest. One student, a young woman in a black bikini and cap, crawls along the edge of the spring, playfully exploring the warm waters. The scene is filled with vibrant greenery, the steam rising from the hot spring, and the natural beauty of the surrounding environment, creating a sense of adventure and camaraderie among the students.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2906
|
videos/HRA_part1/2906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged man wearing a white lab coat over a crisp blue shirt and khaki trousers walks his golden retriever on a leash in a lush, green park. The sun filters through the leaves, casting dappled light on the path. The doctor, with salt-and-pepper hair and glasses, smiles warmly as he interacts with his dog, which bounds joyfully ahead, exploring the surroundings. The two stroll past other park-goers, who exchange friendly nods, creating a scene of community and companionship in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's facial features and fingers are deformed in the video, and the golden retriever's legs are partially missing."
}
] |
seed42_282
|
videos/HRA_part0/282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 person dressed in a panda costume runs playfully through the narrow, cobblestone streets of a quaint town, surrounded by colorful, closely-packed buildings. The panda mascot dashes past outdoor cafes, small shops with hanging signs, and historical architecture, blending elements of fantasy and reality. Locals and tourists alike look on in amusement, some taking photos, as the panda sprints by, adding a touch of unexpected joy to the picturesque town. The mascot's movements are energetic and lively, contributing to the overall sense of fun and adventure in this unique setting.]"
},
{
"from": "gpt",
"value": "Normal. The panda mascot's movements in the video are slightly unsmooth."
}
] |
seed44_1190
|
videos/HRA_part1/1190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant supermarket setting, a middle-aged janitor, clad in a green vest and holding a mop, finds himself unexpectedly chasing after a mischievous weasel. The weasel, sporting a tiny red cap, races down the aisles filled with neatly stacked produce and canned goods, causing mild chaos. The janitor, with a look of determined amusement, sprints behind, weaving through shoppers and dodging displays. Amidst the commotion, the supermarket's bright lights and colorful signage create a dynamic backdrop for this unusual pursuit.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth, and the weasel's movements are not smooth."
}
] |
seed44_2647
|
videos/HRA_part1/2647.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 flat, textured flounder fish lies on a bed of ice, its right eye large and prominent, gazing upwards. The fish is positioned diagonally, with its tail fin pointing towards the bottom right corner of the frame and its head facing upwards. Its skin exhibits a mottled pattern of brownish-grey tones, providing a realistic representation of the marine creature. The icy surface beneath the fish reflects a cool, bluish tint, adding depth and texture to the composition. Surrounding the flounder are shards of ice, creating a natural and authentic setting for the seafood display.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1395
|
videos/HRA_part0/1395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara sits calmly in a natural setting, surrounded by lush greenery and water in the background. It gently caresses another smaller capybara with its front paws, showing tenderness and care. Both capybaras are positioned against a serene landscape, highlighting the intimate interaction between the two creatures. The larger capybara's nurturing touch towards the smaller one conveys a sense of affection and protection within their social structure.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2873
|
videos/HRA_part0/2873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet futuristic scene, a giant panda, wearing a spacesuit and helmet adorned with antennas, sits against a backdrop of stars and galaxies, symbolizing deep space communication. The panda is seen wiping its paw across the visor of its helmet, perhaps to clear condensation, while floating in zero gravity, surrounded by the vastness of space. This unique juxtaposition of elements - the panda representing Earthly innocence, the spacesuit and helmet signifying human exploration, and the cosmic background evoking a sense of wonder - creates a captivating and surreal visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The panda's face in the video is generated blurry, and the paws are deformed."
}
] |
seed42_2476
|
videos/HRA_part0/2476.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, clad in a brown jacket and worn jeans, kneels in a sprawling wheat field under a cloudy sky, his weathered hands digging into the fertile soil. Suddenly, the focus is on a lone wolf, its gray fur blending with the muted colors of the landscape, crawling stealthily through the tall grass at the edge of the field, its eyes fixed on an unseen prey, creating a tense atmosphere in the rural setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and suddenly change."
}
] |
seed44_2340
|
videos/HRA_part1/2340.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cashier, wearing a red apron over a casual outfit of a gray t-shirt and khaki pants, takes a break from his usual duties to fix a leaky faucet. He is shown kneeling before a bathroom sink, tools in hand, with a look of determination on his face. The scene is set in a small restroom, with beige walls and a window casting natural light onto the countertop. As he works, the camera captures his focused expression and the intricate details of the plumbing, highlighting the contrast between his customer service role and his unexpected handyman task.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed42_1274
|
videos/HRA_part0/1274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fisherman, clad in a yellow raincoat and matching hat, stands waist-deep in the water, his gaze fixed on the horizon. His hands, weathered from years of labor, expertly handle the fishing net as he casts it into the vast, shimmering sea. The early morning sun bathes the scene in a golden glow, casting long shadows and highlighting the droplets of water clinging to the net. Seagulls circle overhead, their calls adding to the serene atmosphere of the coastal landscape. In the distance, the silhouette of a small fishing village can be seen, smoke rising from the chimneys of the quaint houses, a reminder of the community that thrives on the fruits of the sea.]"
},
{
"from": "gpt",
"value": "Normal. The fisherman's left arm in the video has generation issues, and some seagulls suddenly disappear in the middle frames."
}
] |
seed42_3087
|
videos/HRA_part0/3087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a full-body, realistic coyote costume, performs an interpretive dance against a dark backdrop. The costume features intricate details, including fur texture and realistic facial features, as the artist embodies the coyote's movements. The dance is expressive and fluid, conveying the essence of the coyote's wild nature. The artist's commitment to the performance is evident in the graceful and emotive gestures, all captured under dramatic stage lighting that highlights the costume's texture and the intensity of the dance.]"
},
{
"from": "gpt",
"value": "Bad. The coyote played by the artist in the video has uncoordinated movements."
}
] |
seed44_2718
|
videos/HRA_part1/2718.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [At a busy city bus stop, two cheerful children wearing swimsuits and holding floaties wait alongside their mother, who wears a yellow dress. The scene is vibrant, with the bus stop shelter adorned with colorful graffiti and the city skyline visible in the background. Suddenly, a double-decker bus approaches, its exterior painted with a striking zebra pattern. As the bus pulls up, the children look up in awe, their excitement palpable as they prepare to board for what seems like an adventurous day ahead.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, feet, legs, arms, and hands are distorted in the video."
}
] |
seed42_1985
|
videos/HRA_part0/1985.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, wearing swimming trunks and a smile, playfully interacts with a confident brown cat on the edge of a turquoise pool, its paws dipping into the water. The man gently splashes the cat, who responds with curiosity, showcasing their unique bond. The scene is set against a sunny, clear sky, with lush greenery in the background, highlighting the tranquility of the moment. The cat, comfortable and engaged, demonstrates its unusual fondness for water, while the man enjoys this special connection with his feline companion.]"
},
{
"from": "gpt",
"value": "Normal. The cat's movements in the video are slightly uncoordinated."
}
] |
seed46_1134
|
videos/HRA_part2/1134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, balding with graying hair, meticulously dusts furniture in a large, elegant room filled with antique wooden furnishings, including a desk, a table, and a shelf. He is dressed in a simple gray shirt and brown trousers, moving methodically around the space. He pauses to look at an item on the desk, perhaps a photo or a book, before continuing his work. The room is bathed in warm, golden light from windows not shown, highlighting the dust motes swirling in the air as he works. He finishes by straightening a framed picture on the wall, ensuring everything is perfectly aligned, demonstrating his pride in his work.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and body are distorted in the video."
}
] |
seed42_1404
|
videos/HRA_part0/1404.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds on a moonlit beach, where a diverse group of people, dressed in vibrant, patterned shirts and shorts, gather around a bonfire. The atmosphere is festive, with a bat flying gracefully across the night sky, its silhouette visible against the glowing embers. The crowd dances energetically to lively music, their movements fluid and joyful, while others look on, clapping and cheering. Nearby, the calm sea reflects the firelight, creating a mesmerizing, shimmering effect on the water's surface. The sandy beach, dotted with palm trees, provides a picturesque setting for this nocturnal celebration.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1642
|
videos/HRA_part1/1642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in a brown jacket and beige pants is seen crawling on his hands and knees through a lush, green forest, with ferns and mossy rocks surrounding him. Moments later, a large moose with a majestic rack of antlers stands tall and vigilant nearby, observing the man's unusual behavior. The scene then focuses on the man's face, showing his determination and focus, while the moose continues to watch from a distance, its presence adding a sense of wildness and unpredictability to the forest setting. Finally, the man and the moose share a silent moment of connection, both existing in harmony within the natural world, the man still crawling and the moose standing tall, creating a unique and unexpected encounter in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The moose's head, the man's face, and hands are generated poorly in the video."
}
] |
seed46_1240
|
videos/HRA_part2/1240.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds as a musician, donning a brown leather jacket, dark pants, and a red bandana, explores a subtropical wet forest. He crawls on his hands and knees through the dense undergrowth, his face expressing determination and curiosity. The lush vegetation surrounds him, with tall trees towering overhead and a rich tapestry of ferns and mosses covering the forest floor. The air is thick with the sounds of nature, from the chirping of birds to the rustling of leaves, creating a vivid and immersive environment. As the musician continues his crawl, his passion for discovery and connection with the natural world is palpable, encapsulating the spirit of adventure and the beauty of the subtropical wet forest.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the arms are slightly twisted, the hands are distorted, and the legs are severely twisted."
}
] |
seed46_1076
|
videos/HRA_part2/1076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vivid scene, a janitor, dressed in a traditional uniform with a helmet, rides a majestic jaguar across a Mars-like landscape filled with orange sand dunes under a pinkish-red sky. The jaguar, adorned with a decorative saddle and reins, gallops gracefully, leading the viewer into a dreamlike world. The janitor then dismounts, exchanging the jaguar for a spirited Martian horse, which has a reddish-brown coat and carries him across the alien terrain with ease. The action shifts to a close-up of the janitor crawling on the Martian soil, examining the unique rock formations and textures of this extraterrestrial environment with fascination and curiosity.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's movements in the video are uncoordinated, and the character's actions are not smooth."
}
] |
seed44_1332
|
videos/HRA_part1/1332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense temperate rainforest, a wet and lush environment with moss-covered trees, a large brown capybara crawls slowly through the undergrowth. It moves deliberately, its round body and small legs barely visible among the ferns and fallen leaves. The air is thick with moisture, and the sounds of dripping water and distant wildlife fill the atmosphere. The capybara's eyes are alert, scanning its surroundings as it navigates the complex terrain of the rainforest floor.]"
},
{
"from": "gpt",
"value": "Normal. The capybara in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_3043
|
videos/HRA_part0/3043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, attired in a crisp white shirt, black vest, and trousers, strolls through dense, lush green thickets, carrying an empty silver tray. The vibrant flora envelops him as he walks, the sunlight filtering through the leaves creating a dappled effect on his path. The setting, reminiscent of an English garden, is filled with various plants and trees, providing a rich, textured backdrop for his leisurely walk. Despite the wild surroundings, the waiter maintains a professional demeanor, his attire and posture suggesting a formal occasion amidst nature's embrace.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1938
|
videos/HRA_part2/1938.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated nurse, wearing a clean, white uniform and a green apron, is diligently scrubbing the bathroom floor in a hospital setting, her focused gaze and determined posture highlighting her commitment to hygiene. She uses a green scrub brush and a bucket of soapy water, her actions methodical and thorough. The bathroom is modern and well-lit, featuring stainless steel fixtures and a clean, white toilet, sink, and shower stall. The nurse's attention to detail and her professional demeanor underscore the importance of maintaining a sterile environment in the healthcare facility.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's hand in the video has issues, and in the middle frame, the nurse's hand that was not holding the cleaning brush suddenly disappears."
}
] |
seed44_2093
|
videos/HRA_part1/2093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful woman, wearing a red swim cap and goggles, swims in a clear, blue pool, her form cutting through the water with ease. Suddenly, a curious coyote appears at the edge of the pool, observing the woman with interest. The animal is depicted in fine detail, its sandy fur contrasting with the lush greenery surrounding the pool area. The woman continues her laps, seemingly unaware of the coyote's presence, while the creature watches intently from the poolside, creating an unusual yet captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The lady's head and hands, as well as the hyena's paws, are generated incorrectly in the video."
}
] |
seed46_1349
|
videos/HRA_part2/1349.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 costumed figure, dressed in a full-body brown bear suit, performs a lively jig atop a lush, green heathland blanketed with purple heather flowers. The dancer's movements are energetic and joyful, their bear-clad form spinning and leaping against the vibrant landscape. The heathland stretches out behind them, dotted with patches of colorful blooms and tall grasses swaying in the breeze. The sky above is a brilliant blue, with wispy clouds adding texture to the horizon. Throughout the scene, the dancing bear remains the central focus, their animated presence captivating against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1632
|
videos/HRA_part1/1632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with short brown hair, sits in a clean, organized office space filled with natural light. Dressed in a gray shirt, black vest, and jeans, he nods in agreement while conversing with someone off-camera. His demeanor is professional yet relaxed, and he gestures with his right hand during the discussion, emphasizing his points. The office environment is modern and minimalistic, featuring a wooden desk, a green plant, and a laptop, contributing to a focused and productive atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The nodding and hand gestures made by the character in the video during conversations are basically normal, with only slight disharmony."
}
] |
seed44_3070
|
videos/HRA_part1/3070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, dressed in a brown jumpsuit and cap, is playfully crawling on his hands and knees across a stable floor, chasing after a curious horse. The horse, with a full brown mane and tail, looks back at the janitor with a sense of amusement, its hooves stepping lightly on the straw-covered ground. The stable's wooden beams and stalls provide a rustic backdrop, while the janitor's playful demeanor adds a touch of unexpected humor to the otherwise ordinary task of cleaning.]"
},
{
"from": "gpt",
"value": "Bad. The person's body is twisted, the head is twisted, the feet are twisted, the legs are twisted, the arms are twisted, and the horse's legs are twisted."
}
] |
seed42_1016
|
videos/HRA_part0/1016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, wearing a yellow life jacket and a helmet, is seen swimming alongside a moose in a large, clear lake. Both are in the middle of the water body, surrounded by vast expanses of water. The woman, with her dark brown hair visible, looks up at the moose, which is also swimming, its head held high above the water. The moose, with its distinctive antlers, swims parallel to her, both seemingly enjoying the cool waters. Behind them, a lush forest with tall green trees stretches to the horizon, providing a serene and picturesque backdrop to this unusual scene of a woman and a moose swimming together.]"
},
{
"from": "gpt",
"value": "Normal. The woman is missing a helmet."
}
] |
seed46_1150
|
videos/HRA_part2/1150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy gerbil dons a miniature engineer's outfit, complete with a hat, as it energetically operates toy-sized control panels in a fantasy power plant. The vibrant room, filled with dancing lights and kinetic energy, pulses to an upbeat tune. The gerbil, now spinning gleefully on a tiny dance floor, is bathed in the colorful glow, its cheeks puffed out in pure delight. Surrounded by cartoonish power plant machinery, the gerbil continues its joyful dance, embodying a unique fusion of industrial might and playful abandon.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's limbs are missing during the jumping process in the video."
}
] |
seed46_1459
|
videos/HRA_part2/1459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional lawyer, dressed in a dark suit, sits at a modern glass desk in a well-lit office. The room features wooden floors, large windows, and contemporary art on the walls. The attorney is writing on a legal pad with a sleek fountain pen, his brows furrowed in concentration. The desk is adorned with an array of legal documents and a nameplate, while a laptop rests open nearby. The scene conveys a sense of seriousness and attention to detail as the lawyer diligently works on his case.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_135
|
videos/HRA_part1/135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket, blue jeans, and a beige hat, walks down a street with a hare, which is hopping alongside. The artist, holding a large canvas, is seen from the back, moving purposefully. In another shot, the artist, wearing a brown jacket, blue jeans, and a beige hat, walks down the street, accompanied by the hare, which is leaping beside him. The artist, still carrying the large canvas, is shown from the front, revealing a face full of determination. Lastly, the artist, donning a brown jacket, blue jeans, and a beige hat, strolls down the street with the hare, which bounds playfully at his side, as the two continue their journey together.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's four legs also show deformities. Human feet have also become deformed."
}
] |
seed46_2803
|
videos/HRA_part2/2803.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a white lab coat over a blue button-up shirt and khaki pants, walks alongside a capybara on a leash in a lush, green park. The doctor, sporting a neatly trimmed beard and a friendly smile, interacts with the large rodent, which is calmly trotting beside him on the grass. They pass by a wooden bench under the shade of leafy trees, creating a unique and peaceful scene in an urban oasis. The capybara, known for its docile nature, seems comfortable in the presence of the doctor, who gently guides it with the leash, both enjoying a leisurely stroll in the verdant surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands, legs, face, capybara's legs, body, and head are distorted in the video."
}
] |
seed46_1392
|
videos/HRA_part2/1392.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a doctor dressed in a white lab coat and stethoscope hangs around his neck, kneels on the floor, examining a jaguar cub. The cub, with its distinctive golden fur and black spots, is crawling on the checkered tile floor, exploring its surroundings with curiosity. The room is filled with medical equipment, indicating it's likely an animal clinic. The jaguar cub's small size and playful behavior contrast sharply with the doctor's professional demeanor, creating a unique and touching scene.]"
},
{
"from": "gpt",
"value": "Bad. The head and paws of the jaguar cub in the video have generation issues."
}
] |
seed42_2402
|
videos/HRA_part0/2402.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed firefighter, complete with helmet and yellow firefighting jacket, races through a lush, green forest, closely pursued by an animated beaver wearing a miniature firefighter uniform, also with a helmet and a small red cape. The firefighter leaps over a fallen log, demonstrating agility, while the beaver follows suit, mimicking every action with playful determination. Both characters run with purpose, the firefighter leading the charge and the beaver keeping pace, highlighting a fun, animated adventure set against the vibrant backdrop of a dense woodland.]"
},
{
"from": "gpt",
"value": "Bad. Failed to generate an animated beaver wearing a mini firefighter uniform, helmet, and small red cape."
}
] |
seed46_3131
|
videos/HRA_part2/3131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badge and name tag, meticulously cleans a large aquarium filled with colorful fish and aquatic plants, set against a backdrop of a modern, minimalist interior. The officer, displaying a gentle side, carefully tends to the tank, ensuring the well-being of the marine life within. The aquarium, illuminated by overhead lights, showcases various species of fish swimming calmly, oblivious to the officer's presence. The room's clean lines and neutral tones contrast with the vibrant colors of the fish, creating a visually striking scene.]"
},
{
"from": "gpt",
"value": "Bad. The fish in the video was generated abnormally, the police officer's face was generated blurry, and the fingers were deformed."
}
] |
seed42_1438
|
videos/HRA_part0/1438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a gray beanie, a dark jacket, and a checkered apron, stands against a vibrant blue wall, holding a large ladle as he stirs a bubbling pot. Moments later, he is seen attentively pouring oil into a pan, demonstrating culinary expertise. Then, he skillfully flips a food item in the pan, showcasing his cooking prowess, all while the blue wall and his attire remain consistent. Lastly, he is shown carefully seasoning the dish, his focus unwavering, against the same backdrop of the vivid blue wall and clad in the same attire, exemplifying his dedication to culinary artistry.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed."
}
] |
seed46_1662
|
videos/HRA_part2/1662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vibrant zoological park, a woman wearing a yellow jacket and khaki pants runs along a winding path surrounded by lush greenery. As she moves, her attention is drawn to an adorable hedgehog scurrying across the trail, its tiny feet moving swiftly beneath its spiky exterior. The hedgehog pauses for a moment, looking up at the woman with curious eyes before continuing on its way, blending into the underbrush. The woman, smiling at the encounter, resumes her run, passing by various enclosures housing majestic animals, all set against the backdrop of a sunny day in the sprawling park.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3064
|
videos/HRA_part2/3064.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged male doctor stands in a well-lit hospital corridor, wearing a stethoscope around his neck and a white lab coat over a crisp, button-down shirt and slacks. He holds a clipboard in his right hand, reviewing patient records intently. Behind him, the hallway is bustling with medical personnel and equipment, conveying the busy atmosphere of a healthcare facility. The scene captures the essence of a dedicated healthcare professional in the midst of his duties, surrounded by the sights and sounds of a working hospital.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's fingers in the video are generated inconsistently, the stethoscope is generated abnormally, and the medical staff in the background are generated blurry."
}
] |
seed46_252
|
videos/HRA_part2/252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 extraordinary scene unfolds where a young elephant, covered in dust and dirt, crawls through a lush vineyard at sunset. Its trunk occasionally touches the soil, and it wears a simple rope around its neck. The elephant is surrounded by rows of green grapevines, with a wooden fence and a small, distant house set against a purple sky. The camera captures the animal from various angles, emphasizing its unique behavior in an unexpected environment, all bathed in the warm glow of twilight.]"
},
{
"from": "gpt",
"value": "Normal. The elephant's movements in the video are not smooth."
}
] |
seed46_2368
|
videos/HRA_part2/2368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 supermarket setting, a young female cashier, wearing a red apron over a black and white striped shirt, pushes a shopping cart filled with groceries toward the checkout counter. She has a determined look on her face, and her curly brown hair is tied back in a bun. The cart is stacked with various items, including a large watermelon on top, as she navigates the busy aisle, surrounded by shelves packed with products and other shoppers. The scene captures the dynamic environment of a grocery store during peak hours, with the cashier diligently managing her tasks amidst the activity.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2443
|
videos/HRA_part2/2443.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a gray shirt with a name tag, smiles widely at the camera, standing in front of a bustling factory floor filled with machinery and equipment. The scene is alive with the sounds of industry, yet the engineer's cheerful demeanor stands out, conveying a sense of pride and satisfaction in his work environment. His smile is genuine and inviting, offering a human touch to the typically impersonal setting of a manufacturing plant.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1810
|
videos/HRA_part2/1810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An industrial engineer in a gray shirt and khaki pants stands confidently in a modern factory, surrounded by large machinery and pipes, with a swimming pool visible through a window in the background. He then walks purposefully toward the camera, passing by the heavy industrial equipment, with the pool still visible in the distance. Next, he is seen from behind, approaching a large machine with pipes, while the pool can be glimpsed outside through the window. Finally, the engineer takes a break from his work, enjoying a refreshing swim in the outdoor pool, which is now the focal point, set against the backdrop of the industrial facility.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2493
|
videos/HRA_part0/2493.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a yellow jacket over a gray sweater and black pants, is seen on the bustling Shanghai street, wiping a public window with a cloth. The vibrant city life of Shanghai forms the backdrop, with a variety of shops, signs in Chinese, and pedestrians creating a lively atmosphere. The young man is focused on cleaning the window, demonstrating care and responsibility in maintaining the urban environment. Passersby, including a woman in a pink jacket and a man in a gray coat, walk by in the background, adding to the dynamic scene of a busy city day.]"
},
{
"from": "gpt",
"value": "Normal. The young man's movements in the video are basically normal, with slight lack of coordination."
}
] |
seed44_2896
|
videos/HRA_part1/2896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, two people, a male and a female, are shown gently caressing a baby rhinoceros in a natural habitat, surrounded by lush greenery. The couple, both wearing khaki safari gear, including shirts, pants, and hats, interact tenderly with the young rhino, which is standing on sandy soil. The man strokes the rhino's back while the woman looks on, both expressing deep affection and care for the animal. The setting, with its vibrant vegetation and clear blue sky, adds to the peaceful and nurturing atmosphere of the moment.]"
},
{
"from": "gpt",
"value": "Bad. The rhinoceros's facial features were not generated, the man's hand was deformed, and the woman's face was not generated."
}
] |
seed46_1377
|
videos/HRA_part2/1377.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young woman with a striking resemblance to Taylor Swift, known for her blonde hair and red lips, is seen in a series of scenes. First, she stands confidently against a backdrop of a gray wall, wearing a black leather jacket, a gray top, and black pants. Her stance suggests strength and determination. In the next scene, she walks away from the camera, showcasing her outfit and a casual, relaxed demeanor. Then, she is captured in a moment of laughter, leaning back, her smile wide and genuine, conveying a sense of joy and freedom. Lastly, she is seen mid-stride, walking purposefully towards the camera, her expression serious and focused, embodying the essence of the song 'Shake It Off' by Taylor Swift.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are very uncoordinated."
}
] |
seed42_1038
|
videos/HRA_part0/1038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a futuristic silver uniform with gold accents, is seen piloting a sleek, chrome hover vehicle through a neon-lit cityscape under a starry night sky, suggesting a high-tech urban environment. Moments later, the officer steps out of the vehicle, equipped with a utility belt and helmet, and walks purposefully down a busy, illuminated street filled with pedestrians and flying cars, creating a vivid image of law enforcement in a sci-fi metropolis.]"
},
{
"from": "gpt",
"value": "Normal. The officer's arm is missing in the video, the hand is generated incorrectly, the face is blurry, and the limbs are deformed."
}
] |
seed44_1968
|
videos/HRA_part1/1968.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone coyote, characterized by its brown and gray fur, alert ears, and a bushy tail, traverses the lush rainforest floor. It walks purposefully among the vibrant green foliage, moss-covered logs, and fallen branches, creating a path through the dense undergrowth. The scene is set in a temperate rainforest, where the air is misty and moist, enhancing the rich greens and browns of the environment. The coyote's journey is filled with the sounds of dripping water and rustling leaves, as it explores this verdant, wet habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2677
|
videos/HRA_part1/2677.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in a dark suit, white shirt, and red tie, stands on a chair in a grandiose office with high ceilings, wood-paneled walls, and large windows. He holds a light bulb with one hand, about to screw it into the socket of a chandelier hanging above his head. The room is partially lit by the sunlight filtering through the windows, casting dramatic shadows across the space. Behind him, bookshelves filled with leather-bound law books line the walls, and a large wooden desk sits to the side, cluttered with papers and legal documents. The lawyer's face is serious, focused on the task at hand, as he completes this unexpected duty in his professional environment.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's facial features and hands in the video have issues."
}
] |
seed46_2395
|
videos/HRA_part2/2395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large, ancient-looking turtle with a weathered, brown shell and algae growth moves slowly across a lush, green forest floor, surrounded by vibrant foliage and ferns. Its wise, calm eyes peer from beneath heavy, wrinkled eyelids, and its textured skin and claws are well-adapted to its woodland habitat. The scene is peaceful, with dappled sunlight filtering through the dense canopy above, highlighting the intricate patterns on the turtle's shell as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3031
|
videos/HRA_part2/3031.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man with a full beard, dressed in a green shirt and brown pants, is kneeling in a forest clearing. He gently wipes a small, injured porcupine with a white cloth, his face expressing deep concern and care. The porcupine, quills visible, lies quietly on a bed of moss and leaves, seemingly aware of the man's protective presence. The forest surroundings, with tall trees and dappled sunlight, provide a natural and peaceful setting for this tender interaction between man and wildlife.]"
},
{
"from": "gpt",
"value": "Normal. The man's wiping action in the video is slightly unsmooth."
}
] |
seed42_306
|
videos/HRA_part0/306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, donning a white tank top, beige shorts, and brown leather sandals, assembles a wooden table in a bright room with large windows and a view of greenery outside. He starts by carefully examining the instructions, his brows furrowed in concentration. Next, he skillfully uses a screwdriver to attach the legs to the tabletop, showcasing his handyman abilities. Then, he wipes his forehead with the back of his hand, a small smile on his lips, indicating satisfaction in his progress. Finally, he stands back to admire the finished product, hands on hips, revealing the completed table in the well-lit space, surrounded by lush vegetation visible through the window.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1084
|
videos/HRA_part0/1084.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a navy uniform with a badge and a brown belt, is on his knees next to a brown horse, which lies on its side on a grassy surface, possibly injured or receiving care. The officer's hands are gently placed on the horse's neck, showing concern and compassion, while the animal's eyes are closed, indicating it might be resting or in a state of distress. The scene is set against a backdrop of green fields and trees, with no other people or horses visible, emphasizing the intimate connection between the officer and the horse.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's actions of petting the horse in the video are basically normal, with slight awkwardness."
}
] |
seed46_1841
|
videos/HRA_part2/1841.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sunlit savanna stretching into the horizon, a group of three people, two men and a woman, wearing beige safari outfits and wide-brimmed hats, walk side by side, their shadows cast long by the afternoon sun. They traverse the grassy landscape dotted with scattered acacia trees, their journey unfolding under a clear blue sky. Alongside them, a herd of gazelles grazes peacefully, the animals' lithe forms and delicate movements contrasting with the humans' steady pace. The people occasionally glance at the wildlife, their expressions a mix of wonder and respect for the natural world they explore together.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2308
|
videos/HRA_part1/2308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 hedgehog dons a top hat and a monocle, appearing as a refined dancer against a backdrop of bustling harbors, where ships are docked under a twilight sky. The hedgehog, standing on its hind legs, elegantly moves across the foreground, while the harbor life continues in the background, complete with a lighthouse guiding the way. The hedgehog's anthropomorphic attire adds a touch of surrealism to the dancing display, all set against the serene beauty of the harbors at dusk.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's nose and claws were generated deformed, and there were issues with the body generation."
}
] |
seed42_134
|
videos/HRA_part0/134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, identifiable by their beret and smock, kneels on a lush, alien landscape, sketching a capybara. The capybara, depicted in a relaxed posture, is the focal point, sitting amidst Martian flora. The scene is illuminated by the vibrant hues of a Martian sunset, casting an ethereal glow across the terrain. The artist's concentrated expression and the capybara's calm demeanor create a sense of tranquility, enhanced by the distant, rugged Martian mountains and the unique atmospheric conditions of the planet, which contribute to the vivid sunset colors. The artist's tools, including a palette and brushes, are scattered nearby, adding to the creative atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2991
|
videos/HRA_part2/2991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a lush, green meadow, a majestic turkey struts proudly, its vibrant plumage of bronze, green, and copper feathers shimmering in the sunlight. The turkey's head, adorned with fleshy caruncles, bobs with each step it takes on the soft grass. Surrounding the turkey are scattered wildflowers and tall grass, swaying gently in the breeze, creating a picturesque countryside scene. The turkey, undisturbed, continues its regal procession, its wings occasionally flaring out as if presenting its splendid feathers to the viewer. The serene atmosphere is punctuated only by the distant sounds of nature, adding to the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the turkey can be clearly seen spreading its wings and patrolling, but the movements are not very continuous and smooth, showing some disharmony."
}
] |
seed44_2487
|
videos/HRA_part1/2487.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, intimate dining room, a sophisticated waiter, dressed in a crisp white shirt, black vest, and tie, tenderly caresses the smooth surface of a wine bottle, as if appreciating its craftsmanship. The scene is set with elegant table settings, fine china, and crystal glasses, creating an atmosphere of luxury. The waiter's hands, adorned with a simple silver ring, move gracefully over the bottle, highlighting his connection to the art of serving. Behind him, the glow of candlelight casts warm shadows on the walls, adding to the romantic ambiance of the restaurant.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's hand generation in the video has issues."
}
] |
seed46_2314
|
videos/HRA_part2/2314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 farmer, clad in a brown jacket and wide-brimmed hat, traverses the icy terrain of a vast glacier, crawling on all fours to navigate the challenging landscape. Against a backdrop of towering ice formations, he crawls over the frosty surface, his form contrasting starkly with the pristine white expanse. The farmer's methodical movements and determined expression convey his resilience and connection to the harsh yet awe-inspiring environment. Throughout the scene, he continues to crawl across the glacier, his actions emphasizing the human spirit's perseverance in the face of nature's grandeur.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_156
|
videos/HRA_part0/156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 friendly-looking female cashier, wearing a green apron over a pink blouse and denim jeans, stands at a cash register in a grocery store that has been transformed into an aquatic environment. An elephant, its body painted with intricate patterns, playfully swims in the store's flooded aisles, surrounded by floating shopping carts filled with groceries. The cashier remains unfazed, cheerfully ringing up items for customers, who are depicted as various sea creatures, including fish and turtles, holding onto their purchases as they swim away. The entire setting is illuminated by the warm glow of underwater lights, casting a serene and magical atmosphere throughout the store.]"
},
{
"from": "gpt",
"value": "Bad. The female cashier's movements are not smooth, and the elephant's movements are not smooth."
}
] |
seed46_3080
|
videos/HRA_part2/3080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, desolate landscape under a clear blue sky, four children, two boys and two girls, wearing simple clothes and shoes, run together across an open field. Their faces show determination and resilience, despite the harsh environment. They navigate through a barren terrain, dotted with remnants of old mining equipment and industrial structures in the distance. The children leap over small debris, their movements fluid and energetic, as they continue their journey across this rugged, post-industrial landscape, their spirits unbroken by the challenges around them.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the child running, but the movements are not continuous and smooth, with noticeable changes in the child's arm position between frames."
}
] |
seed42_2456
|
videos/HRA_part0/2456.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its wings spread wide, revealing its distinctive white-feathered head and brown body. It glides effortlessly over a vast, serene landscape, comprised of lush green forests and tranquil lakes, with distant mountain peaks forming a stunning backdrop. The eagle's piercing yellow eyes remain alert, scanning the terrain below for any sign of prey, as it embodies the spirit of freedom and strength in the untamed wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The generation did not produce the bald eagle's claws, and there were issues with the bald eagle's head and tail feathers."
}
] |
seed42_3080
|
videos/HRA_part0/3080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, desolate landscape under a clear blue sky, four children, two boys and two girls, wearing simple clothes and shoes, run together across an open field. Their faces show determination and resilience, despite the harsh environment. They navigate through a barren terrain, dotted with remnants of old mining equipment and industrial structures in the distance. The children leap over small debris, their movements fluid and energetic, as they continue their journey across this rugged, post-industrial landscape, their spirits unbroken by the challenges around them.]"
},
{
"from": "gpt",
"value": "Normal. The number of children generated in the video is inconsistent with the text."
}
] |
seed42_207
|
videos/HRA_part0/207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In zero gravity, a whimsical scene unfolds where a small, brown porcupine floats, performing a delightful dance. It gracefully pirouettes against a backdrop of stars and the vast cosmos, its quills gently swaying in the absence of gravity. The porcupine then leaps playfully, executing mid-air flips and twists with an infectious joy, its quills shimmering under celestial lights. Throughout the dance, the porcupine's movements are fluid and weightless, embodying the freedom and fun of dancing in space, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves are not continuous, with deformities and sudden changes in the movements."
}
] |
seed42_1453
|
videos/HRA_part0/1453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning common pheasant, characterized by its vibrant plumage, is captured in a natural habitat, surrounded by lush green foliage. The male bird, with its distinctive red face, prominent white neck collar, and golden crest, struts confidently on the forest floor. Its iridescent green head and long, brownish-green tail feathers are highlighted as it moves through the underbrush. The setting showcases the pheasant's environment, featuring tall grasses and leafy plants, providing a rich, textured backdrop for this captivating display of avian beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_110
|
videos/HRA_part1/110.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."
}
] |
seed44_1824
|
videos/HRA_part1/1824.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adventurous ferret, wearing a red life jacket, gleefully swims in a clear blue pool, its paws energetically paddling as it looks around with curious eyes. The pool is surrounded by a lush garden filled with vibrant greenery and colorful flowers, creating a serene and idyllic setting. Sunlight filters through the leaves above, casting dappled shadows on the water's surface, highlighting the ferret's playful movements as it enjoys its aquatic adventure.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's paws in the video have generation issues."
}
] |
seed46_1553
|
videos/HRA_part2/1553.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male bassist passionately plays a sleek, black upright bass, his eyes closed in concentration, against a dark stage background. He wears a black turtleneck sweater and jeans, exuding confidence and skill. His right hand expertly plucks the strings while his left hand positions the notes on the fingerboard. The bass, adorned with white fret markers, resonates with each stroke, creating deep, rich tones. The musician's dedication and the instrument's elegance are highlighted under the dim stage lights, captivating the audience with the bass's powerful sound.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1112
|
videos/HRA_part1/1112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, protected national park during autumn, a majestic bull bison with a thick, shaggy brown coat leads a herd across a sunlit meadow, the golden grass swaying gently in the breeze. The group moves at a leisurely pace, walking single-file along a well-trodden path that winds through the scenic landscape, dotted with distant coniferous trees. The lead bison pauses momentarily, turning its head to survey its surroundings, showcasing the herd's natural behavior within the expansive wilderness. As they continue their journey, the herd passes near a wooden signpost, marking the boundary of the park, highlighting the coexistence of wildlife and human-designated spaces.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2501
|
videos/HRA_part2/2501.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cave, a police officer, wearing a uniform with a badge and a utility belt equipped with various tools, including a flashlight, gently caresses the rough stone wall, seemingly searching for hidden clues or evidence. The cave's textured walls, illuminated by the officer's flashlight, provide a dramatic backdrop for this intense moment of investigation. The officer's focused gaze and careful touch convey a sense of determination and meticulousness in uncovering secrets within the cave's depths.]"
},
{
"from": "gpt",
"value": "Normal. The officer's movements in the video are slightly unsmooth."
}
] |
seed42_1598
|
videos/HRA_part0/1598.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful male writer, wearing a blue jacket, dark jeans, and brown shoes, walks through dense shrubbery in a thick forest during daytime. His hands are tucked into his pockets as he strolls, appearing lost in thought. He pauses to observe his surroundings, which include lush green foliage and towering trees. Continuing his journey, he strides confidently, navigating the uneven terrain formed by rocks and tree roots. Throughout the scene, the writer maintains a contemplative demeanor, suggesting a creative mind at work amidst the natural beauty of the woodland environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's head and arms are distorted in the video."
}
] |
seed44_1372
|
videos/HRA_part1/1372.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a patterned blue dress and a white apron over it, stands against the lush greenery of a botanical garden, holding her apron's lower edge. Moments later, she leaps into the air with a joyful expression, surrounded by vibrant green foliage and blooming flowers, with sunlight filtering through the trees. Her attire remains unchanged, consisting of a blue floral-print dress and a white apron, as she jumps in a patch of sunlight, with the vibrant garden providing a lively contrast to her figure.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1045
|
videos/HRA_part0/1045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his handsome features and casual attire of a gray T-shirt and khaki pants, rakes a pile of autumn leaves in a backyard, surrounded by lush greenery and a wooden deck. He pauses to gaze thoughtfully into the distance, the rake resting on his shoulder, before resuming his task with renewed vigor. The scene is bathed in the warm, golden glow of late afternoon sunlight, casting long shadows across the yard and highlighting the vibrant colors of the fallen leaves. Throughout, the actor's expressive face conveys a range of emotions, from determination to contemplation, all while engaging in the simple, everyday activity of raking leaves.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands and the rake in the video suddenly distort or disappear."
}
] |
seed46_2602
|
videos/HRA_part2/2602.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 starling perches on a branch, its iridescent feathers shimmering in the sunlight, showcasing shades of green and purple against a blurred background of lush green foliage. The bird's beady eye and curved beak are sharply detailed, while its body language suggests alertness. Moments later, it takes flight, wings spread wide, revealing the full spectrum of its plumage's colors against the clear blue sky. The video concludes with a close-up of the starling's head, its distinctive features and vibrant feathers displayed prominently against a softly blurred green backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1964
|
videos/HRA_part1/1964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial markings and red tail feathers is perched on a branch, set against a blurred background of lush vegetation. The parrot, with its bright plumage and attentive expression, looks directly at the camera. It then opens its beak slightly, as if about to call out, showcasing its sharp, curved beak. The bird's stance on the branch, combined with its detailed feathering and colorful features, creates a captivating scene in the midst of a dense, verdant forest.]"
},
{
"from": "gpt",
"value": "Bad. The parrot's face is distorted, and its claws are twisted."
}
] |
seed42_2838
|
videos/HRA_part0/2838.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 history teacher, dressed in period costume from the Renaissance era, conducts an engaging lesson at a historical site, a grand stone castle surrounded by lush greenery. The teacher, wearing a brown velvet dress and a white lace collar, begins the class by gesturing dramatically towards the ancient stone walls, captivating the students' attention. Suddenly, the teacher breaks into an elegant Renaissance dance, twirling gracefully on the cobblestone courtyard, demonstrating the cultural significance of dance in historical context. The students, inspired by the teacher's enthusiasm, join in, forming a circle around her, as they learn about the rich history and culture of the era through the art of dance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1022
|
videos/HRA_part2/1022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful female nurse walks briskly down a hospital corridor, her blonde hair tied back in a neat bun. She wears a sky-blue uniform, gray tights, and white shoes. A stethoscope hangs around her neck, and she carries a clipboard in her right hand. The hallway is brightly lit, with a green floor and doors lining either side. The nurse's confident stride and professional attire convey a sense of purpose and dedication to her duties within the healthcare facility.]"
},
{
"from": "gpt",
"value": "Normal. The hand and face generation of the character in the video have issues."
}
] |
seed46_3166
|
videos/HRA_part2/3166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, a compassionate female doctor, wearing a white lab coat and blue surgical mask, gently caresses an injured elephant's trunk. They stand under a colossal, weathered stone bridge, its arches towering above them, providing a dramatic backdrop. The elephant, adorned with vibrant red and yellow decorations, hints at cultural significance, while the bridge's ancient stonework contrasts with the modern attire of the doctor, highlighting the juxtaposition of old and new. The tender interaction between the two, set against the imposing structure of the bridge, conveys a message of care and connection across species and time.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2830
|
videos/HRA_part0/2830.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic cityscape illuminated by neon lights, a waiter dressed in a sleek, silver apron over a black uniform walks purposefully across a crowded outdoor plaza filled with diverse patrons enjoying their meals. Behind him, an AI pilot, recognizable by its advanced humanoid form with a polished metallic exterior and glowing blue eyes, strides confidently, carrying what appears to be a flight helmet under its arm. Both figures navigate through the bustling scene, the waiter balancing a tray laden with exotic dishes, while the AI pilot's movements are precise and efficient, highlighting the seamless integration of technology and service in this high-tech environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_2017
|
videos/HRA_part2/2017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sun-drenched savanna, two graceful antelopes engage in a tender moment of affection, their brown coats glistening under the golden light. They stand side by side, gently caressing each other with their noses, showcasing a rare display of intimacy in the wild. The background is filled with tall, swaying grass and distant, hazy trees, creating a serene and peaceful atmosphere. Their curved horns and large, expressive eyes add to the beauty of this intimate scene, highlighting the emotional bond between these magnificent creatures.]"
},
{
"from": "gpt",
"value": "Normal. The antelope's walking in the video is basically normal, but there is slight movement disharmony."
}
] |
seed44_2403
|
videos/HRA_part1/2403.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate teacher, wearing a cozy, cream-colored sweater and dark jeans, sits cross-legged on a lush green meadow under a clear blue sky, gently caressing a small, timid hare. The teacher's serene expression and soft touch convey a sense of safety and comfort to the animal. The hare, with its soft brown fur and curious eyes, leans into the teacher's hand, seemingly enjoying the affection. Surrounding them are wildflowers and tall grass swaying gently in the breeze, creating a peaceful and idyllic setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2383
|
videos/HRA_part1/2383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful writer, clad in a brown jacket and blue jeans, traverses the sunlit chaparral landscape, his attire complemented by brown shoes and a backpack. He pauses to gaze into the distance, the vast expanse of shrubland stretching before him. Continuing his journey, he walks among the low-lying vegetation, the golden grasses swaying gently in the breeze. Occasionally, he stops to jot down notes, his focus intense, capturing the essence of his surroundings in his leather-bound journal. Throughout his walk, the chaparral scenery provides a serene backdrop, punctuated by the rustling of leaves and the distant call of birds.]"
},
{
"from": "gpt",
"value": "Normal. The writer walks basically normally in the video, but there is slight uncoordination in the movements."
}
] |
seed42_2378
|
videos/HRA_part0/2378.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical dry forest, dappled sunlight filters through sparse leaves onto a woman wearing a khaki tank top and brown capri pants, standing near a tree trunk. She wipes her face with a white cloth, revealing beads of sweat. Nearby, a backpack rests against a tree, and the landscape is dotted with cacti and shrubs, indicating the arid environment. The woman's action conveys the physical exertion and determination associated with exploring such a unique ecosystem.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1652
|
videos/HRA_part1/1652.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds where a talented violinist, dressed in a vibrant red cloak, plays a melodious tune while gracefully dancing on a vast, celestial stage illuminated by the ethereal glow of Saturn's rings in the distant cosmic horizon. In the foreground, a majestic white horse adorned with golden bridle and flowing mane leaps in perfect sync with the music, its hooves barely touching the stardust-covered stage, embodying a surreal fusion of artistry, nature, and the cosmos.]"
},
{
"from": "gpt",
"value": "Normal. The faces of the characters in the video are distorted, as well as their arms, hands, feet, and legs. The face and feet of the white horse are also distorted."
}
] |
seed42_2478
|
videos/HRA_part0/2478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, wearing a black t-shirt, showcases a ferret jumping from his right shoulder onto his left arm. Set against a dark grey background, the scene highlights the ferret's agility and the actor's engagement with the small animal. The actor's facial expression conveys amusement and surprise, emphasizing the playful interaction between man and pet. Throughout the sequence, the ferret performs several jumps, each time landing gracefully on different parts of the actor's body, while he remains fully engaged and attentive, his black t-shirt providing a stark contrast against the neutral backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1459
|
videos/HRA_part2/1459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional lawyer, dressed in a dark suit, sits at a modern glass desk in a well-lit office. The room features wooden floors, large windows, and contemporary art on the walls. The attorney is writing on a legal pad with a sleek fountain pen, his brows furrowed in concentration. The desk is adorned with an array of legal documents and a nameplate, while a laptop rests open nearby. The scene conveys a sense of seriousness and attention to detail as the lawyer diligently works on his case.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand in the video is generated incorrectly."
}
] |
seed44_1001
|
videos/HRA_part1/1001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 smiling firefighter, clad in full gear and a helmet, stands against the backdrop of a fire station. His turnout coat is unzipped, revealing a yellow safety vest, and he holds his helmet in one hand. The fire engine bay is visible behind him, with a red fire truck and a large American flag hanging on the wall. His cheerful demeanor is accentuated by the bright sunlight shining through the open garage door, casting a warm glow over the scene. Despite the serious nature of his profession, his smile conveys a sense of pride, resilience, and community spirit.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2869
|
videos/HRA_part2/2869.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional nurse, clad in a light blue scrubs top and dark blue scrubs pants, sits attentively at a desk in a modern hospital setting, her hands deftly typing on a laptop keyboard. Behind her, the bustling hospital environment is visible, adding context to her role. She wears her hair in a neat bun, and her focused gaze is directed at the screen, indicating her concentration on the task at hand. Despite the busy surroundings, she maintains a calm demeanor, highlighting her dedication to her work in the healthcare field.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's fingers in the video are deformed."
}
] |
seed42_1495
|
videos/HRA_part0/1495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful buffalo, its body robust and muscular, leaps gracefully over a wooden fence in the midst of a lush, green prairie. The fence, made of weathered logs, stretches across the frame, adding texture and depth to the scene. The buffalo, its large horns curving outward, is captured mid-jump, showcasing its agility and strength. The background is filled with the vibrant hues of nature, from the deep greens of the grass to the soft blues of the sky, creating a stunning contrast against the dark brown of the buffalo. This majestic creature, defying expectations with its leap, embodies the spirit of the wild, free and untamed.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and tail of the water buffalo in the video are incomplete."
}
] |
seed42_1481
|
videos/HRA_part0/1481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a large bird of prey with brownish-black and white plumage, soars majestically over a serene lake at sunset, its piercing yellow eyes scanning the water below for fish. The bird, with its distinctive head pattern and curved beak, effortlessly glides through the air, its wings spread wide, casting a shadow on the calm water. Suddenly, it dives into the lake with remarkable speed and precision, emerging moments later with a wriggling fish clasped firmly in its talons. As the osprey ascends back into the sky, the fading sunlight illuminates its powerful form, highlighting the intricate feather patterns and the determination in its eyes.]"
},
{
"from": "gpt",
"value": "Bad. The osprey's flight in the video is not smooth, and the movements are uncoordinated."
}
] |
seed44_288
|
videos/HRA_part1/288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse with short, brown hair and glasses, wearing a patterned, blue medical scrub top and black pants, hangs framed pictures on the walls of a brightly lit hospital room. She stands on a small, yellow stool to reach the wall above a patient's bed, where a colorful, abstract artwork is already hung. The nurse carefully aligns a new frame next to it, creating a comforting environment for patients. She uses a level to ensure each piece is straight, revealing her attention to detail in the cozy, well-decorated space. Throughout, she maintains a warm smile, demonstrating her caring nature as she enhances the room's aesthetic with more framed prints.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_1607
|
videos/HRA_part1/1607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, open field under a clear blue sky, two young children, a boy and a girl, both wearing vibrant yellow raincoats, wide-brimmed hats, and boots, are seen walking together. They carry a large, reflective solar sail, its metallic surface shimmering in the sunlight. The sail, supported by a wooden frame they hold, catches the wind as they walk, propelling them forward playfully across the grassy landscape. Their joyful expressions and the sail's gentle movements create a whimsical scene, blending elements of childhood wonder with futuristic technology.]"
},
{
"from": "gpt",
"value": "Normal. The faces and hands of the children in the video have generation issues."
}
] |
seed46_1223
|
videos/HRA_part2/1223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet, sunlit forest, a young woman who resembles a cashier from a local store embarks on a hike, dressed in hiking gear that includes a green jacket, khaki pants, and brown boots. She pauses to look at something intriguing in the distance, her hiking backpack visible. Moments later, she is seen walking confidently along the trail, her attire and equipment suggesting a preparedness for the outdoors. Then, she stops to rest, leaning against a tree trunk, her hiking poles propped up beside her, conveying a sense of peaceful contemplation. Finally, she continues her journey, walking away from the camera, her figure framed by the lush greenery and dappled sunlight, embodying the spirit of adventure and nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2953
|
videos/HRA_part1/2953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blue t-shirt and khaki shorts, runs across a vast desert landscape under a clear blue sky, with distant mountains providing a dramatic backdrop. The student, wearing a backpack and a cap, navigates the sandy terrain with determination, the camera capturing the texture of the dunes and the play of light and shadow. As the scene progresses, the focus remains on the runner, highlighting their stamina and resilience against the stark beauty of the desert environment.]"
},
{
"from": "gpt",
"value": "Bad. The student's limbs are missing in the video, and the face generation is blurry."
}
] |
seed42_1724
|
videos/HRA_part0/1724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine, high-quality piece of cod fish is showcased, featuring a clean, white fillet with a compact, flaky texture. The fish is presented on a simple, rustic wooden board, accompanied by fresh lemon wedges and sprigs of dill, enhancing the natural freshness and flavor of the cod. The background is softly blurred, emphasizing the star of the show—the cod fish—while maintaining a clean, modern aesthetic. The lighting highlights the fish's texture and color, making it appear both appetizing and ready for culinary preparation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1473
|
videos/HRA_part1/1473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches on a branch, its vibrant green feathers contrasting against a clear blue sky, before taking flight against a backdrop of lush greenery and distant mountains. It swoops down gracefully, its long, slender beak aimed at capturing prey. The bird then returns to the branch, where it proudly displays its catch, a honeybee, before consuming it. Throughout the scene, the bee-eater's striking plumage, featuring shades of green, blue, and brown, catches the eye against the serene landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2160
|
videos/HRA_part0/2160.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling park setting, two children engage in playful pushing, wearing vibrant, colorful clothing typical of a sunny day. One child, dressed in a yellow shirt and blue shorts, playfully pushes another child, who is wearing a red shirt and green shorts, against the backdrop of lush green grass and clear blue skies. The interaction is filled with laughter and joy, capturing the essence of innocent childhood fun. The children's faces are beaming with delight, their eyes sparkling with excitement, as they enjoy each other's company in the heart of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The faces, hands, and feet of the children in the video have generation issues."
}
] |
seed42_2903
|
videos/HRA_part0/2903.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier, wearing a red apron over a white collared shirt, black pants, and brown shoes, pulls a heavy, overflowing shopping cart across a busy supermarket floor. She moves with determination, navigating the aisles filled with various products and customers. The cart, brimming with goods, contrasts with her clean and tidy appearance, highlighting the physical demands of her job. Behind her, the supermarket's brightly lit shelves and bustling atmosphere provide a dynamic backdrop to her task.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the female cashier pushing the shopping cart, her movements are basically normal but slightly uncoordinated."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a 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": "Normal. The legs of the gazelle appear deformed."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.