video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2575
|
videos/HRA_part0/2575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young children, a boy and a girl, are energetically shoveling snow in their front yard, surrounded by a wooden fence. The boy wears a brown jacket, gray pants, and a matching hat and mittens, while the girl is dressed in a purple jacket, jeans, and a pink hat and mittens. Both are using small red shovels to clear a path through the fresh, fluffy snow, their faces showing determination and joy. The scene is set against a backdrop of a suburban house, with windows reflecting the bright, sunny day, and a green minivan parked in the driveway, partially covered in snow. The atmosphere is one of cheerful family activity on a crisp, wintry day.]"
},
{
"from": "gpt",
"value": "Normal. The children's actions of shoveling snow with red shovels in the video are basically normal, but there is some lack of coordination."
}
] |
seed44_2261
|
videos/HRA_part1/2261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an array of colorful fish. The grouper, with its distinctive spotted pattern and wide, flat head, explores its surroundings with a slow, methodical motion. Its eyes, fixed on the camera, seem to convey intelligence and awareness. The water is crystal clear, allowing every detail of the grouper's body and the intricate ecosystem it inhabits to be visible. The scene is illuminated by natural sunlight filtering through the surface, casting dappled light on the sandy seabed and the marine life above.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2173
|
videos/HRA_part0/2173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, identifiable by its distinctive facial stripes and grizzled gray fur, swims through clear, calm water, showcasing its swimming abilities as it propels itself forward with powerful strokes. Its face is partially submerged, displaying its wet snout and closed eyes, indicating its focus on navigating underwater. The badger's body is fully visible, revealing its muscular build and the water droplets clinging to its fur, highlighting its natural habitat and aquatic skills. The scene is set in a peaceful, natural environment, with the badger's swimming motion captured in detail against a backdrop of still water and lush vegetation.]"
},
{
"from": "gpt",
"value": "Normal. The European badger's face is slightly distorted in the video."
}
] |
seed42_1148
|
videos/HRA_part0/1148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diligent male worker, clad in a green jacket, dark pants, and brown gloves, meticulously rakes a large pile of autumn leaves in the foreground, creating a tidy heap. Behind him, a vast expanse of fallen leaves covers the grassy area, extending into the distance. The scene is set in a spacious backyard surrounded by a wooden fence, with a row of mature trees framing the horizon. As the worker continues to rake, the pile of leaves grows larger, highlighting the laborious task at hand. Throughout the process, the worker maintains a focused demeanor, his movements methodical and efficient, embodying the essence of hard work and determination.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are deformed, the face is distorted, and the hoe in hand is twisted and deformed."
}
] |
seed42_2492
|
videos/HRA_part0/2492.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a futuristic space movie set, a dedicated nurse in a pristine white uniform tends to a unique patient—a green lizard-like alien with intricate facial features. She gently wipes the creature's face with a soft cloth, her compassionate expression conveying care and concern. The sterile environment is contrasted by the exotic presence of the alien, creating a captivating scene blending human kindness with otherworldly elements.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's hand generation in the video has issues, with the fabric suddenly disappearing in the middle frames."
}
] |
seed46_2524
|
videos/HRA_part2/2524.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising juxtaposition, a young, cheerful cashier, wearing a green apron over a striped shirt, is seen enjoying a swim in a clear, tranquil body of water surrounded by scrublands. The cashier, with short, wavy hair and a nose ring, alternates between swimming and floating on the water's surface, showcasing a sense of freedom and relaxation. The scrublands, with their sparse vegetation and sandy soil, provide a stark contrast to the refreshing water, creating a unique and captivating scene. Throughout, the cashier's attire remains consistent, featuring the green apron and striped shirt, as they immerse themselves in the peaceful environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1422
|
videos/HRA_part0/1422.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, clean-shaven male chef with short brown hair waves energetically with his right hand, standing in front of a vibrant green wall adorned with a pattern of white dots. He wears a traditional white chef's uniform with a black necktie, and his left hand rests comfortably in his pocket. The chef's warm smile and engaging demeanor convey a sense of welcome and enthusiasm, perfect for a cooking show introduction or a restaurant greeting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2487
|
videos/HRA_part2/2487.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, 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": "Good. No obvious issues."
}
] |
seed44_3073
|
videos/HRA_part1/3073.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 zero gravity, a male and female astronaut, both clad in navy blue spacesuits with patches and equipped with life support backpacks, engage in a captivating dance. Their movements are fluid and graceful, defying the constraints of Earth's gravity. The man gently caresses the woman's face with his right hand, his fingers tenderly grazing her cheek, while she responds with a warm smile. The intimate moment is set against the backdrop of a space station interior, complete with computers, wires, and scientific equipment, creating a surreal and emotionally charged atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The male astronaut in the video is depicted with deformities."
}
] |
seed46_1795
|
videos/HRA_part2/1795.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 perches on a branch, its intelligent eyes gazing intently into the camera. Set against a lush, green jungle backdrop, the bird's colorful plumage stands out dramatically. It turns its head, showcasing its striking features, including a curved, black beak. The parrot then opens its beak, emitting a loud squawk, its dynamic body language and vivid colors creating a captivating scene in the heart of the rainforest.]"
},
{
"from": "gpt",
"value": "Bad. The parrot's beak in the video has issues, the head and body are generated blurry, and there are ghosting effects on the wings."
}
] |
seed46_2829
|
videos/HRA_part2/2829.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull perches regally atop a wooden pole, its piercing eyes scanning the horizon over a vast, serene ocean. The bird, with its crisp white plumage and distinct black-tipped wings, contrasts beautifully against a backdrop of soft, pastel skies. It stretches its wings gracefully, preparing for flight, before taking off into the air with a powerful swoop. As it glides effortlessly over the calm waters, the seagull's silhouette becomes a striking focal point against the gentle, rolling waves and the peaceful, cloud-dappled sky.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2604
|
videos/HRA_part2/2604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown leather jacket and stylish glasses, stands confidently at the edge of a swimming pool, meticulously observing an ibex gracefully swimming underwater. The ibex, a sure-footed mountain-dwelling mammal, is shown in a surreal scene, effortlessly gliding through the clear blue water, its horns visible above its head. The director's focused gaze and the ibex's unusual aquatic activity create a captivating and thought-provoking visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The sheep's legs show deformities."
}
] |
seed44_1967
|
videos/HRA_part1/1967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 inventive scene unfolds where an engineer, clad in a gray jumpsuit and helmet, meticulously studies blueprints near a full-sized mechanical rhinoceros. Suddenly, the engineer leaps onto the rhino's back as it begins to jump, creating an unexpected yet thrilling spectacle. The mechanical rhinoceros, constructed with intricate metalwork and advanced engineering, bounds across the landscape, while the fearless engineer holds on, embodying a harmonious blend of human ingenuity and mechanical prowess.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2567
|
videos/HRA_part1/2567.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sunlit savanna, two zebras engage in a tender moment, their striped coats shimmering against the golden grass. One zebra gently nuzzles the other's neck, their muzzles touching affectionately, showcasing a rare display of intimacy between these wild equines. The landscape is dotted with scattered acacia trees and distant mountains, providing a serene backdrop to this heartwarming scene. As they caress each other, the bond between them is evident, a beautiful testament to the emotional connections found in the animal kingdom.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1032
|
videos/HRA_part1/1032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge, cap, and sunglasses, stands at the edge of a zoo's flamingo enclosure, where vibrant pink birds congregate. The scene shifts slightly to reveal a clear blue pool within the zoological park, where the officer now interacts with the public, demonstrating water safety techniques. Nearby, children and families watch, some seated on benches under the shade of lush trees, while others lean on the railing, observing the swimming demonstration with interest. Throughout, the police officer remains engaged and attentive, fostering a sense of community and safety among the zoo visitors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2
|
videos/HRA_part1/2.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, rustic shop filled with natural light, a cheerful cashier, wearing a red apron over a cream sweater and dark jeans, sits behind a wooden counter adorned with a vintage cash register and various knitting supplies. She expertly knits a vibrant, multi-colored scarf, her hands moving swiftly as she focuses intently on her craft. The atmosphere is warm and inviting, with the soft clacking of knitting needles adding a soothing soundtrack to the scene. Shelves stocked with yarn in various textures and hues line the walls, creating a backdrop that complements the cashier's skillful knitting.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hands show signs of deformity, and the knitted object in her hands also becomes distorted."
}
] |
seed42_138
|
videos/HRA_part0/138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tropical dry forest, a talented female musician, dressed in a flowy yellow sundress, sits atop a fallen tree trunk, surrounded by lush greenery and vibrant wildflowers. She gently caresses her acoustic guitar, playing a soulful melody that resonates throughout the forest. Sunbeams filter through the canopy overhead, casting dappled light onto the forest floor, as birds chirp in the background, adding to the serene atmosphere. The musician's eyes are closed in concentration, her fingers gracefully moving across the strings, creating a harmonious symphony in the midst of nature's splendor.]"
},
{
"from": "gpt",
"value": "Normal. The guitar playing actions of the person in the video are basically normal, with slight disharmony."
}
] |
seed42_101
|
videos/HRA_part0/101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 starling perches on a branch, its iridescent feathers shimmering in shades of green and purple under the bright sunlight. The bird's eyes are alert, scanning the surroundings with curiosity. Its beak is slightly open, ready to emit a burst of song. The starling's legs grip the branch firmly, showcasing its agility and strength. In the background, lush green foliage provides a serene setting for this captivating display of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2435
|
videos/HRA_part0/2435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stork, distinguished by its gray feathers and black wingtips, is captured in a series of poses. Initially, it stands tall on a grassy bank, legs firmly planted, looking alert. Then, it spreads its wings wide, ready for flight, with a serene lake and lush greenery serving as a backdrop. Next, the bird is seen in mid-flight, gracefully soaring over the water's surface, with its wings fully extended and head held high. Finally, it lands elegantly, tucking its wings and extending its long legs, touching down on the grass near the water's edge, completing the sequence of its daily activities by the lakeside.]"
},
{
"from": "gpt",
"value": "Normal. The stork's legs and head are missing in the video, and the wings and body are deformed."
}
] |
seed46_2833
|
videos/HRA_part2/2833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red flannel shirt and denim overalls, is seen exerting effort as he pulls on a thick rope. The scene is set on a vast, green farm, with lush fields stretching into the horizon. The farmer's weathered hands grip the rope tightly, his face contorted in determination, highlighting the physical demands of his labor. Behind him, a wooden barn with a rusty roof provides a rustic backdrop, while the clear blue sky above adds a sense of serenity to the hardworking atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1702
|
videos/HRA_part1/1702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray wolf, with a thick, shaggy coat, powerful legs, and piercing yellow eyes, swims through a serene, crystal-clear lake surrounded by lush greenery. Its head is raised, showcasing determination, while water droplets glisten on its fur. The wolf's body, well-muscled and agile, propels it forward in the water, highlighting its surprising aquatic prowess. The landscape around the lake is lush and verdant, with tall trees providing a picturesque setting for this unexpected scene of a wolf navigating the water with ease and grace.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1291
|
videos/HRA_part1/1291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a badge, is seen swimming in a large, outdoor pool with a rhinoceros nearby. The setting is a spacious enclosure with lush greenery, reminiscent of a wildlife sanctuary. The officer, wearing sunglasses and a cap, is shown diving into the water, while the rhinoceros, sporting a police-themed saddle, looks on from the edge of the pool. In another scene, the officer is playfully splashing water with the rhinoceros, both enjoying a moment of leisure under the clear blue sky. The final shot captures the officer and the rhinoceros exiting the pool together, the officer patting the rhino affectionately, highlighting an unusual yet heartwarming bond between law enforcement and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the police officer wearing sunglasses and a cap, and the police officer is not shown jumping into the water to play with the rhino and patting the rhino affectionately."
}
] |
seed42_271
|
videos/HRA_part0/271.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest, blue jeans, and a brown shirt, interacts with a moose in a serene lake, both swimming together in the cool, clear water. The scene opens with the worker paddling gently, the moose swimming nearby, and lush greenery framing the tranquil waterscape. Next, the worker and the moose are seen swimming side by side, the man's safety vest and the moose's large antlers clearly visible above water. Then, the worker, still in his yellow safety vest, blue jeans, and brown shirt, floats on his back, the moose swimming peacefully beside him. Finally, the two unlikely companions, the worker in his distinctive attire and the majestic moose, continue to swim together in harmony, the peaceful lake and verdant surroundings creating a picturesque setting.]"
},
{
"from": "gpt",
"value": "Normal. The worker's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1044
|
videos/HRA_part0/1044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, a middle-aged janitor, wearing a yellow high-visibility vest over a dark jacket and a gray cap, gently caresses a kangaroo. The animal, with its distinctive marsupial pouch, is calm and accepting of the man's affection. The setting is a nondescript indoor location with concrete floors and walls, typical of a warehouse or large garage, with various tools and equipment scattered about. The interaction between the unlikely pair is tender and peaceful, capturing a unique moment of interspecies connection.]"
},
{
"from": "gpt",
"value": "Normal. Hand deformity appears, the person's hand is barely visible."
}
] |
seed46_1530
|
videos/HRA_part2/1530.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 parallel universe setting, a distinguished lawyer, wearing a dark suit, white shirt, and red tie, gently caresses a small, mysterious object in his hands, displaying a mix of curiosity and concern. His well-groomed appearance, complete with neatly combed hair and trimmed facial hair, contrasts with the perplexing artifact. Behind him, an office with modern furniture and technology reflects the alternate reality, adding to the intrigue of the scene. The interaction between the lawyer and the object, set against this backdrop, suggests a narrative filled with unexpected twists and turns.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_181
|
videos/HRA_part1/181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A visionary director, wearing a brown jacket, sits on a chair, intently operating a camera, capturing footage of a rhinoceros in a barren desert landscape, with a massive white hole explosion occurring in the distance. The rhinoceros, filmed in extreme close-up, slowly crawls across the sandy terrain, its textured skin and concentrated gaze highlighting its determination. The director, now seen from behind, continues to film the rhinoceros as it traverses the challenging environment, with the white hole explosion's brilliant light illuminating the scene, creating a surreal and captivating contrast between the earthbound creature and the cosmic event.]"
},
{
"from": "gpt",
"value": "Bad. The rhino's body is twisted, and its legs are distorted."
}
] |
seed46_2949
|
videos/HRA_part2/2949.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, donning full gear and a helmet, takes a break from his usual duties to engage in a surprising hobby: gardening. He carefully plants flowers in a small garden plot, surrounded by a wooden fence, with a bright red firetruck visible in the background. His gloved hands, typically used to handle hoses and axes, now delicately place marigolds into the soil. The juxtaposition of his robust firefighting attire and the delicate act of gardening creates a unique and compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Good. The video clearly shows the firefighter planting marigolds into the soil, with basically normal movements and no obvious issues."
}
] |
seed44_2965
|
videos/HRA_part1/2965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male writer, dressed in a black turtleneck sweater and khaki pants, walks through a vast grassland with rolling hills under a clear blue sky. He pauses to observe a herd of deer grazing nearby, the animals' presence adding to the tranquility of the landscape. The writer continues his journey, a pen and notebook visible in his pocket, suggesting inspiration drawn from nature. As he moves further into the grassland, the distant silhouette of mountains can be seen, enhancing the sense of adventure and exploration. Throughout the scene, the focus remains on the writer's contemplative walk among the deer, with the vibrant green grass and expansive sky creating a serene and inspiring atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs are still somewhat uncoordinated while walking, and his hands and legs are deformed. The notebook in his hand suddenly disappears."
}
] |
seed46_2471
|
videos/HRA_part2/2471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a distinguished doctor, clad in a lab coat and stethoscope, runs alongside a prehistoric mammoth through an industrial landscape dotted with colossal power plants. Their breaths form visible clouds in the crisp air, as they navigate the terrain under an overcast sky. The mammoth's massive frame and the doctor's determined gaze create an unlikely alliance, their journey unfolding against the backdrop of towering smokestacks and power lines, blending elements of fantasy and reality in a captivating scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, 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 video did not generate the action of pouring oil into a pan, or flipping food in a pan."
}
] |
seed44_1849
|
videos/HRA_part1/1849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary vulture, with its distinctive bald head and dark plumage, perches majestically on a rocky outcropping, overlooking a vast, arid landscape under an overcast sky. Its powerful, hooked beak is slightly open, revealing its pinkish-red interior, while its piercing eyes survey the terrain for potential prey. The bird's textured skin and feather details are highlighted by the natural lighting, emphasizing its rugged survival instincts in the harsh environment. As it prepares to take flight, the vulture's wings spread wide, displaying their impressive span against the muted tones of the rocky surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1985
|
videos/HRA_part1/1985.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 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, 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": "Bad. The cat's limbs and the man's fingers were generated incorrectly in the video."
}
] |
seed44_3005
|
videos/HRA_part1/3005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, complete with a gray suit, red tie, and glasses, is kneeling in a whimsical scene beside a meerkat standing upright. The lawyer gently wipes the meerkat's face with a white cloth, both figures set against a vibrant green grassy background under a clear blue sky, creating an unusual yet captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2400
|
videos/HRA_part1/2400.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear including a yellow reflective jacket, black helmet, and breathing apparatus, rests his head on his hands atop a wooden table in a dimly lit room. The scene conveys a sense of quiet repose after a night shift, with the firefighter appearing tired yet ready to respond at a moment's notice. His equipment is scattered around him, including a flashlight, gloves, and boots, adding to the realism of the setting. The firefighter's body language suggests exhaustion, as he leans forward with his elbows on the table, seeking solace in a brief moment of rest.]"
},
{
"from": "gpt",
"value": "Bad. Did not generate flashlight, gloves, and boots."
}
] |
seed44_1201
|
videos/HRA_part1/1201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, dressed in a silver spacesuit, floats weightlessly in orbit around Earth, cradling a vibrant red electric guitar. His helmet visor reflects the stunning view of our planet, encapsulating the vastness of space. He gently caresses the guitar, playing it in zero gravity, as the blue and green hues of Earth contrast beautifully with the darkness of space behind him. The visual conveys a sense of tranquility and isolation, with the musician appearing lost in music amid the cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed42_304
|
videos/HRA_part0/304.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, dressed in a classic white uniform and black pants, walks through a lush, green forest carrying a live rabbit in his arms. The chef's attire is detailed, complete with a traditional white chef's jacket, black trousers, and a pristine white chef's hat. The rabbit, a live and lively creature, is held gently in the chef's arms as he strolls through the dense woodland. The forest setting is richly depicted, with tall trees, vibrant foliage, and dappled sunlight filtering through the leaves, creating a dramatic contrast with the chef's uniform and the rabbit's fur.]"
},
{
"from": "gpt",
"value": "Bad. The chef's hands and feet are deformed in the video, and the rabbit is generated abnormally."
}
] |
seed42_1898
|
videos/HRA_part0/1898.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a straw hat and blue overalls, is seen playfully splashing water at a curious jackal on the banks of a serene lake during golden hour. The farmer then dives into the water, swimming with ease, while the jackal cautiously wades in, its ears perked up and attentive. They engage in a lighthearted game, the farmer swimming and the jackal paddling near the shore, both enjoying the cool waters under the warm, golden glow of the setting sun.]"
},
{
"from": "gpt",
"value": "Normal. The hyena's head generation in the video is problematic."
}
] |
seed44_1137
|
videos/HRA_part1/1137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 outdoor festival setting, two joyful people, a man in a red shirt and blue jeans, and a woman in a yellow dress, dance energetically near a food truck, while a cheerful crowd gathers in the background. The man wears a cap, and the woman has her hair in a bun. They are accompanied by a playful brown dog, who is also participating in the dance, leaping and spinning alongside them. The trio moves to the beat of lively music, surrounded by a diverse group of onlookers, all sharing in the festive atmosphere under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The woman's dancing in the video is not smooth, and the man's movements are uncoordinated."
}
] |
seed42_1333
|
videos/HRA_part0/1333.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lively brown and white dog bounds through the shallow waters of a serene lake at sunset, its fur glistening with droplets. It shakes vigorously, sending water flying in a sparkling mist, while standing on the sandy shore. Against the backdrop of a tranquil lake and a stunning sunset, the energetic canine leaps into the air, capturing the essence of joy and freedom. As it lands, it shakes again, creating a captivating spray against the golden hour light, highlighting every droplet in the air. Throughout, the dog wears a red collar, adding a pop of color against the natural hues of the landscape.]"
},
{
"from": "gpt",
"value": "Normal. The dog in the video has stuttering, and some limbs are missing."
}
] |
seed42_168
|
videos/HRA_part0/168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, freshly harvested oyster lies open on a bed of crushed ice, its plump, glistening flesh nestled within the rough, grey shell. The oyster's edges are jagged, contrasting with the smooth, pearly interior. A small pool of briny liquor sits at the center, reflecting the overhead lights. Surrounding the oyster are shards of ice, creating a frosty, clean environment that enhances the raw beauty of the seafood delicacy. The overall effect is a close-up, high-definition shot that captures the essence of fresh, oceanic flavors.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1433
|
videos/HRA_part0/1433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene, two children, a boy and a girl, sprint across a grassy area with wide smiles, dressed in casual play clothes—a red T-shirt and blue shorts for the boy, and a floral dress for the girl. Suddenly, the focus is on the boy as he runs with gleeful determination. Then, the girl takes center stage, her pigtails bouncing as she races forward. The action culminates with both children laughing and running together, their eyes filled with joy, all while a gorilla statue stands watchfully in the background, adding a touch of whimsy to the playful atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's running motion is not smooth."
}
] |
seed46_312
|
videos/HRA_part2/312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic virtual reality environment, a stunningly realistic cheetah lies calmly on a holographic savanna, its sleek golden body adorned with black spots. A person, clad in a full-body VR suit, gently caresses the virtual cheetah's head and back, their movements tracked in detail within the immersive space. The cheetah responds with relaxed body language, indicating comfort and trust, as the human participant experiences the sensation of touching the wild animal through advanced haptic feedback technology. The scene is set against a vast, computer-generated landscape, complete with distant acacia trees and a vivid blue sky, creating an almost tangible illusion of being present in the African wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The leopard in the video has uncoordinated movements."
}
] |
seed42_2447
|
videos/HRA_part0/2447.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a gorilla wearing an astronaut suit stands before a massive spaceship, its textured surface reflecting the alien landscape. The gorilla looks up at the ship with curiosity and determination, ready to embark on a journey through interstellar space. Suddenly, the scene changes to show the gorilla swimming underwater, its powerful arms propelling it forward through crystal clear water, surrounded by colorful fish and vibrant coral reefs. The contrast between the futuristic space travel and the natural beauty of the underwater world highlights the versatility and adaptability of this extraordinary creature.]"
},
{
"from": "gpt",
"value": "Normal. The gorilla's movements in the video are not smooth."
}
] |
seed42_3046
|
videos/HRA_part0/3046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter dressed in a black vest, white shirt, and black pants kneels on all fours, imitating crawling, in a vast, grassy savanna. Nearby, an antelope, startled yet intrigued, observes the unusual sight, standing still amidst the natural landscape, with distant acacia trees framing the horizon. The waiter, maintaining the crawling posture, looks up at the antelope with a mix of curiosity and amusement, creating a surreal juxtaposition between human and wildlife behavior in the serene African wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The server's hands and feet are deformed in the video."
}
] |
seed46_1334
|
videos/HRA_part2/1334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is presented on a clean, white plate, its textured surface and irregular shape contrasting against the smooth, pristine background. The fish's left side faces upward, revealing its distinct dark brown coloration on top and lighter underside. Its eyes are both positioned on the darker left side, glistening and intact, indicating its freshness. The halibut's skin bears a natural pattern of spots and lines, and its mouth is slightly open, showing its small teeth. The setting is simple and unadorned, allowing the fish to be the focal point, perfect for a culinary or educational video feature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_233
|
videos/HRA_part0/233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a plaid shirt, denim overalls, and a worn baseball cap, stands in a modern kitchen. He methodically unloads a sleek, stainless steel dishwasher, handling each plate and utensil with unexpected gentleness. The contrast between his calloused hands and the shiny, clean dishes highlights the unusual domestic task for someone more accustomed to farm chores. The kitchen is spacious and well-lit, featuring granite countertops and contemporary appliances, offering a glimpse into the farmer's home life beyond the fields.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1003
|
videos/HRA_part0/1003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a sleek, form-fitting spacesuit, adorned with intricate details and a VR helmet, is seen in a futuristic, high-tech room filled with advanced equipment. He leaps into the air, seemingly weightless, as the virtual environment around him simulates the zero-gravity conditions of space. The room is illuminated by soft, ambient lighting, highlighting the man's movements as he trains for space missions, surrounded by screens displaying complex data and simulations. The focus remains on the astronaut in the center of the room, his body language conveying determination and excitement as he experiences the thrill of jumping in a virtual space environment.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video has a twisted body, face, arms, legs, and hands."
}
] |
seed46_1621
|
videos/HRA_part2/1621.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray suit with a light gray shirt and red tie, prepares coffee in a modern kitchen. The lawyer, wearing glasses, carefully measures coffee grounds into a French press, adding hot water from a sleek electric kettle. The scene captures the lawyer's meticulous attention to detail, from pouring the water to stirring the mixture gently. The lawyer then presses down the plunger slowly, ensuring a rich brew, all while surrounded by stainless steel appliances and minimalist design elements, creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
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 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, 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": "Normal. The rabbit's movements in the video are not smooth."
}
] |
seed44_2124
|
videos/HRA_part1/2124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, donning a high-tech suit and goggles, operates a gravity manipulation device in a sleek, futuristic lab. He sprints across the room, defying gravity as he runs upside-down on the ceiling, his movements fluid and purposeful. The device, a compact, intricate mechanism attached to his back, emits a soft glow, highlighting its active state. Around him, the lab is filled with advanced equipment and screens displaying complex data, emphasizing the cutting-edge nature of his work. Throughout the sequence, the engineer's confident expression and dynamic actions showcase the thrilling potential of gravity-altering technology.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1345
|
videos/HRA_part2/1345.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman dances joyously at a luxurious beach resort, adorned in a flowing, patterned dress that complements her radiant smile and the tropical surroundings. With the sun setting behind her, casting a warm glow over the sandy shore, she moves gracefully, her bare feet sinking into the soft sand. Palm trees sway gently in the breeze, framing the scene as she twirls, embodying the spirit of celebration and freedom under the clear, star-studded sky.]"
},
{
"from": "gpt",
"value": "Bad. The woman's facial features and limbs in the video are incomplete."
}
] |
seed42_1605
|
videos/HRA_part0/1605.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric landscape under an overcast sky, a colossal mammoth, covered in thick, shaggy fur, is seen crawling on its knees, struggling through deep snow. Its large tusks and body are caked with ice and snow, emphasizing its immense size and the harsh conditions it endures. The creature's eyes, filled with determination and resilience, are set against the barren, icy wilderness, capturing the essence of survival in a frozen world.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_3166
|
videos/HRA_part0/3166.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": "Normal. The action of the female doctor touching the elephant's trunk is slightly unsmooth."
}
] |
seed42_1709
|
videos/HRA_part0/1709.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense boreal forest, dappled sunlight filters through the canopy, illuminating the mossy ground. A curious capuchin monkey, clad in a red vest for visibility, explores this unfamiliar habitat. It cautiously descends from the treetops, venturing onto the forest floor, where it encounters an array of flora and fauna. The monkey walks among tall conifers, its eyes scanning the underbrush for interesting insects and plants, offering a unique perspective on life beneath the towering trees. Throughout the journey, the capuchin's red vest contrasts vividly with the lush greenery, making it a standout figure in the woodland scene.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel monkey's movements in the video are not smooth."
}
] |
seed46_1429
|
videos/HRA_part2/1429.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome waiter, wearing a white button-down shirt, black pants, and a black apron, walks down a busy city street. He gently caresses the side of a food truck, which is brightly lit and surrounded by eager customers. The scene is set during the golden hour, with the warm sunlight casting a glow on the bustling urban environment. The waiter's tender touch on the food truck contrasts with the lively atmosphere of the city, creating a unique and captivating moment.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show black pants."
}
] |
seed42_186
|
videos/HRA_part0/186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of cheerful children, ranging from toddlers to preteens, are engaged in the task of cleaning windows on a bright, sunny day. They wear casual clothes, including t-shirts, shorts, and sneakers, and sport various hairstyles, from pigtails to afros. The kids use squeegees and rags to wipe down the glass, leaving streaks of water and soap behind. They work together, laughing and chatting, as they tackle the large window panes of a suburban home, with lush greenery visible through the transparent surfaces. The atmosphere is one of teamwork and fun, with the youngsters taking pride in their chores under the warm glow of the sun.]"
},
{
"from": "gpt",
"value": "Bad. The children's movements in the video are uncoordinated."
}
] |
seed42_2820
|
videos/HRA_part0/2820.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a white collared shirt, points with her right hand to something outside the frame, her left hand resting on the counter. Behind her, a row of colorful candy bars lines the shelf, while above her head, a sign displays various services offered, such as check cashing and lottery tickets. The scene takes place inside a busy convenience store, with customers visible in the background, creating a snapshot of daily life in a bustling urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2657
|
videos/HRA_part1/2657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a muscular build, wearing a blue shirt and dark pants, carefully hangs pictures on a living room wall. He uses a level tool to ensure perfect alignment, focusing intently on his task. Moments later, he steps back to admire the arrangement of frames, which include a variety of sizes and styles, creating a visually appealing gallery wall. The room is brightly lit, showcasing the art pieces against a neutral backdrop, with the man's satisfied expression indicating his pride in the finished display.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2047
|
videos/HRA_part0/2047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rustic farmyard setting, a fluffy yellow chick is seen crawling across the ground, its tiny feet moving quickly beneath it. The chick crawls under a weathered wooden fence, its feathers ruffling slightly as it navigates the space. It continues its journey, now crawling over a patch of fresh green grass, the blades tickling its delicate underside. Finally, the chick reaches a small cluster of pebbles, over which it crawls, demonstrating determination and resilience in its exploration of the farmyard environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2196
|
videos/HRA_part1/2196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy gray cat with white paws is seen swimming in a clear blue pool, surrounded by green foliage. The cat's face shows visible effort as it paddles through the water with its front paws, displaying a unique and unexpected sight. The pool is framed by lush vegetation, creating a natural, serene environment for this unusual feline activity. The cat's determination and the vibrant greenery around the pool form a captivating contrast against the clear blue water.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1456
|
videos/HRA_part1/1456.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, recognizable by his distinct facial hair and dressed in hiking gear which includes a gray jacket, backpack, and cap, pauses on a rocky trail. The scenic mountain landscape behind him, featuring lush greenery and distant peaks, provides a stunning contrast to his utilitarian appearance. Initially, he looks down at his feet, seemingly contemplating his next step. Then, he turns his head slightly, his gaze following the path ahead. Next, he stops to observe the breathtaking view, his expression reflecting a sense of peace and appreciation for nature. Finally, he smiles widely, perhaps recalling a fond memory, before continuing his journey, embodying the unexpected image of a janitor enjoying a hike in the great outdoors.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand in the video is generated poorly."
}
] |
seed42_2614
|
videos/HRA_part0/2614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man with a muscular build, wearing a black tank top and blue jeans, pushes against a large, gray boulder in the middle of a lush forest. His face contorts with effort, highlighting his determination. The scene is set in a dense woodland area, with sunlight filtering through the trees and casting dappled shadows on the ground. The man's strong physique and focused expression convey a sense of strength and perseverance as he exerts himself against the immovable object.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1179
|
videos/HRA_part2/1179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large brown bear, standing on its hind legs on a wooden stage, wears a golden hat and a red bow tie, engaging in a whimsical dance under the spotlight. The stage is set against a dark, starry night sky, with the bear performing a series of playful dance moves, including a twirl and a playful wave to the audience, all while maintaining its costume of the golden top hat and red bow tie.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and eyes of the brown bear in the video are not fully generated."
}
] |
seed44_148
|
videos/HRA_part1/148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 bison, framed against a vivid orange sunset, leaps gracefully over a wooden fence in slow motion, showcasing its muscular physique and determination. Its shaggy, dark brown fur billows in the wind as it clears the barrier with ease, highlighting the animal's surprising agility and strength. The contrast between the bison's robust form and the delicate beauty of the twilight sky creates a dramatic and captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the bison in the video are not fully generated."
}
] |
seed44_1036
|
videos/HRA_part1/1036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single crow perches on a thin branch, set against a vivid orange sunset, its silhouette stark and striking. The bird has ruffled feathers, indicating a recent bout of activity, and it looks directly at the camera with one intense eye. Its beak is slightly open, as if about to call out into the dusky sky, which is ablaze with fiery hues of red and gold, casting a warm glow on the crow's form. The branch it rests on is delicate, barely able to support its weight, adding a sense of precarious balance to the scene. Behind the crow, the last rays of sunlight filter through the gaps in the bare tree branches, creating a dramatic interplay of light and shadow.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2095
|
videos/HRA_part2/2095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room filled with the scent of old books and memories, two people sit on a vintage, worn-out sofa, their faces reflecting deep sorrow. One, a woman with long, wavy brown hair, wears a simple gray sweater and blue jeans, her eyes red from crying, as she holds a well-loved teddy bear. Beside her, a man in a plaid shirt and khaki pants, his face equally stricken with grief, leans his forehead against hers, both of them finding solace in each other's presence. Tears stream down their cheeks, highlighting the raw emotion of the moment, as they seek comfort in the quiet space they share.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are not smooth and uncoordinated."
}
] |
seed42_3211
|
videos/HRA_part0/3211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, embodying the essence of a 'quantum leap,' sprints across a futuristic cityscape under a vibrant aurora borealis sky, wearing a neon green tracksuit that illuminates against the dark urban background. The artist's forward motion is captured in a series of dynamic poses, showcasing the fluidity and power of their stride. The cityscape, featuring sleek skyscrapers and holographic billboards, reflects the energy of the run. The aurora's ethereal glow adds a mystical touch to the scene, highlighting the artist's journey as a metaphorical leap into the unknown. Throughout the sequence, the artist's determination and the pulsating city life create a visual narrative of innovation and progress.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1689
|
videos/HRA_part2/1689.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crisp, white linen suit and dark sunglasses, sits beside a gorilla wearing a tiny, matching outfit, on a vibrant, sandy beach bustling with activity. The lawyer and gorilla share a lighthearted moment, enjoying the coastal scenery. Nearby, a group of people splash and swim in the crystal-clear water, their laughter blending with the rhythmic sound of the waves. The camera captures this whimsical scene, focusing on the lawyer and gorilla's playful interaction against the backdrop of a stunning beach and swimmers enjoying the refreshing waters.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's body has undergone a deformity mutation. The people swimming in the background have also undergone a deformity mutation."
}
] |
seed46_2448
|
videos/HRA_part2/2448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, characterized by its dark fur and physical strength, leaps powerfully from a low branch in a lush, green forest. The chimp, wearing a radio collar for tracking purposes, is seen mid-jump, demonstrating its agility and vitality. Its movement is captured in high definition, highlighting the details of its fur and the determination in its eyes. The chimpanzee propels itself forward, leaving the branch behind, showcasing its natural habitat and behaviors in a captivating, close-range shot.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the chimpanzee in the video are missing, the body is generated twisted, and there is an issue with the mouth generation."
}
] |
seed46_1014
|
videos/HRA_part2/1014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah, distinguished by its tear-streaked face, black spots, and tawny coat, crawls across a lush, green savanna dotted with small trees. The big cat moves slowly, its muscles rippling beneath its skin, as it focuses intently on something just beyond the frame. The camera captures the cheetah's every movement in stunning detail, from the alertness in its eyes to the careful placement of its paws, showcasing the grace and power of this incredible creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The tail and legs are deformed, with multiple legs appearing."
}
] |
seed44_250
|
videos/HRA_part1/250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, well-lit room filled with bookshelves, two young boys, one wearing a gray shirt and the other in a navy blue sweater, are diligently organizing books on a lower shelf. The atmosphere is calm and focused, with the boys working attentively side by side. One child carefully selects a book from a pile, examining it before placing it on the shelf, while the other arranges the books alphabetically, ensuring each title is correctly positioned. The room is warm and welcoming, with sunlight streaming in through a nearby window, casting a soft glow over the children as they engage in this educational activity together.]"
},
{
"from": "gpt",
"value": "Bad. The little boy's hand and arm are twisted in the video."
}
] |
seed44_1501
|
videos/HRA_part1/1501.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a tan belt holding a radio and handcuffs, diligently repairs a damaged wooden fence in a suburban neighborhood. The fence, marred by graffiti and broken planks, is set against a clear blue sky. The officer, wearing a hat and sunglasses, demonstrates community involvement by hammering a new plank into place, emphasizing public service beyond traditional law enforcement duties.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1266
|
videos/HRA_part0/1266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, donning a gray beanie, black jacket, and blue jeans, stands on the weathered wooden planks of a dock by the water's edge, with a vibrant cityscape visible across the bay. The artist leaps into the air, capturing the essence of freedom, while holding a sketchbook, which hints at their creative pursuits. The scene is bathed in golden hour sunlight, casting a warm glow over the figure and the urban landscape, creating a sense of serenity and inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The character appears deformed, with hands, arms, and legs undergoing morphological mutations, and the sketchbook in hand suddenly appears and disappears."
}
] |
seed46_1632
|
videos/HRA_part2/1632.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": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1698
|
videos/HRA_part2/1698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nimble squirrel, brimming with energy, leaps from a moss-covered branch in a lush, vibrant forest. The scene is bathed in a soft, golden light filtering through the dense canopy above. The squirrel's movement is captured mid-jump, its body arched gracefully in the air, showcasing its agility and speed. Its bushy tail trails behind, adding to the dynamic feel of the action. The background is a tapestry of green foliage, dotted with various tree trunks, providing a rich, textured setting for the squirrel's acrobatics.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's movement in the video is not smooth, and the actions are uncoordinated."
}
] |
seed44_1299
|
videos/HRA_part1/1299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an unusual scene, a waiter wearing a black vest, white shirt, and black pants performs a kick in a dining room. The room features a long wooden table adorned with a white cloth, set with plates and glassware. The waiter's kick is high and assertive, contrasting with the formal setting. His black shoes, part of his uniform, add to the unexpected nature of the action. Behind him, a large window allows natural light to illuminate the space, highlighting the waiter's dynamic movement against the backdrop of the elegantly arranged dining area.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2532
|
videos/HRA_part0/2532.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a blue and white checked shirt under his chef's jacket, walks through a dry scrubland with low vegetation, carrying a large branch over his right shoulder. The landscape is dotted with shrubs and small trees, with distant hills adding depth to the scene. The chef's casual attire, consisting of rolled-up sleeves and cargo pants, contrasts with his professional identity, creating an intriguing juxtaposition as he explores the rugged terrain.]"
},
{
"from": "gpt",
"value": "Normal. The chef's fingers in the video have generation issues."
}
] |
seed44_332
|
videos/HRA_part1/332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A director, attired in a khaki safari outfit, navigates through the dense undergrowth of a tropical dry forest. The sunlight filters through the canopy, casting dappled shadows on the rugged terrain. Lush, gnarled trees surround him, their leaves whispering in the gentle breeze. Insects buzz softly in the background, adding to the ambiance of the wild. The director walks purposefully, his boots crunching on the carpet of fallen leaves and twigs, holding a detailed map in one hand and occasionally stopping to consult it, his focus intense and unwavering.]"
},
{
"from": "gpt",
"value": "Normal. The director's fingers are deformed in the video, the face is generated blurry, and there are missing limbs."
}
] |
seed42_1590
|
videos/HRA_part0/1590.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, dressed in a red shirt, black vest, and dark pants, stands on a dimly lit stage, pointing with his right hand. He wears a black beret and glasses, adding to his artistic flair. Behind him, a vibrant purple curtain complements the stage lights, which cast a warm glow on his face. His left hand rests on his hip, and he points emphatically with his right, engaging the audience in a dynamic performance. The background is blurred, emphasizing the musician's commanding presence as he points with passion and intensity.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth, and the hand actions are incorrect."
}
] |
seed46_2699
|
videos/HRA_part2/2699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great egret, distinguished by its all-white plumage, stands tall and elegant in a shallow pond, surrounded by lush greenery and trees. Its long, slender legs, yellow-orange bill, and sharp eyesight are highlighted as it searches for prey among the reeds and water plants. The egret gracefully extends its neck, demonstrating its hunting prowess in the serene wetland environment. Moments later, it takes flight, showcasing its expansive wingspan against the clear blue sky, before landing nearby to continue its foraging activities, all within the peaceful setting of the pond and its verdant surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The head of the egret in the video is missing parts, the wings are deformed, and there are issues with the feet."
}
] |
seed46_1873
|
videos/HRA_part2/1873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape dominated by skyscrapers, a young female cashier, dressed in a black apron over a white shirt and black pants, stands behind a checkout counter in a modern, glass-walled convenience store. She gently caresses the edge of the counter with her right hand, her eyes softly closed, as if cherishing a moment of peace amidst the urban rush. The city's towering buildings loom outside the large windows behind her, contrasting with her intimate gesture.]"
},
{
"from": "gpt",
"value": "Good. The female cashier in the video has her eyes closed and is touching the counter with her hands, which is basically normal."
}
] |
seed44_1131
|
videos/HRA_part1/1131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate musician, donning a black leather jacket and jeans, pulls vigorously on the strings of an electric violin, his face contorted in intense concentration. The scene is set against a dark, moody backdrop, illuminated only by the warm glow emanating from the instrument. Close-ups capture the intricate movements of his fingers, adorned with silver rings, as they dance across the fretboard. The energy is palpable, as if the very essence of the music is being channeled through him, creating an electrifying performance that captivates the viewer.]"
},
{
"from": "gpt",
"value": "Normal. The musician's hand in the video is not fully generated."
}
] |
seed44_1856
|
videos/HRA_part1/1856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, identifiable by her backpack, dances whimsically across the screen, transitioning from a campus setting to an unexpected otter enclosure at a zoo. She's wearing a yellow top, denim shorts, and sneakers, embodying youthful energy. Suddenly, the scene shifts to a somber cemetery, where she continues to dance among the tombstones, now adorned in a black dress and boots, carrying a red umbrella. The juxtaposition of lively dancing in these varied locations, from educational grounds to wildlife exhibits to a place of remembrance, creates a surreal and captivating narrative.]"
},
{
"from": "gpt",
"value": "Normal. The girl's dance moves in the cemetery are not smooth and coordinated, with abrupt changes."
}
] |
seed42_1968
|
videos/HRA_part0/1968.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."
}
] |
seed42_2098
|
videos/HRA_part0/2098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 marlin, distinguished by its long, pointed bill and sleek, torpedo-shaped body, gracefully glides through the clear, vibrant blue waters of the open ocean. Its striking silver scales glisten as sunlight filters through the water, illuminating its form. The marlin's powerful tail propels it forward with effortless ease, while schools of smaller fish scatter in its wake, highlighting the apex predator's presence in the underwater ecosystem. Against the vast, deep-blue backdrop, the marlin's silhouette is both awe-inspiring and a testament to the beauty and power of marine life.]"
},
{
"from": "gpt",
"value": "Normal. The sailfish's fin generation in the video has problems."
}
] |
seed44_1115
|
videos/HRA_part1/1115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical scene, a man wearing a brown fur coat and matching furry boots is seen dancing joyfully next to a massive, ancient mammoth with long, curved tusks. The mammoth stands placidly, observing the man's lively movements. Behind them, a quaint village is visible, featuring a row of charming, colorful houses with thatched roofs. The houses are nestled among lush greenery, creating a picturesque and harmonious setting. The man's animated dancing contrasts with the mammoth's calm presence, while the village in the background adds a touch of warmth and community to the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2826
|
videos/HRA_part0/2826.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kangaroo, dressed in a chef's hat and apron, is shown playfully hopping around a vibrant, modern restaurant kitchen filled with gleaming stainless steel appliances and colorful, contemporary decor. The kangaroo then takes a break from its culinary duties to enjoy a refreshing swim in an outdoor pool, surrounded by lush greenery and bright, sunny skies, creating a surreal and delightful blend of dining and leisure. After its swim, the kangaroo returns to the restaurant, where it is greeted by patrons sitting at tables, enjoying their meals in the stylish dining area, complete with large windows offering views of the beautiful landscape outside. Finally, the kangaroo is seen back in the kitchen, preparing a dish with precision and care, as if it were a true master chef, all while maintaining its playful and endearing demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the scene of the kangaroo swimming in the outdoor pool."
}
] |
seed42_3078
|
videos/HRA_part0/3078.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, with its distinctive gray body and iridescent green neck feathers, perches on a concrete ledge. It has one leg tucked under its body, a common behavior for warmth, and its head is turned to look back over its shoulder. The pigeon's red webbed feet stand out against the gray urban setting, and its eyes, which are set far back in its head, give it a wide field of vision. It sits against a backdrop of a city street, with buildings and pedestrians visible in the distance, capturing a candid moment of this common urban bird.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2069
|
videos/HRA_part0/2069.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer wearing a red shirt and brown overalls strolls through a vast, lush green field, holding a walking stick as he leisurely promenades. Suddenly, he leaps into the air, his hat flying off, with a wide smile on his face, revealing sheer joy and freedom. The farmer continues his playful jumping spree amidst the vibrant scenery, surrounded by endless rows of corn stalks swaying gently in the breeze. As he lands, he resumes his peaceful walk, stick in hand, with the sun casting a warm glow over the fertile land, creating a sense of harmony and contentment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1743
|
videos/HRA_part2/1743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant green parrot with yellow facial feathers and red tail feathers perches on a branch, set against a blurred green background. The bird turns its head to look over its shoulder, displaying its detailed plumage. It then faces forward, revealing its sharp beak and curious expression. Next, it preens itself, using its beak to adjust its feathers, highlighting its self-care behavior. Finally, the parrot opens its wings slightly, showing off more of its stunning colors, all against a consistent blurred green backdrop that keeps the focus on the bird.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2972
|
videos/HRA_part2/2972.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his black-rimmed glasses and neatly trimmed beard, waters plants in an urban rooftop garden. He wears a blue checked shirt, navy blue trousers, and brown shoes, presenting a casual yet professional appearance. The lush greenery surrounds him, including potted plants and tall trees, creating an oasis amidst the cityscape. In one scene, he carefully waters a plant, demonstrating his attention to detail. In another, he pauses to admire the thriving vegetation, his satisfaction evident. Throughout, the rooftop garden offers a peaceful retreat from the bustling metropolis below, with the engineer's presence adding a human touch to the verdant setting.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the engineer watering the plants, the actions are basically normal but there is some lack of coordination."
}
] |
seed46_2910
|
videos/HRA_part2/2910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a yellow reflective vest, ascends a rocky terrain during the day, exhibiting determination and resilience. His tactical gear, including a backpack and a helmet, is visible as he scales the rugged landscape. The camera captures his focused face, set on completing the climb, and the lush greenery surrounding the rocky area, providing a stark contrast to his mission-driven ascent. Despite the challenging environment, the officer's resolve is evident, making for a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2344
|
videos/HRA_part2/2344.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, wearing a gray suit, white shirt, and patterned tie, stands in a dark room illuminated by a single spotlight, giving a speech about the concept of traveling at light speed. He passionately caresses an abstract sculpture representing the fabric of spacetime, emphasizing his points about the theoretical possibilities of superluminal travel. His gestures are expressive, conveying the emotional weight of discussing such a groundbreaking topic, all while maintaining eye contact with his unseen audience, inviting them to share in the wonder and complexity of his subject matter.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has uncoordinated movements."
}
] |
seed42_2280
|
videos/HRA_part0/2280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a gray sweater over a white collared shirt and khaki pants, sits at a desk in a classroom after hours. The room is illuminated by natural light from a large window, casting a warm glow over the scene. The student is focused on replacing batteries in a scientific calculator, an essential tool for their studies. They carefully remove the old batteries, showing a methodical approach to the task, before inserting new ones, ensuring the device is fully functional for upcoming exams. The calculator is placed beside a stack of textbooks and notebooks, highlighting the academic environment.]"
},
{
"from": "gpt",
"value": "Bad. The student's movements in the video are not smooth."
}
] |
seed46_28
|
videos/HRA_part2/28.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush forest setting filled with tall, verdant trees and patches of sunlight filtering through the leaves, a mongoose is gently caressing a smaller mongoose, possibly its offspring, with its nose. The larger mongoose, with its sleek brown fur and attentive eyes, exhibits tenderness and care, creating a heartwarming scene of familial affection in the midst of the natural environment.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the mongoose in the video are basically normal, with slight lack of coordination."
}
] |
seed46_2796
|
videos/HRA_part2/2796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow high-visibility jacket and hard hat, stands near a bobcat excavator on a construction site. He wipes down the machinery with a cloth, revealing the brand name on the excavator's arm. The scene is set against a backdrop of dirt and gravel, with other construction equipment visible in the background. The engineer's actions showcase the maintenance aspect of his job, highlighting his commitment to keeping the equipment clean and operational.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's movements in the video are not smooth."
}
] |
seed44_3110
|
videos/HRA_part1/3110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy white rabbit sits upright on a clean, wooden surface, using its paw to wipe its face meticulously, akin to a cat grooming itself. The action is repeated several times, showcasing the rabbit's cleanliness and the texture of its fur against the smooth wood. The rabbit then pauses, sitting still with its paws down and ears perked up, before resuming the wiping motion, its pink nose twitching occasionally. Throughout the sequence, the rabbit's focus remains on its grooming, offering a charming display of its self-care routine.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's paws are missing in the video, and the face is not fully generated."
}
] |
seed46_3021
|
videos/HRA_part2/3021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown shirt, beige vest, and dark pants, is seen on his hands and knees in a grassy yard, playfully crawling alongside a small, light brown dog. Both the man and the dog exhibit joyful expressions, with the dog wagging its tail enthusiastically. The man's shirt is untucked, revealing his playful side as he engages in this delightful interaction with his canine companion on a sunny day.]"
},
{
"from": "gpt",
"value": "Normal. The dog's movements in the video are basically normal, with slight disharmony."
}
] |
seed46_1447
|
videos/HRA_part2/1447.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ghost shrimp, nearly transparent with a slight gray tint, clings to the side of an aquarium, showcasing its delicate, see-through body and intricate internal structures. It hovers near a piece of driftwood, its multi-segmented legs and antennae visible as it interacts with its environment. The shrimp's eyes, dark and prominent against its translucent body, stand out as it explores its surroundings, highlighting its unique adaptation to freshwater habitats. Against the green backdrop of aquatic plants, the ghost shrimp's ethereal presence is captivating, offering a close-up view of its otherworldly form.]"
},
{
"from": "gpt",
"value": "Bad. The ghost shrimp's head is twisted, and its claws are deformed."
}
] |
seed42_1356
|
videos/HRA_part0/1356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 hummingbird, vibrant green and iridescent, hovers in a close-up shot against a blurred background of lush vegetation. Its wings, a blur of motion, propel it as it feeds from a red salvia flower, the curved beak piercing the bloom. The bird's small size, quick movements, and the detailed feathers are highlighted, set against the rich greenery and soft, natural lighting. The scene captures the hummingbird's agility and the delicate interaction between the bird and the flower, encapsulating the beauty of nature in high definition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.