video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1891
|
videos/HRA_part1/1891.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 airport terminal, a large, lifelike panda costume lays on its side, partially inflated, as a person inside attempts to crawl into it. The individual struggles comically within the confines of the costume, drawing curious glances from nearby travelers. Once fully inside, the person begins to crawl across the airport floor, the oversized panda head bouncing with each movement, creating a surreal and amusing scene amidst the typical airport chaos. Passengers of all ages watch in amusement, some capturing the unusual sight on their phones, as the person in the panda suit continues to crawl, adding a touch of whimsy to the otherwise ordinary airport environment.]"
},
{
"from": "gpt",
"value": "Normal. The panda character's movements in the video are not smooth."
}
] |
seed42_1157
|
videos/HRA_part0/1157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station pool, a courageous nurse, wearing a protective spacesuit with a clear helmet, fearlessly swims alongside a non-venomous cobra, which has been specially adapted for space travel. The nurse's spacesuit is adorned with patches representing various medical organizations, highlighting her dedication to healthcare even in the cosmos. The cobra, now a docile companion, glides effortlessly through the water, its scales reflecting the artificial lighting of the space station. This extraordinary scene showcases the integration of healthcare, exotic animals, and space tourism in a serene aquatic environment, encapsulating the essence of adventure and innovation in the final frontier.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1667
|
videos/HRA_part0/1667.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a cheerful nurse, clad in a traditional white uniform and cap, finds herself in an expansive landscape of lush farmlands under a clear blue sky. She shares an unexpected moment of joy with a playful otter, who leaps from her hands, its body arcing beautifully against the vibrant green backdrop of rolling fields and distant hills. The nurse's expression reflects pure delight as she watches the otter jump, encapsulating a surreal yet heartwarming encounter between human and nature.]"
},
{
"from": "gpt",
"value": "Bad. The sloth in the nurse's hands undergoes a deformity mutation when it jumps."
}
] |
seed46_2176
|
videos/HRA_part2/2176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating display, a slender cheetah with golden fur and black spots leaps into the air against a vivid, sunlit savanna landscape. Its body curves gracefully mid-leap, capturing the essence of its feline agility. The cheetah's intense, focused gaze is directed forward, suggesting a sense of purpose in its dance-like movements. Its tail extends elegantly, balancing its airborne form as it seemingly dances across the plains, embodying the spirit of the wild. The scene is framed by distant acacia silhouettes, enhancing the dramatic effect of the cheetah's dynamic leap.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2386
|
videos/HRA_part0/2386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, intricate fish with blue fins and a yellow body swims serenely in a clear, turquoise underwater environment, surrounded by lush green seaweed gently swaying in the current. Nearby, a school of smaller, silvery fish dart and weave, their movements synchronized and graceful, creating a mesmerizing display of aquatic life against the vivid backdrop of the underwater world. Above, rays of sunlight filter through the water's surface, casting dappled light on the scene below, highlighting the beauty and tranquility of the ocean depths.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3007
|
videos/HRA_part2/3007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spruce grouse, perched on a branch in a dense forest, displays its vibrant plumage featuring shades of brown, gray, and white speckles. Its red eyelids stand out against the dark eye, while its yellow bill adds a striking contrast. The bird's feathers are ruffled, perhaps due to a breeze or during a display, and it is surrounded by lush green foliage, indicating a healthy habitat. The grouse is stationary, offering a clear view of its unique features against the backdrop of a richly textured forest environment.]"
},
{
"from": "gpt",
"value": "Normal. The pheasant's eyes in the video have issues."
}
] |
seed44_170
|
videos/HRA_part1/170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate writer, donning a black beanie and glasses, sits at a modern desk, engrossed in typing on a sleek laptop. The scene is set in a cozy room with a brick wall and a wooden shelf filled with books, plants, and a clock. Morning sunlight softly illuminates the space, casting a warm glow on the writer's face. A cup of coffee sits nearby, a trusted companion during the creative process. The writer occasionally glances at notes spread across the desk, incorporating ideas into the digital manuscript, capturing the essence of dedication and inspiration in the art of writing.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2913
|
videos/HRA_part1/2913.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and black tactical gear, is seen in a residential backyard with green grass and trees in the background. He kneels beside a golden retriever, gently washing it with a hose and a sponge. The dog, wearing a red collar, happily shakes off water, splashing the officer who laughs good-naturedly. The scene conveys a heartwarming moment of care and connection between the officer and the dog, set against a backdrop of blue skies and lush greenery.]"
},
{
"from": "gpt",
"value": "Bad. The officer's face is distorted, the hands are distorted, and the dog's face is distorted."
}
] |
seed42_2397
|
videos/HRA_part0/2397.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling Turkish market, vibrant stalls brim with colorful spices, fresh fruits, and artisan goods, while traditional music fills the air. A vendor proudly displays a variety of flatbreads, including lahmacun topped with minced meat and vegetables, and pide with cheese and herbs. Patrons haggle over prices, their animated gestures and lively chatter adding to the energetic atmosphere. Amidst the crowd, a man in a fez hat enjoys a cup of strong Turkish coffee, seated at a small table under a canopy of hanging lanterns, encapsulating the rich culture and daily life of Turkey.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2854
|
videos/HRA_part1/2854.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone coyote, with a gray and cream coat, runs across a sunlit prairie, its ears perked and tail held low. It bounds through the tall grass, leaving a slight dust cloud in its wake, indicating speed and purpose. The coyote's focused gaze and agile movements showcase its hunting prowess, as it navigates the open landscape under a clear blue sky. Moments later, it leaps over a small obstacle, demonstrating its agility and grace, all while maintaining its steady pace across the vast, golden plains.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the coyote in the video have generation issues, with sudden distortion and deformation in the middle frames."
}
] |
seed42_1983
|
videos/HRA_part0/1983.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large brown bear, with its shaggy fur glistening in the sunlight, is seen swimming gracefully in a serene lake, surrounded by lush greenery and tall trees. Its powerful forearms propel it through the crystal-clear water, creating ripples that expand outward. The bear's alert eyes and nostrils are just above the waterline, showcasing its keen senses as it navigates the aquatic environment with ease. The peaceful setting, with the occasional splash and the gentle lapping of water against the shore, highlights the bear's natural ability to swim in its tranquil habitat.]"
},
{
"from": "gpt",
"value": "Normal. The brown bear's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed42_3213
|
videos/HRA_part0/3213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet captivating scene, a suave waiter, dressed in a crisp white shirt and black pants, serves refreshments poolside in the middle of a vast temperate shrubland. The swimming pool, an oasis of crystal-clear water, contrasts beautifully with the surrounding landscape of lush green shrubs and scattered trees. The waiter, with a tray balanced expertly in one hand, leans over to offer a glass to a guest, who is seated on a comfortable lounge chair, basking in the warm sunlight filtering through the leaves above. The serene atmosphere is enhanced by the gentle sounds of nature and the occasional splash from the pool, creating a perfect blend of luxury and wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The server's face, hands, and feet are distorted in the video."
}
] |
seed44_1644
|
videos/HRA_part1/1644.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-lit, organized retail store, two diligent employees wearing red aprons and name tags restock the shelves with groceries. One employee, a man with short brown hair, focuses on neatly arranging cereal boxes, ensuring they face forward. Meanwhile, his female coworker, wearing glasses and with her hair tied back, meticulously stacks cans of soup, aligning them perfectly. The shelves are filled with various food items, including crackers, canned goods, and pasta, all neatly organized and easily accessible to customers. The store is clean and inviting, with a fresh produce section visible in the background, showcasing an array of colorful fruits and vegetables.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, arms, legs, and hands are distorted in the video."
}
] |
seed44_1818
|
videos/HRA_part1/1818.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant botanical garden, a middle-aged janitor, wearing a green vest over a blue collared shirt and tan pants, gently caresses a camel. The scene opens with the janitor standing near a wooden fence, holding a leaf blower, before focusing on him tenderly touching the camel's nose. The setting shifts to the janitor embracing the camel's head, conveying a sense of affection and care. Lastly, he is seen feeding the camel from his hand, surrounded by the vibrant greenery of the botanical garden, creating a harmonious and unexpected connection between man and animal in a serene environment.]"
},
{
"from": "gpt",
"value": "Bad. The camel's head, the faces of the people, and the hands are generated poorly in the video."
}
] |
seed44_2230
|
videos/HRA_part1/2230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush green forest setting, a pair of beavers are seen intimately caressing each other, their brown fur glistening with moisture from the nearby river. The male beaver gently touches the female's face with his forepaw, a tender gesture of affection. They are surrounded by tall trees and vegetation, providing a natural and peaceful environment for their interaction. The female beaver responds with a soft look, her whiskers moving slightly as she nuzzles closer to him. This heartwarming scene captures the emotional bond between these two creatures, highlighting the beauty of wildlife relationships.]"
},
{
"from": "gpt",
"value": "Bad. Two beavers have facial deformities."
}
] |
seed42_1525
|
videos/HRA_part0/1525.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pigeon, with feathers of gray and white, perches on a stone ledge against a clear blue sky, its head turned to the side as it observes its surroundings with one round eye. Moments later, the bird stretches its wings, revealing a span of dark and light gray feathers, before settling back into a resting position. It then preens itself, using its sharp beak to groom its feathers, maintaining its cleanliness and hygiene. Finally, the pigeon takes flight, its wings flapping powerfully against the bright sky, leaving the ledge empty as it explores its urban habitat.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the pigeon's neck and claws in the video is problematic."
}
] |
seed42_1242
|
videos/HRA_part0/1242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a waiter wearing a green apron and carrying a tray with refreshments walks through a temperate rainforest. Surrounded by lush greenery, moss-covered trees, and ferns, he moves along a narrow path. The environment is enhanced by the presence of a large tree trunk, its roots exposed, and the sound of a nearby waterfall. Sunlight filters through the dense foliage, casting dappled light on the forest floor, creating a magical atmosphere as the waiter continues his journey.]"
},
{
"from": "gpt",
"value": "Bad. Only one leg can be seen, the other leg is not visible. The person's face appears deformed."
}
] |
seed44_2417
|
videos/HRA_part1/2417.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, golden cheetah crawls under a low-hanging, silver photon sail, its eyes fixated ahead, muscles rippling beneath its spotted coat, set against a backdrop of a futuristic, metallic landscape. The sail, towering above, reflects beams of sunlight, creating an ethereal glow around the big cat. The cheetah, with its distinctive black tear markings and piercing green eyes, moves gracefully, its body positioned low to the ground, as if stalking prey, while the sail's advanced technology hints at a world beyond nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2670
|
videos/HRA_part1/2670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, sits on a wooden crate under a bright blue sky, with scaffolding and building materials in the background. He gently pets a brown and white dog lying on its back, belly-up, on a pile of gravel, showing a tender moment of connection between the worker and the animal. The worker's hands, rough from labor, contrast with the softness of the dog's fur, creating a touching scene of companionship amidst a rugged worksite.]"
},
{
"from": "gpt",
"value": "Bad. The faces and hands of the workers, and the head and paws of the dog in the video have generation issues."
}
] |
seed44_1780
|
videos/HRA_part1/1780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly female cashier with brown hair pulled into a bun, wearing a green apron over a striped shirt, leans over to gently caress a koala standing on its hind legs on the counter. The koala, with its soft gray fur and curious expression, reaches up with its paw toward the cashier's face, creating a heartwarming interaction between the two. Behind the counter, a cash register and various retail items can be seen, adding to the unique setting of this tender moment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed44_3116
|
videos/HRA_part1/3116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate musician, donning a black cap, black jacket, and khaki pants, pushes a large, vintage amp through a crowded, dimly lit backstage area at a music venue. The scene is filled with the energy of an upcoming performance, as the musician maneuvers the amp with determination, highlighting the physical effort and dedication required behind the scenes. The musician's attire and the bustling environment capture the spirit of live music culture.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1904
|
videos/HRA_part2/1904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 casually dressed man in a white shirt and dark pants walks through a lush, green meadow dotted with vibrant wildflowers under a bright, clear blue sky. He strides purposefully, his hands clasped behind his back, exuding a sense of peace and connection with nature. The tall grass sways gently in the breeze around him, and in the distance, a range of rolling hills provides a picturesque backdrop, enhancing the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2702
|
videos/HRA_part0/2702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, vibrant kitchen filled with the warm glow of overhead lights, a group of four individuals, two men and two women, are energetically washing dishes. One man, wearing a dark green apron over a white t-shirt, vigorously scrubs a pot under running water from a stainless steel sink. Beside him, a woman in a yellow apron laughs as she dries a plate with a colorful cloth. Across the room, another man in a chef's coat rinses glasses, while a woman in a floral apron sorts cutlery, her hands deftly separating forks and spoons. The atmosphere is lively, with steam rising from the sink and the clinking of dishes adding to the symphony of post-meal cleanup.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3126
|
videos/HRA_part0/3126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown jacket and beige cap, energetically jumps on a moving walkway inside a bustling airport terminal, his body language conveying enthusiasm and excitement. Around him, the airport's modern architecture and various travelers create a dynamic setting, contrasting with his animated leap. The director's attire includes a brown coat, khaki pants, and a beige hat, while the busy airport environment, complete with passengers, luggage carts, and shops, adds to the scene's vibrancy. Throughout the sequence, the director's joyful leap remains the focal point, encapsulating his spirited personality amidst the airport's lively atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1014
|
videos/HRA_part0/1014.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. There is distortion in the legs."
}
] |
seed42_1389
|
videos/HRA_part0/1389.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate nurse, clad in a blue uniform and wearing a stethoscope around her neck, leaps with exhilaration against a cosmic backdrop featuring an artist's impression of a recently discovered exoplanet. Simultaneously, a cobra, coiled and ready to strike, mimics the action of jumping, adding an unexpected element to the scene. Both figures, the nurse and the cobra, are captured mid-leap, their silhouettes outlined against the star-studded universe, creating a vivid contrast between human emotion and the raw power of nature, all set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The cobra did not appear in the video, and the character was not fully shown."
}
] |
seed44_2960
|
videos/HRA_part1/2960.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a blue jacket and jeans, walks purposefully across a vast, otherworldly landscape illuminated by the ethereal glow of a nearby galactic nebula. The scene opens with the student standing in the foreground, looking intently ahead, with the majestic nebula casting a soft, cosmic light over the terrain. As the student strides forward, the camera captures the detail of their journey, highlighting the unique features of the alien landscape. With each step, the student's determination is evident, their silhouette framed against the mesmerizing backdrop of the swirling nebula. The final shot lingers on the student's resolute figure, now further along the path, continuing their solitary trek under the watchful gaze of the celestial wonder above.]"
},
{
"from": "gpt",
"value": "Bad. The student's fingers in the video are deformed, and the face is generated blurry."
}
] |
seed44_2098
|
videos/HRA_part1/2098.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic 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": "Bad. The caption mentions a group of small fish scattering and fleeing behind a sailfish, but this scene does not appear in the video."
}
] |
seed44_2853
|
videos/HRA_part1/2853.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, adorned in a stylish leather jacket and holding a harmonica, walks alongside a dingo in a serene natural landscape. Both figures stroll leisurely, the musician's outfit complemented by faded jeans and a classic white T-shirt, while the dingo, with its reddish-brown fur, matches the earthy tones of the surroundings. They move in harmony, the musician occasionally playing the harmonica, creating a peaceful melody that resonates with the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The musician and the dingo's walking movements in the video are slightly unsmooth."
}
] |
seed44_1354
|
videos/HRA_part1/1354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic marlin breaches the shimmering turquoise waters of the open ocean, its sleek body glistening in the sunlight. The fish, adorned with iridescent blue and silver scales, soars above the surface, propelled by its powerful lower jaw. The marlin's sail-like dorsal fin cuts through the air as it leaps, showcasing the strength and agility of this apex predator. Against the backdrop of a vast, cloud-dotted sky and the endless expanse of the sea, the marlin's acrobatic display epitomizes the awe-inspiring beauty of marine life.]"
},
{
"from": "gpt",
"value": "Good. The action of the swordfish jumping out of the sea in the video is basically normal."
}
] |
seed42_1391
|
videos/HRA_part0/1391.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling a young Tom Hardy, wearing a futuristic space suit with a gorilla mascot emblem, embarks on an exhilarating lunar buggy ride across a desolate moon landscape, capturing the essence of adventure in outer space. Later, he is seen walking purposefully, leading the lunar buggy with ease, as if navigating through a challenging mission. The actor then pauses to admire the vast, starry expanse, evoking a sense of awe and wonder, before continuing his journey, showcasing determination and resilience. Throughout the scenes, the lunar buggy, with its distinctive design and rugged tires, remains a prominent feature, highlighting the vehicle's role in the astronaut's lunar exploration.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the gorilla emblem."
}
] |
seed42_1116
|
videos/HRA_part0/1116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer kneels on lush green grass, gently caressing a tiny vole with utmost care and tenderness. The officer, wearing a classic navy blue police uniform with a badge and a cap placed nearby, ensures the small creature feels safe and secure. The vole, with its delicate features and curious eyes, seems at ease in the presence of the compassionate law enforcement figure. The background is a serene park setting, with trees and a clear blue sky, highlighting the unexpected yet touching connection between the officer and the vole.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements are not smooth."
}
] |
seed46_2901
|
videos/HRA_part2/2901.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, agile mongoose, with its distinctive reddish-brown fur and sharp eyes, is seen crawling slowly through a dense grassland environment. It moves stealthily, its body hugging the ground, as it searches for prey or navigates its territory. The scene is set under the warm glow of the afternoon sun, casting long shadows and highlighting the mongoose's fur texture against the green backdrop. Its cautious movements and keen senses are evident as it crawls, making it appear both vulnerable and predator in the wild landscape.]"
},
{
"from": "gpt",
"value": "Normal. The body and limbs of the mongoose are deformed."
}
] |
seed46_2082
|
videos/HRA_part2/2082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chef, wearing a traditional white uniform and a tall hat, finds himself in an unexpected encounter with a bobcat. They stand on a dirt path winding through a dense forest, the sunlight filtering through the trees casting dappled shadows on the ground. The chef, holding a basket presumably filled with fresh ingredients, looks surprised yet calm as he meets the gaze of the wild feline. The bobcat, equally intrigued, pauses in its walking, standing tall on the path, its ears perked and tail swishing gently, as if acknowledging the chef's presence in its natural habitat. The two share a moment of mutual respect and curiosity before continuing on their respective paths, the chef moving forward with purpose and the bobcat melting back into the underbrush, both figures disappearing into the lush greenery of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The character's body movements in the video are uncoordinated, and the lynx's actions are not smooth."
}
] |
seed46_1151
|
videos/HRA_part2/1151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a black beret and glasses, sits at a cluttered desk in a dimly lit room, affectionately caressing a small bat perched on her finger. The bat, appearing relaxed and comfortable, is nestled against her hand, which is adorned with silver rings. The scene is set against a backdrop of bookshelves filled with various books, adding to the intellectual and mysterious atmosphere. The writer's other hand rests on a vintage typewriter, hinting at her profession, while the bat's presence introduces an element of the unusual into the intimate scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is deformed; the bat's head is deformed, and its wings are twisted."
}
] |
seed42_2743
|
videos/HRA_part0/2743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, equipped with a backpack, ascends a lush, green mountain trail, pausing occasionally to jot down thoughts in a small notebook. He wears a gray t-shirt, brown shorts, and sturdy hiking boots, while his glasses reflect the sunlight as he looks up at the dense forest canopy above. With a determined look, he continues climbing, passing by a wooden signpost indicating various trails. At one point, he stops to admire the view, taking in the breathtaking scenery of rolling hills and distant mountains, before resuming his upward journey, the camera capturing the vivid colors of nature surrounding him.]"
},
{
"from": "gpt",
"value": "Bad. The writer's face in the video is blurry, the fingers are deformed, and there are problems with the feet."
}
] |
seed42_1814
|
videos/HRA_part0/1814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large moose, adorned with a red bow tie and a top hat, stands on a wooden boardwalk illuminated by warm, golden lights. It gracefully sways side to side, as if dancing to an invisible melody, under a starlit night sky. The boardwalk stretches into the distance, lined with quaint shops and twinkling lanterns, creating a surreal and enchanting atmosphere where reality and fantasy blend seamlessly.]"
},
{
"from": "gpt",
"value": "Bad. The moose in the video has a twisted body, a distorted face, and twisted legs."
}
] |
seed44_2685
|
videos/HRA_part1/2685.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown leather jacket and dark jeans, stands in a rugged chaparral landscape, gesturing emphatically. He watches intently as a porcupine, quills fully displayed, jumps over a small log, showcasing its surprising agility in the wild environment. The director's focused stance and the porcupine's unexpected leap are framed by the chaparral vegetation, highlighting the unique interaction between human creativity and natural wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, hedgehog body, head, and legs are distorted in the video."
}
] |
seed44_1069
|
videos/HRA_part1/1069.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wildlife park worker, clad in khaki shorts, a green shirt, and a wide-brimmed hat, interacts closely with a hippopotamus in a large, naturalistic enclosure filled with clear, blue water. The worker confidently swims alongside the hippo, which floats gracefully on its back, showcasing the unique bond between caretaker and animal in a peaceful, sunlit setting. Moments later, the worker is seen playfully engaging with the hippopotamus, which swims submerged in the water, its eyes closed in apparent bliss, highlighting the trust and connection they share in their aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2785
|
videos/HRA_part0/2785.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 desert landscape, a well-dressed doctor, wearing a white coat, blue shirt, and khaki pants, stands next to a camel. The scene is set near traditional African villages, with huts visible in the background. The doctor, sporting a beard and glasses, holds a rope attached to the camel, which is adorned with red and blue blankets. Suddenly, the camel leaps into the air, its hind legs kicking up sand, while the doctor watches intently. The village scenery, complete with palm trees and thatched-roof huts, adds a cultural touch to this dynamic scene.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the camel leaping and its hind legs raising dust, but the movements are not very continuous and smooth, with abrupt changes."
}
] |
seed46_1925
|
videos/HRA_part2/1925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 mature male silverback gorilla, marked by a prominent sagittal crest and large, powerful body, crawls through dense, lush vegetation in a misty, mountainous habitat. His dark fur stands out against the vibrant greenery, and his expressive face, complete with attentive eyes and a strong jawline, conveys a sense of intelligence and strength. The scene is set in a protected wildlife reserve, where the gorilla moves purposefully through the undergrowth, highlighting the beauty and resilience of these endangered primates in their natural environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2809
|
videos/HRA_part2/2809.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, elegant restaurant, a cunning weasel, dressed in a crisp white waiter's outfit with a black bow tie, gracefully crawls across a wooden floor, passing beneath a table draped with a pristine white cloth. The weasel's sleek body and sharp features are accentuated by the warm glow of candlelight, casting dramatic shadows as it moves stealthily, weaving between the legs of ornate chairs. Its eyes gleam with mischief, hinting at some secretive mission unfolding among the unsuspecting diners.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's movements in the video are not smooth."
}
] |
seed46_1927
|
videos/HRA_part2/1927.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a casual green shirt and khaki pants, finds inspiration while leaping energetically onto a large rock in a lush forest setting, as if escaping the ordinary to explore the unknown. Nearby, an awe-inspiring mammoth, seemingly from another time, stands majestically under a canopy of ancient trees, its massive frame and textured skin adding an element of prehistoric wonder to the scene. The juxtaposition of the writer's leap and the mammoth's presence creates a surreal and captivating narrative, blending human creativity with the grandeur of nature's past.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2191
|
videos/HRA_part0/2191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A captivating scene unfolds, focusing solely on zebrafish within a clear, cylindrical fish tank. The vibrant striped patterns on the zebrafish stand out against the neutral background of the tank, which is devoid of any plants or decorations. The water is crystal clear, allowing every detail of the zebrafish, from their distinctive black and white stripes to their delicate fins, to be visible. The tank is illuminated by overhead lighting, casting a soft glow over the swimming zebrafish, highlighting their movement and the rippling effect they create in the water.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1105
|
videos/HRA_part2/1105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark uniform with a badge clearly visible, traverses a vast wetland landscape, the lush greenery contrasting sharply with his authoritative attire. He is seen wading through shallow water, his boots partially submerged, indicating a purposeful journey through this natural terrain. Moments later, he is fully immersed in swimming, his uniform now soaked, navigating the intricate network of waterways under a cloudy sky. This scene captures the unexpected sight of a law enforcement figure engaging with the wild, uncharted environment of the wetlands.]"
},
{
"from": "gpt",
"value": "Bad. The movements are somewhat uncoordinated, and it's hard to see the swimming actions."
}
] |
seed44_1030
|
videos/HRA_part1/1030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an expansive, arid landscape under a clear blue sky, a large red kangaroo stands on its hind legs amidst dry, yellow grass and scattered shrubs. It uses its forepaws to wipe across its face in a self-grooming gesture, highlighting its distinctive marsupial features and natural behaviors. The kangaroo's muscular tail supports its balance as it engages in this routine, offering a rare close-up view of its grooming habits in its native environment.]"
},
{
"from": "gpt",
"value": "Bad. Legs and tail show deformities."
}
] |
seed46_2834
|
videos/HRA_part2/2834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded musician, clad in a black leather jacket and jeans, performs an intense, passionate crawling motion across a vast, icy glacier landscape, his electric guitar amplifying the dramatic scene. The stark, snow-covered mountains and glaciers provide a breathtaking, icy backdrop, contrasting with the musician's raw energy. Throughout the sequence, he continues to crawl, his body language conveying determination and struggle, while the icy wilderness remains a constant, awe-inspiring presence.]"
},
{
"from": "gpt",
"value": "Normal. The musician's movements in the video are slightly unsmooth."
}
] |
seed44_1438
|
videos/HRA_part1/1438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a gray beanie, a dark jacket, and a checkered apron, stands against a vibrant blue wall, holding a large ladle as he stirs a bubbling pot. Moments later, he is seen attentively pouring oil into a pan, demonstrating culinary expertise. Then, he skillfully flips a food item in the pan, showcasing his cooking prowess, all while the blue wall and his attire remain consistent. Lastly, he is shown carefully seasoning the dish, his focus unwavering, against the same backdrop of the vivid blue wall and clad in the same attire, exemplifying his dedication to culinary artistry.]"
},
{
"from": "gpt",
"value": "Normal. The human hand appears deformed."
}
] |
seed42_2254
|
videos/HRA_part0/2254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, middle-aged with short, neatly trimmed brown hair and a well-groomed beard, pauses in his cleaning duties. Dressed in a dark green uniform with a name badge, he rests a mop against a pristine white wall. His eyes meet the camera, and he gives a slow, deliberate nod, acknowledging an unseen presence. The setting is a spotless, modern school hallway, with large windows casting soft light onto the polished floor, highlighting the cleanliness maintained by the janitor.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not move."
}
] |
seed46_1060
|
videos/HRA_part2/1060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patient, smiling teacher, dressed casually in a blue T-shirt and khaki shorts, tenderly bathes a small, brown dog in a white plastic tub placed atop a green picnic table, set against the backdrop of a lush, grassy park. The teacher, wearing a simple blue shirt and beige shorts, gently washes the dog, who looks content and relaxed. In another angle, the teacher, now seen from the back, continues to bathe the dog, demonstrating care and attention. Lastly, the teacher, still wearing the blue top and khaki bottoms, rinses the dog with a handheld showerhead, capturing the essence of a nurturing educator spending quality time with a beloved pet.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2692
|
videos/HRA_part1/2692.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warehouse district under a cloudy sky, a worker clad in a yellow vest and hard hat operates a compact yellow Bobcat excavator. The machine crawls carefully across the concrete floor, maneuvering through the tight spaces between towering stacks of pallets filled with cardboard boxes. The excavator's bucket is raised, ready to perform its task amidst the industrial environment, while the worker remains focused, guiding the machinery with precision.]"
},
{
"from": "gpt",
"value": "Normal. The excavator's movements in the video are slightly unsmooth."
}
] |
seed46_167
|
videos/HRA_part2/167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in period-specific attire from the late 1800s, including a brown shirt, brown trousers, and brown boots, explores historical sites in a rural setting. He crawls through dense grass to uncover ancient artifacts, revealing a deep interest in history. Against a backdrop of historical ruins, the farmer meticulously examines the site, emphasizing his connection to the land and its past. Throughout, he maintains a focused demeanor, highlighting his dedication to understanding the historical significance of the area.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's crawling motion in the video is not smooth and uncoordinated."
}
] |
seed46_2165
|
videos/HRA_part2/2165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, ancient-looking turtle with a mossy, textured shell slowly moves across a lush, green forest floor, surrounded by vibrant ferns and fallen leaves. Its wise, gentle eyes and wrinkled skin reflect its age and resilience. Nearby, a small stream glistens in the dappled sunlight, while tall trees tower overhead, creating a serene, natural habitat for this majestic creature. The turtle continues its unhurried journey, embodying the peaceful, enduring spirit of the forest.]"
},
{
"from": "gpt",
"value": "Normal. The turtle's eyes and claws in the video have generation issues."
}
] |
seed46_1445
|
videos/HRA_part2/1445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned with vibrant orange beads and feathers woven into its fur, dances gracefully in the dappled sunlight of a lush savanna. Its body moves fluidly to an unheard beat, each leap and twist a display of raw power and elegance. Surrounded by tall grass swaying gently in the breeze, the cheetah's every motion is captured in high definition, from the flex of its muscles to the gleam in its eyes, embodying the spirit of the wild in a captivating dance.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's body is twisted, its claws are twisted, its face is distorted, and its legs are twisted."
}
] |
seed46_132
|
videos/HRA_part2/132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, clad in a black turtleneck and jeans, sits on a stage, intently playing a marimba with mallets. Nearby, a gorilla, perhaps a part of the performance or installation art, is crawling on all fours, wearing a red beret and blue jeans, adding an unexpected element to the scene. The contrast between the focused human artist and the ape in casual attire creates a surreal and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The actions are mostly normal, but there is slight disharmony; the chimpanzee's movements of crawling on all fours are discontinuous and have abrupt changes."
}
] |
seed46_2409
|
videos/HRA_part2/2409.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the vibrant coral reef ecosystem, a pair of butterfly fish, characterized by their distinctive black stripes and oval-shaped bodies, gracefully swim among the colorful corals and anemones. One fish displays a striking yellow hue with bold black markings, while the other exhibits a more subdued brown and white pattern. They navigate the intricate underwater landscape, their movements synchronized, as they explore the nooks and crannies of the reef in search of food. The scene is illuminated by the filtered sunlight that penetrates the clear blue water, casting dappled light on the fish and their surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The facial and tail generation of the butterfly fish in the video has problems."
}
] |
seed42_1942
|
videos/HRA_part0/1942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a traditional white chef's uniform with a name tag reading \"Chef Tyler,\" sits at a wooden table in a rustic, candlelit dining room. He savors a spoonful of his signature dish, a creamy risotto, with eyes closed in blissful concentration. His neatly trimmed beard and mustache, along with short brown hair, add to his distinguished appearance. Behind him, a bustling restaurant kitchen is visible through an open doorway, offering a glimpse into the energetic culinary environment. Throughout the scene, Chef Tyler continues to enjoy his meal, occasionally glancing up with a satisfied smile, embodying the essence of a passionate and accomplished chef relishing his own creation.]"
},
{
"from": "gpt",
"value": "Normal. The chef in the video has uncoordinated movements while eating."
}
] |
seed42_129
|
videos/HRA_part0/129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An endearing otter, with wet brown fur and a charming face, is seen grooming itself in its natural habitat. It wipes its paw across its face in a cute and meticulous manner, showcasing its daily cleaning ritual. The otter is positioned against a backdrop of lush greenery and water, highlighting its wild environment. Throughout the scene, the otter continues to groom its whiskers and face, occasionally pausing to look around, offering a captivating glimpse into its world.]"
},
{
"from": "gpt",
"value": "Normal. The otter in the video is mostly shown wiping its face and paws, with only slight uncoordinated movements."
}
] |
seed42_1376
|
videos/HRA_part0/1376.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark uniform with a badge and a radio attached to his belt, stands with a serious expression in the middle of an urban street, partially illuminated by the glow of a streetlight. In the background, a large, gray wolf leaps over a chain-link fence in a single, powerful bound, its eyes locked onto something unseen beyond the frame. The scene captures the juxtaposition of law enforcement and untamed nature, with the officer's authoritative presence contrasted by the wolf's wild, instinctive leap.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there is a sudden change."
}
] |
seed42_1519
|
videos/HRA_part0/1519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished middle-aged doctor, wearing a white lab coat over a navy blue shirt, sits in a cozy, dimly lit pub, sipping a glass of red wine. The pub is filled with the warm glow of hanging lights and a fireplace, creating a relaxed atmosphere. The doctor, with short brown hair and a neatly trimmed beard, leans back in his chair, holding the stem of the wineglass, and gazes thoughtfully into the distance. The scene conveys a sense of calm and tranquility, with the doctor enjoying a moment of respite from his busy medical career.]"
},
{
"from": "gpt",
"value": "Bad. The video mentioned in the caption does not show the tasting of red wine."
}
] |
seed44_1133
|
videos/HRA_part1/1133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dromedary camel, marked with dark spots, runs across a barren desert landscape under a hazy sky, its large, leathery feet kicking up puffs of sand with each stride. It wears a simple, rustic saddle adorned with red and white striped fabric, fluttering in the wind as the camel sprints. In the distance, the outlines of shrubs and distant mountains provide a sense of scale, emphasizing the vastness of the desert environment. The camel's powerful legs and muscular build are highlighted as it maintains its steady, fast pace through the sandy terrain.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2896
|
videos/HRA_part0/2896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 heartwarming scene, two people, a male and a female, are shown gently caressing a baby rhinoceros in a natural habitat, surrounded by lush greenery. The couple, both wearing khaki safari gear, including shirts, pants, and hats, interact tenderly with the young rhino, which is standing on sandy soil. The man strokes the rhino's back while the woman looks on, both expressing deep affection and care for the animal. The setting, with its vibrant vegetation and clear blue sky, adds to the peaceful and nurturing atmosphere of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_133
|
videos/HRA_part2/133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, standing in a lush, green meadow dotted with vibrant wildflowers, shakes its body vigorously to rid itself of water, its fur rippling and droplets flying in slow motion against the serene landscape. The wolf, with piercing yellow eyes, then looks directly at the camera, its powerful presence commanding attention against the backdrop of nature's beauty. After shaking, it stands still, water dripping from its thick fur, with the sun casting a warm glow on the scene, highlighting the wolf's resilience and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1509
|
videos/HRA_part0/1509.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense forest setting, a majestic stag with an impressive set of antlers leads a herd of deer through a narrow path, their movements graceful and unhurried. The camera captures their journey from a low angle, emphasizing the size and strength of the animals. The lush greenery surrounds them, providing a natural backdrop that complements their brown coats. As they walk, the sound of their hooves softly hitting the ground echoes through the woods, creating a serene atmosphere. The herd moves with purpose, navigating the terrain with ease, highlighting the beauty and resilience of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1509
|
videos/HRA_part2/1509.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense forest setting, a majestic stag with an impressive set of antlers leads a herd of deer through a narrow path, their movements graceful and unhurried. The camera captures their journey from a low angle, emphasizing the size and strength of the animals. The lush greenery surrounds them, providing a natural backdrop that complements their brown coats. As they walk, the sound of their hooves softly hitting the ground echoes through the woods, creating a serene atmosphere. The herd moves with purpose, navigating the terrain with ease, highlighting the beauty and resilience of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The deer's legs are deformed, and the deer in the background are also deformed."
}
] |
seed44_1850
|
videos/HRA_part1/1850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a green apron over a casual outfit, stands in a pet store, carefully washing a small brown dog in a white tub. The dog, on a leash, looks relaxed and happy, sitting in soapy water while the cashier, sporting a stylish bun hairstyle, uses a handheld showerhead to rinse the suds away. The scene is set against a backdrop of pet supplies and products, creating a vibrant and welcoming environment. The cashier's warm smile and gentle touch convey a sense of care and affection for the animal, making it a heartwarming moment captured on video.]"
},
{
"from": "gpt",
"value": "Bad. The dog's head in the video is generated incorrectly, and an extra hand is floating in the air, which is very uncoordinated;"
}
] |
seed46_1877
|
videos/HRA_part2/1877.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by soft purple and blue lights, a woman with curly brown hair, styled in a bun, wears a silver sleeveless dress and silver earrings. She gently caresses a large, textured, abstract artwork, the colors of which resemble cosmic nebulas, while standing on a transparent floor that reveals city lights below. The walls are lined with similar cosmic-themed art pieces, creating an immersive environment. She leans toward the artwork, her expression showing deep appreciation, as she stands on the glowing, see-through floor, with the dazzling cityscape visible beneath her feet.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1343
|
videos/HRA_part2/1343.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic scene, a brave firefighter, clad in full gear and a helmet, runs through a dense cosmic dust storm that engulfs a desolate landscape. The storm, swirling with hues of orange and red, is illuminated by an ethereal glow from above, casting an otherworldly light on the surroundings. As the firefighter dashes forward, a majestic buffalo emerges from the storm, its silhouette powerful against the cosmic backdrop. Both figures, the firefighter and the buffalo, embody resilience and strength as they navigate the chaotic environment, creating a striking visual narrative of survival against all odds.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth, and the bison's movements are not smooth."
}
] |
seed46_2952
|
videos/HRA_part2/2952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown leather jacket and dark pants, kneels on a wooden floor, engaged in a crawling motion, as he observes a live hare sitting on a white table nearby. The scene is set indoors, with a large window in the background, allowing natural light to illuminate the room. The director's intent gaze and careful movement convey a sense of focus and determination as he studies the animal, which remains calm and still, seemingly unfazed by the presence of the human.]"
},
{
"from": "gpt",
"value": "Bad. The director's hands and feet in the video are generated deformed."
}
] |
seed42_2567
|
videos/HRA_part0/2567.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, 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 no issues."
}
] |
seed46_1193
|
videos/HRA_part2/1193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, young female teacher dances joyfully on a wide, sandy beach, her bare feet sinking into the warm sand as she moves. Dressed in a vibrant, floral-print sundress and a denim jacket, she twirls with her arms extended, embracing the freedom and beauty of the seaside. The sun casts a golden glow on the beach, highlighting her graceful silhouette as she dances with abandon, surrounded by the vast, serene ocean and clear, blue skies. Her carefree spirit and the stunning beach scenery create a captivating, uplifting scene.]"
},
{
"from": "gpt",
"value": "Normal. The female teacher in the video has uncoordinated dance moves."
}
] |
seed42_1882
|
videos/HRA_part0/1882.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated female nurse, clad in a white uniform and wearing her hair in a bun, attentively checks a smoke detector mounted on the ceiling in a modern hospital hallway. The space is pristine and well-lit, with pale green walls and white trim, exuding a sense of cleanliness and professionalism. The nurse, displaying her commitment to safety, uses a long, red-handled tool to test the device, ensuring it functions properly in the healthcare environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_2813
|
videos/HRA_part2/2813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badge and a hat, stands next to a large, brown buffalo with a red saddle. The officer gently wipes the buffalo's face with a white cloth, showing care and attention. The scene takes place in a rural setting, with wooden fences and green fields stretching into the distance. The buffalo, with its massive horns and calm demeanor, contrasts with the authoritative presence of the police officer, creating an unusual yet harmonious image.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1480
|
videos/HRA_part2/1480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a large hippopotamus walks along a riverbank, its massive body glistening under the sun, with industrial factories looming in the background. The scene opens with a wide shot of the river, where the hippo emerges from the water, its wet skin reflecting the sunlight. It then proceeds to walk along the riverbank, its powerful legs propelling it forward, as it passes by the factories, which emit plumes of smoke into the sky. The camera focuses on the hippo's movements, capturing its every step as it traverses this unusual landscape, the factories serving as a stark contrast to the natural beauty of the animal.]"
},
{
"from": "gpt",
"value": "Bad. The hippopotamus in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed46_2401
|
videos/HRA_part2/2401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, athletic woman with a pixie haircut, wearing a blue t-shirt and khaki cargo pants, kneels on a concrete floor in a garage. She focuses intently on repairing a mountain bike, her tools spread out on a red mat beside her. Her blue scrubs, adorned with colorful medical symbols, hint at her profession as a nurse. In another angle, she lifts the bike, revealing her strength and determination. Throughout, she exhibits a confident smile, demonstrating her dual passions for healthcare and cycling. The garage space is filled with various tools and equipment, emphasizing her hands-on approach to both her work and hobbies.]"
},
{
"from": "gpt",
"value": "Normal. The woman's actions of repairing and lifting the bicycle in the video are basically normal, but there is some lack of coordination."
}
] |
seed46_2785
|
videos/HRA_part2/2785.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 desert landscape, a well-dressed doctor, wearing a white coat, blue shirt, and khaki pants, stands next to a camel. The scene is set near traditional African villages, with huts visible in the background. The doctor, sporting a beard and glasses, holds a rope attached to the camel, which is adorned with red and blue blankets. Suddenly, the camel leaps into the air, its hind legs kicking up sand, while the doctor watches intently. The village scenery, complete with palm trees and thatched-roof huts, adds a cultural touch to this dynamic scene.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the camel leaping and its hind legs kicking up dust, but the action is not very continuous and smooth, with abrupt changes."
}
] |
seed44_1347
|
videos/HRA_part1/1347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged doctor with short, neatly styled brown hair, wearing a white lab coat over a blue button-up shirt and khaki pants, is comforting a crying young patient. The child, dressed in a yellow T-shirt and blue shorts, sits on a medical examination table, clutching a stuffed animal, while the doctor gently places a reassuring hand on the child's shoulder. The scene takes place in a brightly lit clinic room, with medical posters on the walls and a computer screen visible in the background. The doctor's empathetic expression and the child's teary face convey a moment of vulnerability and care in a clinical setting.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's hand appears deformed, with a third hand appearing."
}
] |
seed46_1990
|
videos/HRA_part2/1990.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a majestic raven perched on a branch, its glossy black feathers shimmering under the sunlight, revealing hints of blue and green. The bird has striking yellow eyes that seem to hold a world of wisdom. Its beak is curved and sharp, a testament to its carnivorous nature. The raven is surrounded by lush green foliage, and in the background, misty mountains add to the mystical atmosphere. Occasionally, the raven caws, a deep, resonant sound that echoes through the dense forest, asserting its presence in the serene wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The text does not describe the action, but the video generates the action of a crow turning its head to look around, which is basically normal but slightly uncoordinated."
}
] |
seed44_2399
|
videos/HRA_part1/2399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, industrial-style hallway, a janitor wearing a yellow vest and holding a mop walks purposefully toward the camera. Behind him, a theoretical spectacle unfolds: a white hole explosion, depicted as an intense burst of light and energy, engulfs the far end of the corridor, creating a dramatic contrast to the mundane setting. The janitor's steady pace and resolute expression suggest an intriguing juxtaposition between the cosmic event and his daily routine.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's walking movements are slightly uncoordinated."
}
] |
seed42_2478
|
videos/HRA_part0/2478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 attractive male actor, wearing a black t-shirt, showcases a ferret jumping from his right shoulder onto his left arm. Set against a dark grey background, the scene highlights the ferret's agility and the actor's engagement with the small animal. The actor's facial expression conveys amusement and surprise, emphasizing the playful interaction between man and pet. Throughout the sequence, the ferret performs several jumps, each time landing gracefully on different parts of the actor's body, while he remains fully engaged and attentive, his black t-shirt providing a stark contrast against the neutral backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's jumping movements in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed44_2367
|
videos/HRA_part1/2367.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, known for his mastery of the banjo, takes a break from his art to sweep his wooden porch on a sunny day. Dressed casually in a gray shirt and khaki pants, he methodically sweeps with a broom made of natural fibers, revealing the clean, weathered wood beneath. The porch, adorned with potted plants and a rustic rocking chair, overlooks a lush garden filled with vibrant flowers and greenery. In the background, a vintage acoustic guitar leans against the wall, hinting at the musician's passion for music, while the peaceful, suburban neighborhood provides a serene setting for this ordinary yet captivating task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2111
|
videos/HRA_part0/2111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young siblings, a boy and a girl, both wearing casual clothes and with distinct hairstyles, are seen in a modern kitchen with wooden floors and white cabinets. The boy, wearing a blue striped shirt and brown pants, reaches into a large, open dishwasher to unload plates, while the girl, in a pink dress and white socks, stands on tiptoe to put glasses away in a high cabinet. The kitchen features a large window with a view of greenery outside, adding a splash of natural light to the scene. The siblings work together, the boy passing items to the girl, who carefully places them in their respective spots, showcasing their teamwork and responsibility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1957
|
videos/HRA_part0/1957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly lit classroom, a biology teacher, wearing a green button-down shirt and khaki pants, kneels on the floor with a focused gaze. A live lizard, displaying intricate patterns, crawls across the tabletop in front of him. The teacher's hands are positioned ready to guide the creature gently, ensuring its safety during this educational demonstration. Students observe intently from their desks, their faces a mix of fascination and mild concern, as the small lizard explores its temporary environment under the watchful eye of their knowledgeable instructor.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's hand movements in the video are not smooth, and the lizard's crawling motion is not obvious."
}
] |
seed42_1510
|
videos/HRA_part0/1510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, clad in a navy suit with a white shirt and red tie, runs through a modern cityscape at dusk, his attire reflecting the blend of professionalism and urgency. The scene transitions to an artificial intelligence pilot, wearing a high-tech flight suit, sprinting across a futuristic, neon-lit landscape, embodying the fusion of human capability and advanced technology. Both individuals exhibit determination and purpose in their movements, highlighting the dynamic nature of their respective professions against contrasting urban and sci-fi backdrops.]"
},
{
"from": "gpt",
"value": "Bad. The hands and legs appear deformed."
}
] |
seed42_1680
|
videos/HRA_part0/1680.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 swordfish, distinguished by its elongated, sword-like upper jaw, glides gracefully through the clear, turquoise waters of the open ocean. Its sleek, metallic blue body shimmers as it swims, propelled by a powerful tail fin. The fish is seen from various angles, showcasing its impressive size and streamlined shape designed for speed. At one point, it leaps out of the water, displaying its agility and strength, before plunging back into the depths, leaving a trail of shimmering ripples on the ocean surface.]"
},
{
"from": "gpt",
"value": "Normal. The swordfish's mouth in the video is generated unreasonably, and the fins are of different sizes."
}
] |
seed42_1676
|
videos/HRA_part0/1676.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, attractive female nurse, wearing a white uniform and her hair in a bun, yawns widely while standing alone in a brightly lit hospital hallway. She is seen from different angles, first yawning with her eyes closed, then covering her mouth with her right hand, followed by a close-up of her face showing tired eyes. Lastly, she is captured yawning again, revealing her exhaustion, all within the sterile, well-lit corridor of the medical facility.]"
},
{
"from": "gpt",
"value": "Bad. The face and hands of the character in the video are poorly generated."
}
] |
seed44_3099
|
videos/HRA_part1/3099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savannah dotted with distant acacia trees, a large herd of African cape buffaloes gathers. The scene opens with a panoramic view of the herd, then zooms in on two buffaloes standing face-to-face, seemingly engaged in a dance-like interaction. The dominant male, with massive horns and a thick mane, takes a step forward, while the other male responds with a matching step, creating a rhythmic pattern. They continue this 'dance', mirroring each other's movements against the serene backdrop of the savannah, the clear blue sky, and the distant horizon, evoking a sense of primal connection and ritual within the herd.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1728
|
videos/HRA_part1/1728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female barista, wearing a gray apron over a black shirt, completes a transaction with a customer at a contemporary coffee shop. The cafe features wooden floors, a glass cooler, and a large digital menu display. After the sale, she turns to prepare a coffee beverage, carefully measuring ingredients into a French press. With practiced movements, she adds hot water from a stainless steel kettle and stirs the mixture. The barista then pours the freshly brewed coffee into a white ceramic cup, adding a touch of foam art on top before presenting it to the customer with a warm smile. Throughout the process, the cafe's modern decor, including high-top tables and minimalist chairs, provides a backdrop to the barista's efficient and skilled routine.]"
},
{
"from": "gpt",
"value": "Normal. No customer generation, glass refrigerated display cases, large digital menu screens, stainless steel water kettles."
}
] |
seed44_2859
|
videos/HRA_part1/2859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal cinematic scene, a majestic buffalo leaps gracefully over a row of vintage cinema seats, its powerful muscles straining against the force of gravity. The buffalo, with its shaggy brown fur and large horns, seems unfazed by the unusual setting, focusing solely on the jump. The cinema seats, arranged neatly in rows, are old-fashioned, with red upholstery and gold accents, creating a striking contrast against the buffalo's wild nature. The room is dimly lit, casting dramatic shadows on the walls and floor, emphasizing the buffalo's impressive leap. The air is filled with tension and anticipation as the buffalo soars through the air, its hooves inches from touching the seat backs. This captivating scene combines elements of nature and culture in a way that challenges traditional boundaries and expectations.]"
},
{
"from": "gpt",
"value": "Bad. The body is twisted, the head is twisted, and the feet are twisted."
}
] |
seed46_1662
|
videos/HRA_part2/1662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant zoological park, a woman wearing a yellow jacket and khaki pants runs along a winding path surrounded by lush greenery. As she moves, her attention is drawn to an adorable hedgehog scurrying across the trail, its tiny feet moving swiftly beneath its spiky exterior. The hedgehog pauses for a moment, looking up at the woman with curious eyes before continuing on its way, blending into the underbrush. The woman, smiling at the encounter, resumes her run, passing by various enclosures housing majestic animals, all set against the backdrop of a sunny day in the sprawling park.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video is distorted, with twisted arms, legs, and a contorted face of the little hedgehog."
}
] |
seed44_174
|
videos/HRA_part1/174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest setting, a mature monkey tenderly caresses a smaller monkey, possibly its child, against a backdrop of vibrant foliage and dappled sunlight. The older monkey, with a fur color that appears dark brown or black, gently holds the smaller monkey, whose fur is lighter in color, perhaps blonde or sandy. The interaction is intimate and caring, with both monkeys seated on a branch amid the dense vegetation. This heartwarming scene captures the essence of primate affection in their natural habitat, surrounded by the rich textures and colors of the forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The facial and hand generation of the monkeys in the video is problematic."
}
] |
seed42_2834
|
videos/HRA_part0/2834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded musician, clad in a black leather jacket and jeans, performs an intense, passionate crawling motion across a vast, icy glacier landscape, his electric guitar amplifying the dramatic scene. The stark, snow-covered mountains and glaciers provide a breathtaking, icy backdrop, contrasting with the musician's raw energy. Throughout the sequence, he continues to crawl, his body language conveying determination and struggle, while the icy wilderness remains a constant, awe-inspiring presence.]"
},
{
"from": "gpt",
"value": "Bad. The musician's face, hands, arms, legs, and the instrument in their hands are distorted in the video."
}
] |
seed44_1138
|
videos/HRA_part1/1138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a yellow raincoat and clutching a large sketchbook, walks through a lush botanical garden filled with vibrant greenery and colorful flowers. A curious vole scampers across the path ahead of her, its presence adding a touch of whimsy to the serene environment. The artist pauses, observing the small creature before continuing her leisurely stroll, the intricate details of the garden's foliage providing inspiration for her artwork. The scene is framed by towering trees and the sounds of nature, creating a peaceful atmosphere as the artist explores the beauty of the botanical gardens.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3059
|
videos/HRA_part2/3059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, dressed in a yellow high-visibility jacket and blue jeans, stands near a buffalo swimming in a serene, placid lake, surrounded by lush greenery. The buffalo, with its massive frame and shaggy coat, gracefully paddles through the clear water, creating ripples that extend outward. In the background, a wooden pier extends into the lake, and tall trees line the shore, providing shade and a sense of serenity. The janitor looks on, perhaps during a break from his duties, observing the buffalo in its natural habitat, a harmonious blend of nature and human presence.]"
},
{
"from": "gpt",
"value": "Normal. The buffalo's head generation in the video has problems, and the limbs are generated in incorrect positions."
}
] |
seed46_1385
|
videos/HRA_part2/1385.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a whole, raw Atlantic cod fish, eyes glassy and intact, laid upon a bed of ice chips, its skin shimmering under bright market lights. The fish is sizable, with a length suggesting it weighs several pounds, and is presented head-on, showcasing its freshness in a fishmonger's display. The setting is a bustling, open-air market, with other seafood visible in the background, emphasizing the variety and vibrancy of the scene. The cod's mouth is slightly agape, and its body lies across the ice, evoking the traditional presentation of fresh catches in coastal communities.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2793
|
videos/HRA_part1/2793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a crisp, white lab coat over a blue shirt and khaki pants, leaps playfully along a weathered boardwalk by the ocean, his stethoscope swinging freely. The setting sun casts a golden hue over the scene, highlighting the contrast between his professional attire and the casual, joyful activity. The boardwalk, lined with aged wooden planks, extends into the distance, offering a picturesque view of the shoreline and the sea beyond. The doctor's action, captured mid-jump, conveys a sense of freedom and happiness, juxtaposed against the typically serious context associated with medical professionals.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2182
|
videos/HRA_part1/2182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated nurse, wearing a classic white uniform and cap, is seen attentively checking a series of smoke detectors in a pristine hospital corridor. She methodically inspects each device, her actions conveying a sense of responsibility and care for patient safety. With a focused gaze and a tool in hand, she demonstrates her commitment to ensuring that the smoke alarms are functioning properly, maintaining a vigilant stance against potential hazards in the healthcare facility. Throughout the process, she moves from one detector to another, her white shoes echoing softly on the polished floor, reinforcing the importance of routine safety checks in a medical environment.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show any tools being generated."
}
] |
seed44_2719
|
videos/HRA_part1/2719.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station adorned with lavish decorations for an extravagant wedding, a neatly-dressed cashier, wearing a classic black vest and bow tie, diligently wipes the immaculate glass counter with a small cloth. The backdrop features elegant table settings, floral arrangements, and a large, illuminated dance floor, all indicative of an upscale celebration. The cashier's meticulous attention to detail ensures the space station's cash register area remains spotless amidst the grand festivities.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's fingers are deformed, the arm is incomplete, and the face is distorted."
}
] |
seed44_2684
|
videos/HRA_part1/2684.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heroic firefighter, clad in full gear and a yellow helmet, stands in a lush, green forest near a majestic waterfall, holding a gerbil gently in his hands. He carefully wipes water from the small animal's face, ensuring its safety, as the waterfall cascades powerfully in the background, creating a dramatic contrast between the tender moment and the raw force of nature.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's movements in the video are very uncoordinated, and the firefighter's actions are slightly uncoordinated."
}
] |
seed46_1061
|
videos/HRA_part2/1061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a yellow shirt and black pants, is seen carefully cleaning a large aquarium filled with vibrant fish. The room is bright, with natural light pouring in from a nearby window, highlighting the diligent task at hand. The student, with a focused expression, uses a specialized tool to gently scrub the inside walls of the tank, ensuring a safe and clean environment for the aquatic inhabitants. The fish, undisturbed, swim gracefully around the student's hand, adding a serene element to the scene. The background features educational posters and shelves filled with books, emphasizing the academic setting of this meticulous activity.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.