video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1891
|
videos/HRA_part0/1891.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling 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": "Bad. The panda man's arms and legs are twisted, the surrounding crowd's bodies and faces are distorted."
}
] |
seed42_2338
|
videos/HRA_part0/2338.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an assortment of smaller fish. The grouper, distinguished by its size and spotted brown skin, explores its surroundings with a sense of ownership, occasionally pausing to inspect something of interest. Its powerful body and broad fins propel it through the crystal-clear waters, showcasing the serene beauty of life beneath the ocean's surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_271
|
videos/HRA_part2/271.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 a brown shirt, interacts with a moose in a serene lake, both swimming together in the cool, clear water. The scene opens with the worker paddling gently, the moose swimming nearby, and lush greenery framing the tranquil waterscape. Next, the worker and the moose are seen swimming side by side, the man's safety vest and the moose's large antlers clearly visible above water. Then, the worker, still in his yellow safety vest, blue jeans, and brown shirt, floats on his back, the moose swimming peacefully beside him. Finally, the two unlikely companions, the worker in his distinctive attire and the majestic moose, continue to swim together in harmony, the peaceful lake and verdant surroundings creating a picturesque setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_2997
|
videos/HRA_part0/2997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush tropical dry forest, two smiling children, a boy and a girl, are seen caressing a friendly wild animal, possibly a capybara, against the backdrop of a dense forest with tall trees and patches of sunlight filtering through the leaves. The children wear simple clothing suitable for outdoor adventures, and their joyful expressions convey a sense of connection with nature. They sit on the forest floor covered with dry leaves and twigs, surrounded by various plants and vegetation typical of a tropical dry forest environment. The scene captures a tender moment of human-animal interaction in a natural setting, highlighting the innocence and curiosity of childhood amidst the wonders of the natural world.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2977
|
videos/HRA_part2/2977.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned worker, donning a brown jacket and blue jeans, leads a strong, brown horse by a red halter, walking together in unison on a dirt path. The pair moves at a steady pace, the man guiding the horse with care and respect. The horse, with its muscular build and glossy coat, follows obediently, the two sharing a bond reflective of their partnership. The setting is a rural landscape, with distant hills and trees providing a serene backdrop to their peaceful walk.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_21
|
videos/HRA_part2/21.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man with short brown hair, wearing a khaki safari shirt and matching trousers, stands in a lush, verdant enclosure at a wildlife sanctuary. He gently caresses the wrinkled, gray skin of a large hippopotamus, which towers over him, standing on its hind legs with its front paws on the man's shoulders. The man looks up at the creature with a mixture of awe and tenderness, while the hippo appears relaxed and comfortable with the interaction. The enclosure is filled with tall grasses and scattered trees, providing a natural habitat for the animal, and the man's presence suggests a close bond between human caretaker and wild creature.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and hippo in the video were generated abnormally."
}
] |
seed42_2606
|
videos/HRA_part0/2606.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, spotted jaguar leaps powerfully across a narrow stream in a lush, green rainforest, its muscles rippling beneath golden-brown fur, with water droplets splashing upwards. The big cat's intense gaze is fixed ahead, showcasing its agility and grace in motion against the vibrant jungle setting, complete with lush vegetation and the misty atmosphere of the rainforest environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2319
|
videos/HRA_part2/2319.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-themed setting, a large, friendly capybara wearing a golden astronaut helmet embarks on a diplomatic mission. The capybara, donning a silver spacesuit and a golden astronaut helmet, crawls purposefully across a metallic space station floor, surrounded by high-tech equipment and screens displaying cosmic visuals. Its determined gaze and deliberate movements convey the importance of its interstellar diplomatic task. Nearby, alien delegates watch curiously, their various forms and colors contrasting with the capybara's brown fur and the sterile environment. The scene conveys a sense of unity and cooperation among different species in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1970
|
videos/HRA_part0/1970.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, takes a break from his laborious tasks to sketch on a piece of paper, seated on a wooden beam at a construction site bustling with activity. Amidst the backdrop of unfinished buildings and heavy machinery, he focuses intently on his art, revealing a moment of unexpected creativity in the midst of a gritty urban environment. The scene captures his dedication to both his profession and his passion, offering a glimpse into the dual nature of his daily life.]"
},
{
"from": "gpt",
"value": "Normal. The worker's movements in the video while creating on paper are basically normal, with only slight awkwardness."
}
] |
seed46_2658
|
videos/HRA_part2/2658.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a dark green shirt, beige shorts, and a brown belt, is seen meticulously dusting vintage furniture within a grand room filled with antique artifacts. He pauses to adjust his glasses, revealing a look of deep concentration. His gaze then shifts to a large painting hanging on the wall, as if contemplating its significance. The director continues his task, now focusing on a wooden cabinet, his movements deliberate and precise, demonstrating his attention to detail. Lastly, he inspects a polished table, his reflection visible in its gleaming surface, as he ensures every inch is free from dust, all the while remaining in the same room with its collection of cherished items.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video, as well as the item they are holding."
}
] |
seed44_1897
|
videos/HRA_part1/1897.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 depiction, a gray and white cat, wearing a miniature spacesuit complete with a gold badge, is seen floating weightlessly in a spaceship, its paws gently touching a control panel. The cat, named Ambassador Fluff, is on a diplomatic mission among the stars, representing Earth's feline population. As zero-gravity music plays, the cat begins to dance, its movements fluid and graceful in the microgravity environment, embodying the spirit of intergalactic diplomacy through the universal language of dance. Behind Ambassador Fluff, a view of distant galaxies and nebulae can be seen through the spaceship's windows, adding to the surreal and majestic atmosphere of this cosmic dance.]"
},
{
"from": "gpt",
"value": "Bad. The cat's body is twisted, the arms are twisted, the paws are twisted, the face is twisted, and the legs are twisted."
}
] |
seed42_2121
|
videos/HRA_part0/2121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small hamster, characterized by its golden-brown fur and tiny ears, energetically jumps across wooden dock planks by a serene lake, surrounded by lush greenery. The hamster's miniature size contrasts with the vast, natural setting, creating a whimsical scene. Its movements are agile and lively, as it leaps from one dock plank to another, showcasing its playful spirit against the backdrop of a peaceful lakeside environment.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's movement in the video is very unsmooth, and the actions are uncoordinated."
}
] |
seed44_2091
|
videos/HRA_part1/2091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student wearing a gray sweater and black jeans sits in a classroom, wiping the surface of a large, advanced telescope with a cloth, as if preparing it for use. The room is dimly lit, with a projector screen displaying images of deep space in the background. The student's focus is intense, their actions deliberate, as they handle the telescope with care, its size and complexity suggesting it is used for serious astronomical research or communication. The overall scene conveys a sense of dedication and curiosity about the mysteries of the universe.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1812
|
videos/HRA_part0/1812.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, recognized by her messy red hair and paint-splattered white apron over a yellow dress, scrubs the bathroom floor with vigor, her face expressing determination. She uses a green scrub brush and a blue bucket filled with soapy water, set against a backdrop of white tiles. The scene conveys the juxtaposition of creativity and mundane chores, as she kneels on the floor, her hands stained with dirt and her sleeves rolled up, highlighting the physical effort involved in cleaning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1798
|
videos/HRA_part1/1798.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a green shirt and khaki shorts, tends to a lush garden filled with vibrant flowers and greenery. He strums his acoustic guitar, creating a melodic soundtrack for his gardening endeavors. The garden is brimming with life, featuring an array of colorful flowers such as daisies, roses, and tulips. The musician, wearing a wide-brimmed straw hat and sunglasses, works diligently, watering plants and trimming bushes. As he gardens, he occasionally pauses to play his guitar, seamlessly blending his passions for music and nature in a harmonious outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and legs are distorted in the video."
}
] |
seed46_2173
|
videos/HRA_part2/2173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, identifiable by its distinctive facial stripes and grizzled gray fur, swims through clear, calm water, showcasing its swimming abilities as it propels itself forward with powerful strokes. Its face is partially submerged, displaying its wet snout and closed eyes, indicating its focus on navigating underwater. The badger's body is fully visible, revealing its muscular build and the water droplets clinging to its fur, highlighting its natural habitat and aquatic skills. The scene is set in a peaceful, natural environment, with the badger's swimming motion captured in detail against a backdrop of still water and lush vegetation.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1010
|
videos/HRA_part1/1010.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, dressed in a dark gray jacket and light gray shirt, sits at a desk in a space hotel room, the Earth visible through the window behind him. He wipes the screen of his laptop with a cloth, revealing the reflection of the planet. The room is illuminated by soft, ambient light, giving it a futuristic yet cozy feel. The writer's focused expression and the clean, high-tech environment convey a sense of dedication and precision in his work, all set against the backdrop of the majestic Earth, which fills the large window behind him.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2524
|
videos/HRA_part2/2524.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 young, cheerful cashier, wearing a green apron over a striped shirt, is seen enjoying a swim in a clear, tranquil body of water surrounded by scrublands. The cashier, with short, wavy hair and a nose ring, alternates between swimming and floating on the water's surface, showcasing a sense of freedom and relaxation. The scrublands, with their sparse vegetation and sandy soil, provide a stark contrast to the refreshing water, creating a unique and captivating scene. Throughout, the cashier's attire remains consistent, featuring the green apron and striped shirt, as they immerse themselves in the peaceful environment.]"
},
{
"from": "gpt",
"value": "Normal. The cashier in the video does not have any obvious water-drawing actions."
}
] |
seed42_2217
|
videos/HRA_part0/2217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed writer, wearing a gray t-shirt, sits at a desk in a modern, minimally decorated room with large windows and a wooden floor, yawning widely as he leans back in his chair. The room is sparsely furnished, featuring a desk lamp and a painting on the wall. As the scene progresses, the yawning writer, now seen from the side, wears a black cap and glasses, revealing more of his appearance. He continues to yawn, appearing tired yet relaxed, as he rests his head on his hand, gazing out the window. Throughout, the setting remains a contemporary space with ample natural light and simple decor.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed42_2838
|
videos/HRA_part0/2838.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate history teacher, dressed in period costume from the Renaissance era, conducts an engaging lesson at a historical site, a grand stone castle surrounded by lush greenery. The teacher, wearing a brown velvet dress and a white lace collar, begins the class by gesturing dramatically towards the ancient stone walls, captivating the students' attention. Suddenly, the teacher breaks into an elegant Renaissance dance, twirling gracefully on the cobblestone courtyard, demonstrating the cultural significance of dance in historical context. The students, inspired by the teacher's enthusiasm, join in, forming a circle around her, as they learn about the rich history and culture of the era through the art of dance.]"
},
{
"from": "gpt",
"value": "Bad. The woman's face in the video is deformed, with missing parts on her arms and feet, and her body is distorted."
}
] |
seed44_1750
|
videos/HRA_part1/1750.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, energetic ferret clad in a miniature red cape sprints across the frame, set against the backdrop of an otherworldly landscape featuring two active volcanoes, one spewing a spectacular eruption of lava and ash into the twilight sky. The ferret, displaying a sense of urgency and adventure, runs through this dramatic scene, its path illuminated by the orange glow from the volcanic activity, creating a surreal and captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Bad. The ferret in the video has a twisted body, twisted paws, a distorted face, and twisted legs."
}
] |
seed46_1567
|
videos/HRA_part2/1567.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant garden filled with vibrant flowers and greenery, two young children, a boy and a girl, are happily engaged in gardening activities under a clear blue sky. The boy, wearing a red shirt and khaki shorts, attentively waters plants with a small watering can, while the girl, clad in a pink dress and white shoes, diligently digs soil using a tiny shovel. They both wear wide-brimmed hats to shield them from the sun. Nearby, a wooden bench sits beside a stone walkway, and a white picket fence surrounds the garden, completing the idyllic scene of youthful enthusiasm and nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_302
|
videos/HRA_part0/302.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a yellow apron over his gray shirt and dark pants, diligently scrubs a bathroom floor with a green cleaning solution, using a large, round scrub brush. The bathroom is modern, featuring white walls, a white toilet, and a white sink. The man's focused expression and the steam from the hot water convey his determination to clean. In the next shot, he is seen squeezing out the dirty water from the mop into a large, rectangular bucket. Finally, he pauses to wipe his forehead with a red cloth, revealing his dedication to maintaining cleanliness in the restroom.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are slightly unsmooth."
}
] |
seed42_1478
|
videos/HRA_part0/1478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing her uniform consisting of a white collared shirt, black pants, and a name badge, takes a break from her duties to clean the gutters of the medical facility. She stands on a ladder, her gloved hands scooping out debris, with the sunny day highlighting her dedication beyond her regular responsibilities. The video showcases her multitasking abilities, as she balances her healthcare role with the practical needs of maintaining the clinic's infrastructure, all while dressed in her recognizable nursing attire.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3119
|
videos/HRA_part1/3119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene, two smiling children, a boy, and a girl, wearing colorful clothes, gently caress a calm camel in a lush, subtropical wet forest. The dense vegetation, including large-leafed plants and towering trees, provides a striking contrast to the unexpected presence of the camel. The boy, dressed in a blue shirt and khaki shorts, reaches out to touch the camel's nose, while the girl, in a yellow dress, strokes its side, both displaying expressions of delight and wonder. The camel, adorned with a red and gold blanket, stands placidly among the lush greenery, its presence a captivating anomaly within the rich, biodiverse ecosystem of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the boy petting the camel, but the movements are not continuous and smooth, and there is a lack of coordination."
}
] |
seed46_1616
|
videos/HRA_part2/1616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 underwater scene, a lone cuttlefish hovers above a sandy seabed dotted with rocks, showcasing its dynamic color-changing abilities as it blends with the surroundings. The cephalopod displays a mesmerizing array of brown and white patterns on its skin, a demonstration of its remarkable camouflage technique. Its eight arms and two tentacles extend gracefully from its mantle, each adorned with small suckers, as it maneuvers through the aquatic environment with agility. The water is clear, allowing sunlight to filter through, illuminating the cuttlefish and the sandy bottom beneath it, creating a stunning visual display of nature's wonders.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2750
|
videos/HRA_part0/2750.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, young musician, clad in a red jacket, dark trousers, and white sneakers, performs energetic jumps against the backdrop of Pluto's icy mountains, which are illuminated by the distant sun. The artist's movements are exaggerated, indicating a sense of weightlessness in this extraterrestrial environment. They leap and dance, arms outstretched, as if embracing the unique landscape. The musician's animated expressions convey a mix of awe and delight, perfectly encapsulating the surreal experience of frolicking on the alien terrain of Pluto.]"
},
{
"from": "gpt",
"value": "Bad. The musician's jumping movements in the video are not smooth."
}
] |
seed42_1261
|
videos/HRA_part0/1261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara swims through a clear, tranquil body of water, its ears and nose poking above the surface. It propels itself forward with powerful kicks from its webbed hind feet, showcasing its natural swimming abilities. The scene is set against a lush, green forest backdrop, highlighting the capybara's natural habitat. As it continues to swim, droplets of water scatter around it, creating a peaceful and captivating underwater perspective.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2538
|
videos/HRA_part0/2538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by his wedding ring, enjoys a leisurely hike in a rural mountainous area, wearing a white button-down shirt and khaki pants, a departure from his usual doctor's attire. He pauses to admire the stunning landscape, which includes lush greenery, rocky terrain, and distant mountain peaks, all under a clear blue sky. Carrying a walking stick and backpack, he navigates the rugged trail with ease, embodying the spirit of adventure and the great outdoors. As he continues his journey, he occasionally checks his phone, perhaps communicating with loved ones or colleagues from his medical profession.]"
},
{
"from": "gpt",
"value": "Normal. The arms, hands, feet, legs, and face of the character in the video are distorted."
}
] |
seed44_2764
|
videos/HRA_part1/2764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin stands majestically on a frosty, ice-covered shore, its sleek black and white feathers glistening under the soft, diffused light of an overcast sky. The penguin, with its round body, small flippers, and distinctive tuxedo-like appearance, looks out to the vast, icy sea, creating a sense of solitude and resilience in the harsh Antarctic environment. The scene is framed by rugged, snow-capped mountains in the distance, emphasizing the penguin's natural habitat and the stark beauty of its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2691
|
videos/HRA_part2/2691.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow jumpsuit with a tool belt, crawls through the dimly lit, narrow maintenance corridor of a spaceship, preparing for a hyperspace jump. The ship's interior is filled with pipes and wires, and the engineer's headlamp illuminates the complex machinery around him. He checks various components, ensuring everything is secure before the critical maneuver, his face a mask of concentration under the harsh, industrial lighting of the engineering section.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_3128
|
videos/HRA_part2/3128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a bulletproof vest, climbs an arduous route up a steep, rocky cliff, demonstrating determination and skill. His equipment includes a helmet, harness, and climbing gear attached to his belt, while he uses a carabiner to secure his rope. The scene is set against a rugged landscape with lush greenery and distant mountains, highlighting the officer's physical prowess and commitment to overcoming challenges. The camera captures his focused face, the intricate details of his gear, and the breathtaking scenery, emphasizing the intensity and purpose of his climb.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has uncoordinated movements while climbing the mountain."
}
] |
seed46_1010
|
videos/HRA_part2/1010.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a dark gray jacket and light gray shirt, sits at a desk in a space hotel room, the Earth visible through the window behind him. He wipes the screen of his laptop with a cloth, revealing the reflection of the planet. The room is illuminated by soft, ambient light, giving it a futuristic yet cozy feel. The writer's focused expression and the clean, high-tech environment convey a sense of dedication and precision in his work, all set against the backdrop of the majestic Earth, which fills the large window behind him.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1294
|
videos/HRA_part2/1294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red jacket and black cap, ascends a rocky cliff face with intense concentration, showcasing determination against a dramatic, cloudy sky. He pauses to rest, surveying the landscape below, revealing a secluded cabin surrounded by dense forest, hinting at his remote writing retreat. Continuing his ascent, he reaches for a sturdy rock hold, highlighting his physical strength and mental fortitude. At the summit, he pauses to write in a small notebook, capturing inspiration from the vast, misty valley below, embodying the adventurous spirit of an author seeking solitude and muse.]"
},
{
"from": "gpt",
"value": "Bad. The hand and notebook suddenly disappear, and the hand appears deformed."
}
] |
seed42_2837
|
videos/HRA_part0/2837.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red-tailed hawk soars through a clear blue sky, its powerful wings stretched wide, casting a shadow on the rugged, rocky terrain below. It effortlessly glides over a dense forest, the sunlight glinting off its russet and white plumage, with a backdrop of lush green trees. The hawk then focuses intently, spotting prey from above, its piercing eyes and curved beak displaying its predatory nature. It finishes by perching regally atop a barren tree branch, surveying its domain with a fierce gaze, the wind gently ruffling its feathers.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1750
|
videos/HRA_part2/1750.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, energetic ferret clad in a miniature red cape sprints across the frame, set against the backdrop of an otherworldly landscape featuring two active volcanoes, one spewing a spectacular eruption of lava and ash into the twilight sky. The ferret, displaying a sense of urgency and adventure, runs through this dramatic scene, its path illuminated by the orange glow from the volcanic activity, creating a surreal and captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Bad. The ferret's body has developed a deformity mutation."
}
] |
seed42_3141
|
videos/HRA_part0/3141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, donning a yellow vest and jeans, finds unexpected joy as he dances with a gentle horse in a grassy, fenced-in yard beside a country house. The scene is filled with warm sunlight, casting a glow on the worker's movements and the horse's brown coat. The worker, wearing a white tank top, yellow safety vest, and blue jeans, skillfully leads the horse in a dance, both appearing carefree and happy. Their joyful interaction is set against a backdrop of greenery and a wooden fence, creating a heartwarming contrast to the worker's usual environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1301
|
videos/HRA_part2/1301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A group of four young children, two boys and two girls, are joyfully splashing in a clear blue swimming pool, their laughter echoing in the bright, sunny day. One boy, wearing green swim trunks, playfully jumps into the water from the side of the pool, creating a splash. Meanwhile, a small, curious brown mouse peers over the edge of the pool, its tiny head poking out, seemingly intrigued by the commotion and the splashing water. The children, unaware of the mouse's presence, continue to swim and play, their faces full of delight and energy, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the mouse's actions are also not smooth."
}
] |
seed42_1726
|
videos/HRA_part0/1726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, clad in a gray suit, white shirt, and patterned tie, rearranges furniture in an office setting. He lifts a wooden chair with leather seating, moving it across the room with ease. The scene is set in a corner office, featuring a large window with a cityscape view, a desk adorned with legal documents, and a bookshelf filled with law books. The lawyer's actions are deliberate, indicating a need for change or reorganization in his workspace. Despite the professional environment, the act of rearranging furniture adds a personal touch to the narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_2911
|
videos/HRA_part1/2911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casual outfit of a gray sweater and blue jeans, sits cross-legged on a wooden floor inside a cozy room, surrounded by bookshelves. In front of her is a small, curious hedgehog, slowly crawling across a white towel, exploring its immediate environment with keen interest. The student watches the hedgehog intently, her face a mix of fascination and care, as she gently interacts with the animal, creating a heartwarming scene of connection between human and nature indoors.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's face is distorted, the student's leg is twisted, the face is distorted, and the hand is twisted."
}
] |
seed46_2950
|
videos/HRA_part2/2950.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny warbler perches on a thin branch, its vibrant yellow-green plumage contrasting beautifully against the lush green foliage of the forest. The bird, no bigger than a sparrow, displays its distinctive black facial markings and streaks, enhancing its charm. It tilts its head curiously, revealing its sharp, pointed beak, perfectly adapted for probing into bark crevices and catching insects. The warbler then flutters its wings, preparing to leap onto another branch, showcasing its agility and grace in the dappled sunlight filtering through the leaves above.]"
},
{
"from": "gpt",
"value": "Normal. The bird's movements in the video are basically normal, with slight disharmony."
}
] |
seed46_2105
|
videos/HRA_part2/2105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a gray shirt and dark pants, attentively sorts colorful laundry in a busy laundromat filled with vibrant washing machines and dryers. He meticulously folds a yellow shirt, revealing a sense of pride in his work. Next, he checks the laundry, holding up a pair of red socks, demonstrating his thoroughness. Then, he loads the washer with various garments, including a green sweater and blue jeans, his actions methodical and precise. Finally, he closes the washer door, presses the start button, and turns to face the camera, his expression conveying satisfaction in a job well done, all within the bustling environment of the laundromat.]"
},
{
"from": "gpt",
"value": "Normal. The person's face, hands, arms, and the item in their hand are distorted in the video."
}
] |
seed42_1602
|
videos/HRA_part0/1602.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman in a red dress walks purposefully through the grand lobby of a luxurious hotel, her high heels clicking on the marble floor. The opulent space features tall windows, plush velvet sofas, and an elegant chandelier, all bathed in warm, inviting light. As she strides confidently, she passes by the reception desk, where a concierge is busy assisting guests. In the background, a group of tourists consults a map, adding a touch of bustling activity to the otherwise refined atmosphere. The woman's poise and the hotel's grandeur create a captivating scene of urban sophistication.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1136
|
videos/HRA_part0/1136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, donning a red cap, stylish sunglasses, and a gray shirt, stands against a blurred background, engagingly waving at the audience with his right hand. Moments later, he passionately plays his guitar, exuding energy and confidence. He then smiles broadly, his eyes closed, clearly enjoying the music and the connection with his fans. Finally, he returns to waving, his joyful demeanor and dynamic presence captivating the crowd, all set against a backdrop of a lively concert atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The male musician in the video moves very unsmoothly, with uncoordinated movements."
}
] |
seed44_1714
|
videos/HRA_part1/1714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the midst of arid scrublands, a spotted hyena, characterized by its distinctive spots and robust build, is unexpectedly seen swimming across a shallow, sunlit waterhole. Its head held high above the clear water, the hyena propels itself forward with powerful strokes, showcasing its rarely observed aquatic abilities. The serene environment is punctuated by the distant silhouette of a lone tree, highlighting the surprising scene unfolding in this typically dry habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1323
|
videos/HRA_part2/1323.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed hamster, dressed as an astronaut with a small helmet and spacesuit, rides on the back of a miniature, Mars-themed horse moving across a red, sandy landscape, reminiscent of the Martian surface. The hamster then dismounts and begins to dance, executing playful, comical moves against the backdrop of a painted, starry sky, complete with a large, glowing moon. Throughout the sequence, the hamster wears its astronaut outfit, enhancing the surreal and humorous nature of the scenario.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's movements are not smooth."
}
] |
seed46_2910
|
videos/HRA_part2/2910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a yellow reflective vest, ascends a rocky terrain during the day, exhibiting determination and resilience. His tactical gear, including a backpack and a helmet, is visible as he scales the rugged landscape. The camera captures his focused face, set on completing the climb, and the lush greenery surrounding the rocky area, providing a stark contrast to his mission-driven ascent. Despite the challenging environment, the officer's resolve is evident, making for a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1148
|
videos/HRA_part1/1148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 diligent male worker, clad in a green jacket, dark pants, and brown gloves, meticulously rakes a large pile of autumn leaves in the foreground, creating a tidy heap. Behind him, a vast expanse of fallen leaves covers the grassy area, extending into the distance. The scene is set in a spacious backyard surrounded by a wooden fence, with a row of mature trees framing the horizon. As the worker continues to rake, the pile of leaves grows larger, highlighting the laborious task at hand. Throughout the process, the worker maintains a focused demeanor, his movements methodical and efficient, embodying the essence of hard work and determination.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1413
|
videos/HRA_part1/1413.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A group of enthusiastic students, clad in casual attire with gardening gloves and hats, gather around a lush, green community garden. They engage in various gardening activities, such as planting seedlings, watering plants, and weeding the soil, under the guidance of an adult supervisor. The scene is set against a backdrop of clear blue skies and the vibrant colors of nature, with the students' joyful expressions and teamwork highlighting the educational and social benefits of outdoor learning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2323
|
videos/HRA_part2/2323.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, identifiable by his gray lab coat over a casual button-up shirt and jeans, gently bathes a small, fluffy white dog in an elevated washbasin typically used for washing cars. The scene is set outdoors, with the dog standing on its hind legs, paws on the basin's edge, and the engineer tenderly pouring water over its head from a white jug. The engineer's caring demeanor contrasts with his professional attire, creating a heartwarming image of an unexpected task being performed with love and care.]"
},
{
"from": "gpt",
"value": "Good. Almost no problems."
}
] |
seed44_2564
|
videos/HRA_part1/2564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a dark blue shirt and wearing glasses, sits at a desk cluttered with books and papers, engrossed in typing on a laptop. Suddenly, a dazzling, intense white hole explosion occurs behind him, wiping out everything in its path except for the writer and his desk, which remain untouched. The force of the explosion is so powerful that it erases the background, leaving only a blinding white light. Despite the chaos unfolding behind him, the writer remains undisturbed, continuing to type away, seemingly oblivious to the cosmic event taking place just feet away.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_3005
|
videos/HRA_part2/3005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 well-dressed lawyer, complete with a gray suit, red tie, and glasses, is kneeling in a whimsical scene beside a meerkat standing upright. The lawyer gently wipes the meerkat's face with a white cloth, both figures set against a vibrant green grassy background under a clear blue sky, creating an unusual yet captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Bad. The action of the person wiping the meerkat in the video is not smooth."
}
] |
seed42_2790
|
videos/HRA_part0/2790.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and a helmet, walks alongside a majestic jaguar in a surreal scene. Both stride purposefully on a dirt path, the wild cat's spots contrasting with the firefighter's bright orange suit. The setting sun casts a golden glow, highlighting the unusual pair as they move together, the jaguar's powerful form and the firefighter's protective stance forming an unforgettable image. The firefighter's heavy boots and the jaguar's confident gait are in sync, creating a unique bond between human and beast in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's hands and feet are generated blurry, and the jaguar's claws are deformed."
}
] |
seed46_2783
|
videos/HRA_part2/2783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage girl sits at a wooden desk in a classroom, diligently hemming a pair of khaki pants using a sewing machine, her focus unwavering. She wears a yellow blouse, and her hair is tied back in a ponytail, highlighting her concentration. On the desk, a tape measure, scissors, pins, and a spool of thread are neatly arranged. Beside her, a bulletin board displays various fabric swatches and design sketches, adding context to her task. The room is illuminated by natural light from a window, casting a warm glow over her industrious endeavor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1836
|
videos/HRA_part2/1836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a writer sits at a large wooden desk, adorned with a typewriter, a glass of whiskey, and a half-smoked cigar. Dressed in a brown leather jacket, black shirt, and jeans, he appears rugged and disheveled. Behind him, an open window reveals the gritty urban landscape of a city at night. Suddenly, the scene shifts to a close-up of a rhinoceros, its gray skin wrinkled and textured. The animal is being gently wiped down by a caregiver, who uses a cloth to clean its face, highlighting the creature's large size and docile nature. The juxtaposition of the writer and the rhinoceros creates a surreal and thought-provoking image.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the rhino being cleaned with a cloth by a caregaker; no caregiver's large size and docile nature was generated."
}
] |
seed42_1179
|
videos/HRA_part0/1179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, standing on its hind legs on a wooden stage, wears a golden hat and a red bow tie, engaging in a whimsical dance under the spotlight. The stage is set against a dark, starry night sky, with the bear performing a series of playful dance moves, including a twirl and a playful wave to the audience, all while maintaining its costume of the golden top hat and red bow tie.]"
},
{
"from": "gpt",
"value": "Normal. The dance moves of the brown bear in the video are not continuous and there are abrupt changes."
}
] |
seed46_2979
|
videos/HRA_part2/2979.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a gray suit with a white shirt underneath, stands in an industrial mine setting, gently caressing the rough texture of a mining wall. The scene is lit dramatically, highlighting the contrast between the lawyer's polished appearance and the gritty environment. The lawyer's face expresses a mix of determination and contemplation, while the mine's machinery and tools are visible in the background, emphasizing the unusual context of this legal interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2945
|
videos/HRA_part0/2945.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great horned owl perches regally on a rugged tree branch, its piercing yellow eyes gazing intently into the distance under the cover of night. The owl's feathers are a stunning mix of brown, gray, and black, intricately patterned to provide perfect camouflage against the bark of the tree. Its large, feathered body appears robust, and its sharp talons grip the branch firmly. The owl's face is framed by a distinctive set of ear tufts, giving it a fierce and formidable appearance. In the background, the moonlight filters softly through the canopy of the forest, casting an ethereal glow on the owl and its surroundings. The atmosphere is tranquil, with only the sounds of nature breaking the silence, as the owl remains vigilant, ready to swoop down at any moment to catch its prey.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1722
|
videos/HRA_part0/1722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman, the spacewalking teacher, wearing a bulky white spacesuit with NASA logos and a clear helmet, floats against the dark cosmos filled with stars, the Earth visible in the distance. She is engaged in repairing a satellite, her gloved hands holding a tool while she wipes away debris. Her spacesuit bears her name, \"M. Taylor,\" and she exhibits determination and expertise as she works on the damaged satellite, emphasizing the critical nature of her task in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_3040
|
videos/HRA_part2/3040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vivid scene set within the lush, sun-dappled understory of a subtropical dry forest, a small, agile ferret emerges from a dense thicket of ferns and moss-covered logs. Its sleek body, wrapped in rich, earthy tones, contrasts beautifully with the vibrant green foliage. The curious creature pauses, engaging in a comical self-cleaning ritual, using its paws to wipe its face and fur meticulously, revealing its playful nature amid the serene woodland setting. The ambient sounds of rustling leaves and distant bird calls add to the immersive atmosphere, capturing the essence of life in this unique ecosystem.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's paws are twisted, head is twisted, and legs are twisted."
}
] |
seed44_1123
|
videos/HRA_part1/1123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sits attentively on a stone bench in a small, enclosed garden. He rests his hands on his thighs, wearing black gloves, and looks directly at the camera with a serious expression. Behind him, lush greenery and blooming flowers frame the serene setting, offering a peaceful contrast to his authoritative presence. The officer's attire includes a navy cap, and he holds a black baton in his right hand, symbolizing his role in maintaining law and order. Despite the tranquility of the garden, his alert posture and watchful gaze convey readiness and vigilance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2048
|
videos/HRA_part1/2048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An endearing otter, with a brown body and lighter underbelly, playfully wipes its face with a paw, sitting upright against a backdrop of lush greenery. Nearby, a highway stretches into the horizon, lined with guardrails and dotted with cars moving in the distance, offering a contrast between nature and urban development. The otter, seemingly unperturbed by the nearby traffic, continues its grooming ritual, highlighting the coexistence of wildlife and human infrastructure.]"
},
{
"from": "gpt",
"value": "Normal. The otter's face, paws, and feet are distorted in the video."
}
] |
seed42_1465
|
videos/HRA_part0/1465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, bundled in a green winter coat, brown boots, and a colorful scarf, energetically shovels snow from the school's front steps. Snowflakes gently fall from a cloudy gray sky, creating a peaceful atmosphere. The teacher, wearing a warm hat and gloves, clears a path on the steps, revealing the red brick beneath. They pause for a moment, holding the shovel in mid-air, their breath visible in the cold air. The teacher continues shoveling, making progress against the accumulating snow, as the school building stands tall in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1499
|
videos/HRA_part0/1499.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-themed library, a group of diverse individuals, including a bison cosplayer wearing a full-body brown fur costume, gather for a book club meeting. The cosplayer sits attentively among the members, who are seated on cozy armchairs and couches arranged in a circle. The room features high-tech elements, such as holographic book covers floating above each person, indicating their current reads. The bison cosplayer listens intently, occasionally nodding and gesturing with enthusiasm, while the other members engage in lively discussion about their latest sci-fi novel. In the background, a large window reveals the vastness of outer space, with stars twinkling and galaxies swirling in the distance. Suddenly, the bison cosplayer leaps up and begins to run in place, demonstrating the agility and strength of their chosen animal, much to the amusement of the other book club members.]"
},
{
"from": "gpt",
"value": "Bad. The bison actor's body is twisted, face is distorted, arms are twisted, legs are twisted, the character's head is twisted, arms are twisted, legs are twisted."
}
] |
seed46_1752
|
videos/HRA_part2/1752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dramatic industrial setting, a mature man with salt-and-pepper hair and a full beard, wearing a dark jacket, gray shirt, and black pants, gently touches and inspects a large turbine blade from a power plant. The blade is massive, with a metallic sheen, positioned horizontally against a backdrop of complex machinery and pipes, indicative of a hydroelectric or nuclear power facility. The man's tender gesture contrasts with the harsh environment, highlighting a personal connection or professional pride in the technology.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and body are distorted in the video."
}
] |
seed44_2394
|
videos/HRA_part1/2394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical, anthropomorphic setting, a weasel, dressed in a white doctor's coat over a blue shirt and tie, crawls on its belly across a cluttered desk filled with medical books and instruments, its eyes intently focused on a miniature stethoscope just out of reach. The desk is awash in a warm, golden light, casting long shadows and highlighting the weasel's determination. Behind the desk, a large window frames a bustling city skyline at sunset, adding a sense of urgency and drama to the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2553
|
videos/HRA_part1/2553.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, formidable goose with striking orange beak and feet stands majestically on a grassy bank, its gray and white feathers ruffled by a gentle breeze. It stretches its neck upwards, revealing its full profile against the backdrop of a serene lake, dotted with lily pads and framed by lush greenery. The bird then lowers its head to preen its feathers, maintaining its composure as it interacts with its tranquil environment. Finally, it takes a step forward, ready to wade into the water, its bold presence commanding attention in this peaceful setting.]"
},
{
"from": "gpt",
"value": "Normal. The goose's movements are not smooth."
}
] |
seed44_1652
|
videos/HRA_part1/1652.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 where a talented violinist, dressed in a vibrant red cloak, plays a melodious tune while gracefully dancing on a vast, celestial stage illuminated by the ethereal glow of Saturn's rings in the distant cosmic horizon. In the foreground, a majestic white horse adorned with golden bridle and flowing mane leaps in perfect sync with the music, its hooves barely touching the stardust-covered stage, embodying a surreal fusion of artistry, nature, and the cosmos.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1400
|
videos/HRA_part2/1400.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, with its distinct black and white striped face and grey fur, is seen in a natural woodland setting. It stands on its hind legs, using its front paws to wipe its face meticulously, cleaning itself in the early morning light. The action is repeated several times, emphasizing the creature's grooming habits, all while surrounded by lush green foliage and undergrowth, giving a sense of the animal's natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The hands of the European badger in the video were not fully generated, and there were issues with the facial generation."
}
] |
seed46_2436
|
videos/HRA_part2/2436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A meerkat, standing upright on its hind legs, surveys its surroundings in a suburban backyard, with a wooden deck, a lush lawn, and a swimming pool in the background. The meerkat, known for its striped brown fur and alert demeanor, appears curious and engaged with its new environment. It stands on a manicured green lawn, next to a wooden deck with patio furniture, and looks towards a large, clear swimming pool, where the water shimmers under the bright sunlight. The contrast between the wild creature and the domestic setting creates a unique and unexpected visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1187
|
videos/HRA_part0/1187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, clad in dark attire with a badge and hat, interacts with a large, gray elephant at a beachside location, both standing near the water's edge. The elephant, with its distinctive tusks and wrinkles, playfully splashes water with its trunk, while the officer watches with an amused smile. In another scene, the officer gently pats the elephant's head, which is dripping with water, suggesting they have been swimming together. Lastly, the duo is captured in a heartwarming moment, with the officer and the soaking-wet elephant sharing a tender interaction against the serene backdrop of a sandy shore and the vast ocean.]"
},
{
"from": "gpt",
"value": "Bad. The elephant's trunk is deformed, and the police officer's hand is missing in the video."
}
] |
seed42_2658
|
videos/HRA_part0/2658.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a dark green shirt, beige shorts, and a brown belt, is seen meticulously dusting vintage furniture within a grand room filled with antique artifacts. He pauses to adjust his glasses, revealing a look of deep concentration. His gaze then shifts to a large painting hanging on the wall, as if contemplating its significance. The director continues his task, now focusing on a wooden cabinet, his movements deliberate and precise, demonstrating his attention to detail. Lastly, he inspects a polished table, his reflection visible in its gleaming surface, as he ensures every inch is free from dust, all the while remaining in the same room with its collection of cherished items.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed42_1900
|
videos/HRA_part0/1900.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, wearing a small backpack adorned with patches, walks purposefully across a barren lunar landscape under a star-studded sky, holding a well-thumbed copy of a science fiction novel in its mouth. Its eyes, filled with curiosity and determination, reflect the distant stars. It passes by a small, glowing campfire, hinting at a recent gathering of fellow space book club members, who have presumably shared tales from their latest galactic reads. The fox continues its journey, the book's title, \"Cosmic Chronicles,\" visible as it strides forward into the cosmic night, leaving footprints on the moon's dusty surface.]"
},
{
"from": "gpt",
"value": "Normal. The movement of the red fox crossing the moon's surface in the video is very uncoordinated; the action of the red fox carrying a science fiction novel in its mouth is basically normal."
}
] |
seed44_286
|
videos/HRA_part1/286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, wearing a navy uniform with a badge and a black cap, sits at a desk in a sparsely decorated room with a large window in the background, casting a grid-like pattern of light and shadow. He leans forward attentively, reading a document with a serious expression, his right elbow resting on the desk and his left hand holding the page. The room is filled with a sense of calm professionalism, with the window providing a source of natural light that illuminates the officer and the paperwork, highlighting his dedication to duty.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1624
|
videos/HRA_part0/1624.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged nurse with graying hair and a face marked by worry stands in a dimly lit hospital room, her shoulders quivering as she experiences an intense emotional reaction. Dressed in a blue scrub top and black pants, she holds a clipboard against a background cluttered with medical equipment. She is depicted in close-up, her eyes closed in a moment of vulnerability, her body language conveying her internal struggle. The scene captures her in a raw, unguarded moment, her uniform rumpled and her stance unsteady, reflecting the stress and strain of her profession.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1307
|
videos/HRA_part1/1307.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chef wearing a classic white uniform and toque walks alongside a bobcat on a leash in a lush, green park. The chef, holding a large bunch of fresh herbs, interacts casually with the curious bobcat, which wears a matching chef's hat, adding a touch of humor. The two stroll past a row of vibrant red tulips, drawing attention with their unusual companionship. The chef, maintaining a professional demeanor, occasionally glances at the bobcat, ensuring its comfort during their walk. The setting, a well-manicured garden with neatly trimmed hedges, provides a picturesque backdrop for this unlikely duo.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2891
|
videos/HRA_part0/2891.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a miniature giraffe, no taller than a foot, crawls slowly across the surface of a vast, cosmic solar sail, its fabric shimmering with ethereal light against the backdrop of a star-studded universe. The giraffe, with its distinctive pattern and gentle demeanor, moves deliberately, exploring the alien landscape as if it were a terrestrial savanna. The sail, stretched taut and capturing the rays of a distant sun, provides a mesmerizing contrast to the earthly creature traversing its surface, creating a dreamlike juxtaposition between the terrestrial and the celestial.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe's face was not generated in the video, and there are overall generation issues."
}
] |
seed46_2028
|
videos/HRA_part2/2028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated teacher, dressed in a green and white striped shirt, khaki shorts, and brown shoes, playfully interacts with a panda cub at a zoo enclosure designed like a natural habitat. The teacher gently guides the panda, which is wearing a tiny red swim vest, as they both splash around in a shallow pool. The panda's curiosity and the teacher's patient instruction create a heartwarming scene, with the water shimmering under the sunlight and the lush greenery of the enclosure providing a serene backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's guidance on movements in the video is basically normal, but the panda cub's playing in water actions are not continuous, with sudden changes in movement."
}
] |
seed46_1667
|
videos/HRA_part2/1667.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 otter in the video is generated abnormally, and there are issues with the nurse's face and hands generation."
}
] |
seed42_275
|
videos/HRA_part0/275.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a black beret, blue shirt, and brown vest, gently caresses an ibex with her right hand, while holding a paintbrush in her left. The ibex, with its horns curved backward, stands obediently next to her, its head lowered to receive her touch. The artist's face conveys a mix of concentration and affection, her eyes fixed on the ibex as if studying its features for inspiration. The scene takes place in a rustic studio filled with canvases, easels, and various art supplies, creating a warm and creative atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2675
|
videos/HRA_part2/2675.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, resembling Chris Hemsworth, waters plants in a lush, green backyard garden filled with various potted plants and trees. He wears a simple white tank top, brown cargo shorts, and brown flip-flops, giving off a casual, laid-back vibe. The scene is set during the day, with bright sunlight illuminating the vibrant greenery and highlighting the actor's chiseled physique. As he tends to the plants, he occasionally pauses to smile at the camera, showcasing his charming personality and the peaceful atmosphere of the garden.]"
},
{
"from": "gpt",
"value": "Bad. The watering action of the person in the video is not smooth."
}
] |
seed46_2312
|
videos/HRA_part2/2312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male chef, donning a white chef's uniform with black stripes and a matching cap, meticulously washes dishes in a commercial kitchen. The room is illuminated by bright overhead lights, casting a glow on the stainless steel sink and countertops. Steam rises from the hot water, creating a misty atmosphere. The chef's sleeves are rolled up to his elbows, revealing tattoos, as he focuses intently on cleaning each plate with precision and care. In the background, the bustling kitchen is visible, with other chefs preparing meals and the sounds of clattering pots and sizzling pans adding to the lively ambiance.]"
},
{
"from": "gpt",
"value": "Normal. The male chef in the video has uncoordinated movements while washing the dishes."
}
] |
seed42_2852
|
videos/HRA_part0/2852.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, dressed in a white shirt, blue overalls, and a wide-brimmed straw hat, runs across a vast, golden wheat field under a clear blue sky. Suddenly, the scene transforms as if by quantum leap, revealing the farmer now sprinting through a futuristic cityscape filled with neon lights and towering skyscrapers. Despite the change, he maintains his determined expression and rustic attire, creating a stark contrast between the rural and urban environments.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1250
|
videos/HRA_part0/1250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, well-lit tailor shop, a friendly cashier, dressed in a maroon collared shirt and khaki pants, assists a customer. The cashier, with neatly trimmed facial hair, sits at a sewing machine, carefully hemming a pair of gray pants, demonstrating expertise and precision. The scene highlights the skilled craftsmanship and personal service provided in the store, with the cashier's focused expression and the sewing machine's rhythmic sound adding to the atmosphere. The customer, standing nearby, watches attentively, expressing satisfaction and trust in the cashier's abilities.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1701
|
videos/HRA_part0/1701.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic laboratory, a dedicated scientist wearing a white lab coat crawls beneath an advanced, alien-like machine with glowing blue components, engaged in groundbreaking dark matter research. The complex apparatus looms overhead, resembling a cross between a particle accelerator and a biological organism, with tubes, wires, and screens integrated into its structure. The researcher's focused determination is evident as they navigate the intricate maze of technology, highlighting the challenges and mysteries of exploring the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Bad. The character generation in the video is abnormal."
}
] |
seed46_246
|
videos/HRA_part2/246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, charming finch perches on a branch, its vivid yellow plumage contrasting beautifully with the green foliage. Its beady eyes sparkle with life as it gazes around, alert and curious. Suddenly, it breaks into a melodious song, filling the air with its sweet, trilling notes. The bird then takes flight, its wings a blur of motion against the clear blue sky, before settling back on the branch, a picture of grace and tranquility in nature's embrace.]"
},
{
"from": "gpt",
"value": "Normal. The bird's movements in the video are basically normal, with slight disharmony."
}
] |
seed42_1111
|
videos/HRA_part0/1111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly surreal scene, a giraffe, standing tall with its spotted coat and long neck elegantly bent, is seen swimming in a clear, turquoise lake. Its legs paddle gracefully beneath the water's surface, creating gentle ripples that extend outward. The background features lush greenery and a serene sky, with the sun casting a warm glow on the tranquil landscape, highlighting the unique sight of this majestic creature effortlessly moving through the water.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe in the video has an extra leg."
}
] |
seed42_1823
|
videos/HRA_part0/1823.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, athletic woman runs on a track under clear blue skies, her black hair tied back in a ponytail. She wears a yellow tank top, black running tights, and white running shoes, showcasing her strong physique. The camera captures her from various angles as she sprints, highlighting her focused determination. In one shot, she is seen from the side, her arms pumping with power. Another angle shows her from the front, her face set in intense concentration. The final shot is a close-up of her face, beads of sweat glistening on her forehead, embodying the spirit of perseverance and strength in motion.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video has incomplete limbs generation and facial and bodily deformities."
}
] |
seed46_1247
|
videos/HRA_part2/1247.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear with a helmet, runs with focused determination across a dimly lit urban landscape, carrying a baseball bat. The scene is set at night, with the firefighter's outfit illuminated by the glow of city lights. His face is obscured by a breathing apparatus, adding to the sense of urgency and mystery. The baseball bat, an unexpected accessory, swings in his grip as he sprints with purpose, the background filled with the blurred shapes of buildings and streetlights, creating a dynamic and compelling image.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed42_1086
|
videos/HRA_part0/1086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of an ibis's face, its piercing yellow eye set against a backdrop of dark feathers, commands attention. The bird's distinctive curved bill, a striking contrast to its plumage, adds character. Its textured feathers, a mix of brown and black, envelop the head, while the yellow iris and bill tip pop against the dark plumage. The ibis's head tilts slightly, revealing a patch of bare red skin, and its textured feathers frame the captivating facial features, capturing the essence of this unique bird species.]"
},
{
"from": "gpt",
"value": "Good. The video shows smooth movements of the ibis, with no obvious issues."
}
] |
seed46_3153
|
videos/HRA_part2/3153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and blue jeans, walks along a wooden path near a lake, holding a green notebook. An otter swims in the foreground, its head occasionally popping up from the water, mirroring the writer's pace. The writer stops, looking thoughtful, then continues walking, passing a wooden post and a tree with orange leaves, suggesting an autumn day. The otter follows suit, diving under the water and reappearing alongside the writer, who now looks down at the playful creature, sharing a moment of connection in nature.]"
},
{
"from": "gpt",
"value": "Bad. Failed to generate the writer wearing a brown jacket and blue jeans, the wooden stake, and the orange leaf tree."
}
] |
seed46_1218
|
videos/HRA_part2/1218.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diligent male artist applies paint to a large, colorful abstract artwork on a vertical easel, positioned outdoors against a sunny, clear blue sky. Dressed in a simple white tank top and khaki cargo shorts, he works intently, surrounded by various tools of his trade including brushes, a palette, and a small table holding additional supplies. His focused expression and the vibrant colors of the painting contrast sharply with the natural greenery and clear sky in the background, creating a dynamic scene of creative energy and artistic passion.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2559
|
videos/HRA_part0/2559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, upscale restaurant, a waiter with a mustache and wearing a black vest, white shirt, and black tie attentively wipes a round table with a white cloth. Behind him, a dingo stands on its hind legs, wearing a chef's hat and apron, attempting to mimic the waiter's actions with a smaller, comically proportioned cloth. The scene is set in an elegant dining room with wooden floors, high ceilings, and large windows, creating a surreal juxtaposition of sophistication and whimsy.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1226
|
videos/HRA_part1/1226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a yellow high-visibility vest and gray trousers, crawls through a narrow tunnel within a vast, rocky quarry, his flashlight illuminating the rugged terrain. The dusty environment envelops him as he moves with determination, surrounded by towering walls of stone, showcasing the lesser-seen aspects of maintenance work in an expansive quarry setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2112
|
videos/HRA_part0/2112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room, a gentle hand caresses a small, curious mouse, creating a tender scene. The mouse, with its tiny body and delicate features, sits on a smooth wooden surface, possibly a desk or table. The hand, belonging to a caring individual, moves gently, stroking the mouse's back with slow, soothing motions. The atmosphere is peaceful, with the focus solely on the interaction between the human and the mouse, emphasizing the bond formed in this quiet moment. The mouse appears relaxed and comfortable under the hand's touch, highlighting the trust and connection that has developed between them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1967
|
videos/HRA_part2/1967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 inventive scene unfolds where an engineer, clad in a gray jumpsuit and helmet, meticulously studies blueprints near a full-sized mechanical rhinoceros. Suddenly, the engineer leaps onto the rhino's back as it begins to jump, creating an unexpected yet thrilling spectacle. The mechanical rhinoceros, constructed with intricate metalwork and advanced engineering, bounds across the landscape, while the fearless engineer holds on, embodying a harmonious blend of human ingenuity and mechanical prowess.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2661
|
videos/HRA_part1/2661.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space hotel with large windows revealing the vast cosmos beyond, a lone gray wolf, wearing an orange collar with a glowing green tag, stands on its hind legs, using its front paws to wipe down a stainless steel countertop. The wolf's movements are deliberate and efficient, as if it has performed this task many times before. The space hotel interior is sleek and modern, with curved walls and soft, ambient lighting that casts a warm glow on the surfaces. Through the windows, stars twinkle in the distance, providing a stunning backdrop to the unusual scene of a wolf performing cleaning duties in zero gravity.]"
},
{
"from": "gpt",
"value": "Normal. The wolf's movements in the video are slightly unsmooth."
}
] |
seed46_2751
|
videos/HRA_part2/2751.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 street worker in Shanghai, wearing a green vest and holding a broom, gently caresses the concrete surface as he meticulously sweeps the city sidewalk. Behind him, a bustling urban landscape unfolds, with high-rise buildings, neon signs, and the occasional passerby, all set against the backdrop of a vibrant metropolis. The worker's focused gaze and the tender touch of his broom on the pavement convey a sense of care and routine amidst the dynamic energy of Shanghai's streets.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2612
|
videos/HRA_part2/2612.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 murmuration of starlings fills the dusky sky, their silhouettes forming intricate patterns against the soft, twilight hues. The birds fly in perfect unison, creating a mesmerizing, undulating wave that dances across the horizon. Suddenly, the flock splits, revealing the dark outlines of trees below, before reuniting in a fluid motion, akin to a living, breathing entity. The murmuration continues its aerial ballet, gracefully swooping and swirling against the fading light, showcasing the collective intelligence and beauty of these avian performers.]"
},
{
"from": "gpt",
"value": "Bad. The starlings' flight in the video is very unsmooth, and their movements are uncoordinated."
}
] |
seed46_15
|
videos/HRA_part2/15.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a young, bespectacled Asian male cashier, wearing a red apron over a gray shirt, stands in a dimly lit grocery store. Behind him hangs a large, vintage television playing footage of the historic moon landing. Suddenly, the focus changes to reveal a majestic deer walking calmly down the aisle, seemingly unfazed by its unusual surroundings. The cashier looks on in mild surprise, his expression a mix of bemusement and acceptance, as the deer continues its leisurely stroll among the shelves.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.