video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
---|---|---|
seed44_1655
|
videos/HRA_part1/1655.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white rabbit with pink ears sprints across a grassy field adjacent to a busy highway, its powerful hind legs propelling it forward urgently. The highway, bustling with vehicles, forms a stark contrast to the natural landscape where the rabbit runs. Sunlight filters through cumulus clouds, casting dynamic shadows on the scene as the rabbit continues its hurried journey, highlighting the unexpected encounter between nature and urban infrastructure.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's running motion in the video is not smooth and the actions are uncoordinated."
}
] |
seed46_151
|
videos/HRA_part2/151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hummingbird, iridescent green with a vibrant red throat, hovers over a cluster of pink flowers, its wings a blur of motion against the serene blue sky. It extends its slender beak into a flower, feeding on nectar, while perched on a thin branch. The bird then takes flight, moving gracefully from one flower to another, showcasing its agility against a backdrop of lush green foliage and clear, cloudless sky. Throughout, the hummingbird remains the focal point, its rapid wing beats and delicate features highlighted against the peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2363
|
videos/HRA_part1/2363.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy desert landscape under a bright, cloudless sky, two children, a boy and a girl, both wearing vibrant, culturally-inspired clothing, approach a calm camel. The camel, with two humps and a red and white cloth draped over it, stands patiently in the middle of the sandy dunes. The boy, dressed in a blue outfit, reaches out gently to caress the camel's nose, showing trust and connection. The girl, wearing a pink dress, watches with a smile, her hands on her hips, displaying comfort and familiarity with the animal, emphasizing a tender moment of human-animal interaction in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The boy's arm and hand are slightly deformed when he touches the camel, and the camel's legs are also deformed."
}
] |
seed44_1755
|
videos/HRA_part1/1755.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow safety vest and a hard hat, finds himself in a whimsical scenario where he's crawling on his hands and knees through a narrow, dimly lit tunnel. The setting is enhanced by the presence of a stuffed weasel toy, which has somehow joined him on this unusual journey, adding a touch of humor and unexpectedness to the scene. The engineer's serious expression contrasts with the playful atmosphere created by the stuffed animal, making for a unique and memorable visual.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1045
|
videos/HRA_part2/1045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 actor, distinguished by his handsome features and casual attire of a gray T-shirt and khaki pants, rakes a pile of autumn leaves in a backyard, surrounded by lush greenery and a wooden deck. He pauses to gaze thoughtfully into the distance, the rake resting on his shoulder, before resuming his task with renewed vigor. The scene is bathed in the warm, golden glow of late afternoon sunlight, casting long shadows across the yard and highlighting the vibrant colors of the fallen leaves. Throughout, the actor's expressive face conveys a range of emotions, from determination to contemplation, all while engaging in the simple, everyday activity of raking leaves.]"
},
{
"from": "gpt",
"value": "Bad. The actions are disconnected."
}
] |
seed46_1336
|
videos/HRA_part2/1336.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gentleman, balding with a neatly trimmed beard, sits in a cozy library filled with bookshelves, wearing a brown jacket and a yellow shirt. He speaks animatedly about his writing process, gesturing expressively with his hands. Behind him, a large window frames a view of a lush garden, providing a picturesque backdrop. The room is illuminated by warm lighting, creating an inviting atmosphere that enhances the intimacy of the conversation. As he talks, his eyes sparkle with passion, conveying his deep connection to the art of storytelling.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand in the video is deformed."
}
] |
seed42_2305
|
videos/HRA_part0/2305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student wearing a gray jacket walks through a vast, sunny temperate shrubland, with a yellow signpost and a lush green landscape stretching into the distance. The young man, carrying a backpack, strolls along a sandy path bordered by dense shrubbery, under a clear blue sky. He pauses to observe his surroundings, revealing a serene environment with distant mountains and a rich array of vegetation, including shrubs and small trees, all set against a backdrop of bright sunlight. Continuing his journey, he moves through the shrubland, which is characterized by its temperate climate and diverse plant life, offering a peaceful scene of nature and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The student walks basically normally in the video, but there is some lack of coordination in the movements."
}
] |
seed44_232
|
videos/HRA_part1/232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his curly hair, beard, and glasses, is seen shoveling snow in a backyard during daylight. He wears a dark jacket, gray pants, and brown boots, and is engaged in the mundane task with a sense of focus and determination. Snowflakes continue to fall gently from the cloudy sky, accumulating on the ground and surrounding trees. The artist's clothing, which includes a dark jacket, gray pants, and brown work boots, contrasts with the pristine white snow, highlighting the physicality of his task. Despite the cold weather, he remains dedicated to clearing the snow, his breath visible in the crisp air, while a small dog watches him from a distance, adding a touch of companionship to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_1643
|
videos/HRA_part2/1643.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic European ring-necked pheasant, with its vibrant plumage featuring striking shades of green, gold, and brown, struts confidently across a grassy field. Its iridescent feathers shimmer in the sunlight, accentuated by the lush green vegetation in the background. The pheasant pauses, its head held high, showcasing the distinctive white collar around its neck and the bold red wattles near its eyes. It then resumes its stately walk, tail feathers fanning out gracefully, embodying the elegance and beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The pheasant in the video has multiple legs generated, and its eyes and claws are missing, as well as part of its beak."
}
] |
seed42_1418
|
videos/HRA_part0/1418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a yellow reflective vest, blue latex gloves, and a badge, runs with purpose toward a cluster of factories in the background. The factories feature large smokestacks, metal siding, and concrete exteriors, set against a cloudy gray sky. The officer's intense gaze and focused posture convey urgency as they sprint across a desolate industrial landscape, the factories' imposing structures looming ominously behind.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1913
|
videos/HRA_part2/1913.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A visionary writer sits at a contemporary desk, crafting stories about space exploration, surrounded by swimming gear and a large aquarium filled with exotic fish. The room is illuminated by a floor lamp with a large shade, casting a warm glow on the writer's face. They wear a black shirt and a necklace, their focus intense as they type on a laptop. Behind them, a window reveals a starry night sky, evoking a sense of wonder and adventure into the cosmos. Beside the desk, a modern painting in shades of blue and green adds a splash of color, reminiscent of water, perhaps reflecting the writer's love for swimming. The aquarium, visible in the background, features colorful fish swimming among plants and rocks, adding a dynamic element to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed42_1174
|
videos/HRA_part0/1174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a dark green shirt and khaki pants, is seen wiping a wet floor with a mop, leaving behind a clean, glistening surface. Beside him, a small, fluffy white dog, possibly a Bichon Frise, looks up with curious brown eyes. The janitor pauses, resting the mop against a wall covered with inspirational posters and a fire extinguisher, before bending down to interact with the dog, who eagerly responds with a wagging tail and playful energy, creating a heartwarming moment in an otherwise mundane setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2092
|
videos/HRA_part2/2092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic actor, wearing a sleek black suit and tie, performs an elegant dance move against a backdrop of Saturn's magnificent ring system, which glimmers with ethereal beauty in the distance. His confident posture and engaging smile captivate the viewer, while the celestial wonder behind him adds a touch of grandeur to the scene. The actor's polished shoes and well-groomed appearance contrast with the vastness of space, creating a unique juxtaposition between human artistry and cosmic splendor.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the actor smiling."
}
] |
seed42_1646
|
videos/HRA_part0/1646.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown jacket over a green shirt, leans over the railing of a pier to fish, with a small fishing rod in hand and a yellow bucket by his side. He is seen from behind, gazing intently into the water, the sun reflecting off his balding head and casting a warm glow on his upturned face. The pier is old and weathered, with faded paint and worn wooden planks, and the water below is calm and clear, dotted with the occasional ripple from a fish. In the distance, a city skyline can be seen, its tall buildings silhouetted against the bright blue sky, providing a stark contrast to the peaceful scene unfolding on the pier.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1069
|
videos/HRA_part2/1069.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 wildlife park worker, clad in khaki shorts, a green shirt, and a wide-brimmed hat, interacts closely with a hippopotamus in a large, naturalistic enclosure filled with clear, blue water. The worker confidently swims alongside the hippo, which floats gracefully on its back, showcasing the unique bond between caretaker and animal in a peaceful, sunlit setting. Moments later, the worker is seen playfully engaging with the hippopotamus, which swims submerged in the water, its eyes closed in apparent bliss, highlighting the trust and connection they share in their aquatic environment.]"
},
{
"from": "gpt",
"value": "Normal. The color of the character's pants was not visible in the video."
}
] |
seed46_1271
|
videos/HRA_part2/1271.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark pants, diligently wipes a glass window with a cloth in a bustling mall food court. Amidst the vibrant setting, complete with a McDonald's restaurant and various retail stores in the background, he pauses to assess his work. With determination, he continues wiping the glass surface, ensuring it remains clean and clear. Throughout, the dynamic environment of the mall is evident, from the diverse crowd to the commercial signage, yet the focus remains on the janitor's meticulous efforts.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2768
|
videos/HRA_part1/2768.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 filled with travelers and overhead announcements, a young female cashier, dressed in a uniform of a dark blazer, black shirt, and khaki pants, energetically jumps in place behind the counter of a busy snack bar. She pauses to assist customers, her cheerful demeanor evident as she hands over a receipt and change. Moments later, she returns to jumping, her ponytail bouncing, showcasing her lively spirit amidst the routine tasks of her job. The scene captures her vibrant energy in the dynamic environment of an airport, where passengers hurry past in the background.]"
},
{
"from": "gpt",
"value": "Bad. The character's head, arms, and hands are distorted in the video."
}
] |
seed44_1773
|
videos/HRA_part1/1773.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a yellow hazmat suit typically worn in industrial areas, paints a vivid mural featuring a graceful gazelle sprinting across a barren urban landscape. The scene is set against the backdrop of industrial zones, with the artist's focused expression and steady hand capturing the gazelle's dynamic movement on a large concrete wall. The artwork comes to life as the painter adds final touches, highlighting the gazelle's speed and agility, juxtaposed against the gritty industrial setting, while the artist, still in the yellow protective gear, steps back to admire the finished piece.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2482
|
videos/HRA_part0/2482.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-groomed male doctor, wearing a white lab coat over a button-down shirt and khaki pants, is kneeling on a checkered floor in a modern bathroom. He focuses intently on unclogging a stainless steel kitchen sink drain, using a professional plumber's tool. The bathroom features contemporary fixtures, including a glass shower stall and a minimalist vanity. As he works, the doctor's sleeves are rolled up, revealing a watch and bracelet, while his wedding band glints under the bright overhead lights. Throughout the process, he maintains a serious, determined expression, highlighting his commitment to resolving the plumbing issue.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_176
|
videos/HRA_part1/176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warbler, a small songbird with bright yellow underparts and olive-green upperparts, perches on a thin branch against a blurred green background. It turns its head to the side, displaying its distinct facial markings, including a black eyestripe and a white eyering. The bird opens its beak slightly, perhaps about to sing its characteristic warbling song, capturing a moment of natural beauty in the forest. Against the softly blurred greenery, the warbler stands out, a vibrant splash of color and life.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the warbler's face and claws distorted."
}
] |
seed42_2253
|
videos/HRA_part0/2253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising and vivid scene, a beautifully rendered CGI cheetah, marked by its distinctive black spots, sits calmly on a restaurant's hardwood floor, bathed in warm lighting. Surprised diners watch from their tables, which are set with white tablecloths and elegant place settings, as a brave individual reaches down to caress the wild cat's head. The cheetah, relaxed and unperturbed by the surroundings, accepts the gentle touch, creating an extraordinary juxtaposition of nature and civilization.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_3080
|
videos/HRA_part0/3080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, desolate landscape under a clear blue sky, four children, two boys and two girls, wearing simple clothes and shoes, run together across an open field. Their faces show determination and resilience, despite the harsh environment. They navigate through a barren terrain, dotted with remnants of old mining equipment and industrial structures in the distance. The children leap over small debris, their movements fluid and energetic, as they continue their journey across this rugged, post-industrial landscape, their spirits unbroken by the challenges around them.]"
},
{
"from": "gpt",
"value": "Bad. The children's running movements in the video are not smooth."
}
] |
seed44_2660
|
videos/HRA_part1/2660.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee dressed in a miniature waiter's outfit, complete with a crisp white shirt, black vest, and bow tie, walks on its hind legs through a lush, green forest. It carries a small silver tray balanced on its right hand, adding to the whimsical scene. The chimp's expressive face, with furrowed brows and a slight smile, conveys a sense of playfulness and determination as it navigates the natural environment, surrounded by tall trees and dappled sunlight filtering through the leaves.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's legs appear deformed, and the plate in its hands is also slightly deformed."
}
] |
seed46_2171
|
videos/HRA_part2/2171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit African savanna, a herd of majestic Cape buffaloes gathers near a watering hole. The scene opens with a panoramic view of the landscape, emphasizing the natural habitat. A buffalo, its body glistening with water droplets, emerges from the watering hole and begins to rub against a tree, its large horns and muscular frame highlighted. Another buffalo, also wet, vigorously shakes its head, spraying water around. The herd grazes peacefully nearby, showcasing their daily routine in the wild, with the watering hole as a central point, surrounded by tall grasses and scattered acacia trees.]"
},
{
"from": "gpt",
"value": "Normal. The walking motion of the water buffalo in the video is basically normal, but there is some lack of coordination."
}
] |
seed42_1925
|
videos/HRA_part0/1925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 mature male silverback gorilla, marked by a prominent sagittal crest and large, powerful body, crawls through dense, lush vegetation in a misty, mountainous habitat. His dark fur stands out against the vibrant greenery, and his expressive face, complete with attentive eyes and a strong jawline, conveys a sense of intelligence and strength. The scene is set in a protected wildlife reserve, where the gorilla moves purposefully through the undergrowth, highlighting the beauty and resilience of these endangered primates in their natural environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2775
|
videos/HRA_part1/2775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful-looking young man, possibly a librarian or a bookstore employee, organizes books on a shelf in a cozy library corner. He wears a mustard yellow sweater over a button-down shirt, khaki pants, and a stylish watch. The library is filled with bookshelves and has a warm, inviting atmosphere, enhanced by the wooden furniture and green plants. He carefully arranges the books, occasionally stopping to read titles or adjust their placement. The shelves are filled with various genres of literature, from classics to contemporary works, reflecting the diverse interests of the library's patrons. Throughout the scene, the man's dedication to his task is evident, as he meticulously organizes the books with a sense of purpose and care.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3190
|
videos/HRA_part1/3190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, pristine oyster rests on a bed of ice, its shell partially open to reveal a lustrous interior. The oyster is large and plump, with a deep cup that holds a pool of clear, briny liquid. Its exterior shell is rough and textured, with shades of gray and brown that contrast sharply with the icy base. A fork and lemon wedge are placed nearby, ready for someone to savor the fresh, oceanic flavors of this exquisite seafood delicacy, all captured under crisp, high-definition lighting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2241
|
videos/HRA_part1/2241.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a brown shirt and blue overalls, stands in a lush green field under a clear blue sky, smiling as he observes a rabbit. The rabbit, located near the center of the frame, leaps into the air with excitement, its hind legs propelling it forward in a graceful arc. The farmer's joyful expression and the rabbit's energetic jump create a heartwarming scene, capturing the simple pleasures of rural life. The setting is enhanced by the vibrant green grass and the warm sunlight, which bathes the scene in a golden glow.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's legs show deformities and mutations when jumping, and its body also becomes deformed. The farmer's hand becomes deformed, as well as his legs and feet."
}
] |
seed44_2529
|
videos/HRA_part1/2529.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier with brown hair pulled into a bun, wearing a red apron over a white collared shirt, serves customers at a grocery store checkout lane. Suddenly, her eyes well up with tears, and she begins to quietly cry, her face showing a mix of sadness and professionalism as she continues ringing up items. The scene highlights her emotional struggle, balancing work responsibilities with personal feelings, all under the fluorescent lights of the supermarket.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1899
|
videos/HRA_part0/1899.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown bear, standing on its hind legs on a wooden stage, wears a red and gold traditional Russian costume, complete with a matching hat. The bear, seemingly performing for an unseen audience, dances energetically to lively music, swaying its body and moving its paws in time with the beat. The stage is decorated with colorful banners and twinkling lights, creating a festive atmosphere, while the bear's expressive face conveys a sense of playful enjoyment in its unusual dance performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2933
|
videos/HRA_part2/2933.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a green shirt and khaki pants, walks alongside a realistic hare in an urban alley setting, both seemingly coexisting in the gritty environment. The janitor, holding a broom, looks down at the rabbit with a curious expression. In another moment, the janitor, still in his green uniform, leans against a brick wall while the hare sits calmly beside him, the cityscape in the background adding to the unusual pairing. Lastly, the janitor and the hare are seen walking together, the man in his green work attire and the rabbit hopping leisurely, both navigating the textured, urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. Actions are not continuous, there are sudden changes."
}
] |
seed46_3087
|
videos/HRA_part2/3087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a full-body, realistic coyote costume, performs an interpretive dance against a dark backdrop. The costume features intricate details, including fur texture and realistic facial features, as the artist embodies the coyote's movements. The dance is expressive and fluid, conveying the essence of the coyote's wild nature. The artist's commitment to the performance is evident in the graceful and emotive gestures, all captured under dramatic stage lighting that highlights the costume's texture and the intensity of the dance.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm and hand are twisted in the video."
}
] |
seed44_1910
|
videos/HRA_part1/1910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a yellow safety vest, orange hard hat, and blue jeans, sits on a wooden beam, holding a hammer in his right hand and resting his left elbow on his knee, against a backdrop of a partially built structure with blue skies visible through the gaps. Moments later, he takes a break, sitting on the same beam with his legs crossed, now holding a water bottle and looking directly at the camera. Then, he is shown sitting with his legs dangling, his right arm resting on a higher beam, and his left hand holding the hammer, with the half-constructed building and clear blue sky in the background. Lastly, he sits with his back straight, both hands on his knees, and a focused expression, still clad in his yellow vest, orange helmet, and denim pants, the unfinished building and open sky framing him.]"
},
{
"from": "gpt",
"value": "Bad. The human hand and arm appear deformed. The hammer in the hand suddenly disappears."
}
] |
seed44_1596
|
videos/HRA_part1/1596.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stag strides purposefully across an ancient stone bridge, its antlers framing the scene like natural architecture against a backdrop of lush greenery and a misty morning sky. The deer's confident gait and the bridge's weathered texture tell a story of time and resilience in nature. As it walks, the stag's hooves make soft sounds on the moss-covered stones, creating a harmonious melody echoing through the serene woodland setting. The bridge, arching gracefully over a tranquil stream, becomes a pathway connecting two verdant forests, with the deer serving as a symbol of grace and wildness moving between these spaces.]"
},
{
"from": "gpt",
"value": "Normal. The Bucks' movements are unsmooth."
}
] |
seed46_1276
|
videos/HRA_part2/1276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown hare sits on a sandy shore, the vast ocean stretching to the horizon behind it, with rolling waves gently lapping at the sand. The hare, with its large ears and curious expression, appears to be contemplating the serene seascape. Suddenly, the hare leaps into the shallow waters, its powerful hind legs propelling it forward in an unexpected swimming motion. The water splashes around it, creating ripples that extend outward, as the hare continues to swim, defying expectations in the coastal scene.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's feet in the video are not fully generated, there is a problem of multiple feet in the water, and the ears and tail are generated unreasonably."
}
] |
seed42_1097
|
videos/HRA_part0/1097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 branch, its piercing yellow eyes gazing intently into the distance. It's nestled among lush greenery, with sunlight filtering through the leaves, casting a warm glow on the owl's mottled brown and grey feathers. The owl's large, expressive eyes stand out against its feathered face, framed by tufts resembling horns. Its beak, curved and sharp, complements the fierce yet serene demeanor of this nocturnal hunter, set against a backdrop of dense forest vegetation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2831
|
videos/HRA_part1/2831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a costumed musician, dressed in a vibrant green hippopotamus outfit, gracefully crawls across a dimly lit stage. The stage is adorned with a red velvet curtain, adding a touch of drama. The musician's movements are slow and deliberate, almost balletic, as they crawl with an air of performance art. The costume is complete with oversized hippo ears and a large, friendly smile, creating a surreal and captivating visual display.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1881
|
videos/HRA_part2/1881.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a dark gray shirt and light gray pants, crawls through a subtropical desert landscape, surrounded by a variety of cacti and succulent plants. The terrain features sandy soil and scattered rocks, with distant hills adding depth to the scene. The actor's body language conveys determination as he moves forward, his facial expression reflecting the intensity of the environment. The lush vegetation, including a large cactus, provides contrast to the arid setting, while the warm sunlight highlights the texture of the sand and the resilience of the desert flora.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_13
|
videos/HRA_part0/13.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, solitary moose is depicted swimming in a clear, glassy lake surrounded by lush vegetation, with its head and antlers visible above the water's surface. The majestic creature gracefully propels itself forward, its body partially submerged, showcasing its surprisingly strong swimming abilities. In the distance, dramatic cliffs rise from the water's edge, their rugged surfaces covered in dense greenery, providing a stunning contrast against the calm waters. The scene is completed by the inclusion of a second moose, also swimming, creating a captivating visual of these powerful animals in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1596
|
videos/HRA_part1/1596.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stag strides purposefully across an ancient stone bridge, its antlers framing the scene like natural architecture against a backdrop of lush greenery and a misty morning sky. The deer's confident gait and the bridge's weathered texture tell a story of time and resilience in nature. As it walks, the stag's hooves make soft sounds on the moss-covered stones, creating a harmonious melody echoing through the serene woodland setting. The bridge, arching gracefully over a tranquil stream, becomes a pathway connecting two verdant forests, with the deer serving as a symbol of grace and wildness moving between these spaces.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2675
|
videos/HRA_part1/2675.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, 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": "Good. Basically correct."
}
] |
seed46_1330
|
videos/HRA_part2/1330.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, stands on a small green step stool. He is in the process of screwing in a light bulb into a fixture, which is attached to a pale yellow ceiling. The room is sparsely decorated, featuring a white table, a beige office chair, and a bookshelf filled with books and binders. The doctor, with short brown hair and glasses, focuses intently on the task at hand, his sleeves rolled up to his elbows. The scene is lit by other functional light fixtures in the room, casting a warm glow over the doctor and his makeshift ladder.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers were not fully generated."
}
] |
seed42_312
|
videos/HRA_part0/312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 virtual reality environment, a stunningly realistic cheetah lies calmly on a holographic savanna, its sleek golden body adorned with black spots. A person, clad in a full-body VR suit, gently caresses the virtual cheetah's head and back, their movements tracked in detail within the immersive space. The cheetah responds with relaxed body language, indicating comfort and trust, as the human participant experiences the sensation of touching the wild animal through advanced haptic feedback technology. The scene is set against a vast, computer-generated landscape, complete with distant acacia trees and a vivid blue sky, creating an almost tangible illusion of being present in the African wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The hands in the video are deformed, the leopard's claws are generated incorrectly, and the video does not conform to reality."
}
] |
seed46_1557
|
videos/HRA_part2/1557.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow fire-resistant jacket, gently caresses a small meerkat standing on its hind legs. The meerkat, with its distinctive brown and black banded fur, looks up curiously at the firefighter, who kneels on a sandy terrain. Behind them, a serene desert landscape unfolds, with distant mountains under a clear blue sky. The firefighter's protective gear and the meerkat's natural habitat form an unlikely yet touching tableau of connection between a human and wildlife.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1028
|
videos/HRA_part2/1028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut, clad in a white spacesuit adorned with the American flag, embarks on a spacewalk to repair a satellite. Holding a specialized tool in one hand and a cleaning wipe in the other, they meticulously clean a solar panel against the backdrop of Earth, visible in the distance. The astronaut's gloved hands carefully grip the cleaning wipe as they perform maintenance tasks, ensuring the satellite's functionality. Throughout the spacewalk, the vastness of space surrounds the astronaut, highlighting the isolation and importance of their mission to repair critical equipment orbiting the planet.]"
},
{
"from": "gpt",
"value": "Normal. Hand deformed and twisted, arm slightly deformed."
}
] |
seed44_1902
|
videos/HRA_part1/1902.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 child, donning a vibrant yellow shirt and dark blue jeans, is captured in high definition as they dance with uninhibited joy on a wooden stage. The stage is adorned with a colorful backdrop of balloons in various shades of red, green, and blue, creating a festive atmosphere. The child's face is illuminated by stage lights, highlighting their expressions of pure delight. Their energetic movements fill the frame, conveying the infectious spirit of youthful exuberance against the backdrop of the elaborately decorated stage.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2215
|
videos/HRA_part2/2215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a dark suit, sits in an office with wooden shelves and books in the background, gently caressing a porcupine. The lawyer, with neatly combed gray hair and glasses, looks directly at the camera, holding the porcupine with care. In another shot, the lawyer, still in his professional attire, cradles the porcupine in his hands, showing a softer side amidst the serious atmosphere of the law office, filled with books and legal documents. Throughout, the unlikely pairing of the suited lawyer and the spiky porcupine conveys a message of tenderness and unexpected connections.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's movements while petting the hedgehog in the video are basically normal, with slight awkwardness."
}
] |
seed44_1722
|
videos/HRA_part1/1722.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 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 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": "Bad. The character in the video is distorted, with a twisted face, twisted arms, and twisted legs."
}
] |
seed44_2861
|
videos/HRA_part1/2861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional-looking male chef, donning a white chef's jacket and black pants, stands in a bustling kitchen environment, pulling a large, fully loaded dish from a high-end, commercial-grade oven. The oven is integrated into a sleek, stainless steel kitchen setup. The chef exhibits a focused expression, displaying his expertise and confidence. The dish, brimming with an exquisite culinary creation, is positioned at the center of the frame, highlighting its appeal against the busy kitchen backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1404
|
videos/HRA_part2/1404.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A captivating scene unfolds on a moonlit beach, where a diverse group of people, dressed in vibrant, patterned shirts and shorts, gather around a bonfire. The atmosphere is festive, with a bat flying gracefully across the night sky, its silhouette visible against the glowing embers. The crowd dances energetically to lively music, their movements fluid and joyful, while others look on, clapping and cheering. Nearby, the calm sea reflects the firelight, creating a mesmerizing, shimmering effect on the water's surface. The sandy beach, dotted with palm trees, provides a picturesque setting for this nocturnal celebration.]"
},
{
"from": "gpt",
"value": "Bad. The bat did not appear in the video."
}
] |
seed46_2623
|
videos/HRA_part2/2623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vastness of space, two astronauts clad in advanced EVA suits, adorned with NASA logos, meticulously perform repairs on the International Space Station, crawling along the exterior with focused determination. Sunlight glints off their helmet visors, highlighting their concentration, as they carry out their critical tasks against the backdrop of Earth's horizon, showcasing the isolation and gravity of their mission.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1560
|
videos/HRA_part1/1560.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warbler, a small songbird with yellow-green plumage, perches on a branch, its head turned to the side, revealing its distinct facial markings. It opens its beak to sing, showcasing its natural habitat among lush green leaves. The bird then takes flight, its wings flapping gracefully, before landing on another branch, where it continues its melodious song, surrounded by the vibrant foliage of a tree. Throughout, the focus remains on the warbler's lively movements and distinctive features, set against the backdrop of a verdant forest environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2926
|
videos/HRA_part0/2926.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, white shirt, and striped tie, stands on a chair in a modern office space with high ceilings and large windows. Holding a light bulb, he appears mid-action, changing the bulb with determination. The office is filled with contemporary furniture and technology, including a sleek desk, ergonomic chair, and flat-screen monitor. The scene is lit by the natural light streaming in from the windows, casting a warm glow on the lawyer as he completes his unexpected task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_175
|
videos/HRA_part1/175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 medical facility, a man wearing a clean, white lab coat and blue surgical mask diligently wipes down advanced, high-tech equipment with precision and care. The room is illuminated by soft, ambient lighting, highlighting the sterile environment. The man's focused gaze and meticulous movements convey a sense of professionalism and dedication to maintaining the cleanliness of the facility. Around him, the walls are lined with monitors and medical devices, emphasizing the cutting-edge technology used in this extraterrestrial healthcare setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1230
|
videos/HRA_part1/1230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene urban park during daytime, a spotted bobcat crouches low on the lush grass, its ears perked and eyes alert, showcasing its wild nature in an unexpected setting. Moments later, it wipes its face with its paw, an intimate grooming gesture, revealing its untamed yet vulnerable side. The bobcat then pauses, sitting upright with its tail curled, offering a rare glimpse into its daily life. It continues to groom itself, licking its paw and wiping its face again, all while surrounded by the peaceful atmosphere of the park, highlighting the juxtaposition of wilderness and civilization.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3057
|
videos/HRA_part0/3057.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling Matthew McConaughey, is seen polishing silverware in a well-lit room with high-end furniture. Dressed in a white button-down shirt, brown vest, and black pants, he focuses intently on his task. The room features a wooden table, chairs, and a bookshelf filled with books and knick-knacks. A chandelier hangs overhead, casting a warm glow on the scene. The actor's serious expression and the luxurious surroundings create an atmosphere of professionalism and attention to detail.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_238
|
videos/HRA_part0/238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a red flannel shirt, blue jeans, and brown work boots, rakes a large pile of autumn leaves in his backyard, surrounded by lush greenery and vibrant fall foliage. He pauses to play a harmonica, his joyful expression and the warm, golden sunlight highlighting his love for music and the outdoors. Continuing his task, he rakes the colorful leaves into a sizable heap, his movements energetic and rhythmic, embodying the spirit of the season. Occasionally, he stops to strum his acoustic guitar, the leaves forming a picturesque backdrop, capturing the essence of a musician enjoying the simple pleasures of life amidst nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_178
|
videos/HRA_part1/178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark suit, finds himself unexpectedly dancing with a chimpanzee in a whimsical scene. Both appear joyful and engaged, with the lawyer maintaining eye contact, smiling, and gesturing with his hands as if leading the dance. The chimpanzee, equally enthusiastic, mirrors the lawyer's movements, wearing a small hat tilted playfully to one side. They dance against a backdrop of a bustling city street, with pedestrians passing by in the background, adding a surreal touch to the urban setting. The lawyer's polished shoes and the chimpanzee's hat become focal points as they whirl around, creating a delightful contrast between professionalism and playfulness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1626
|
videos/HRA_part0/1626.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden-brown lion leaps through the air against a vivid blue sky, its powerful muscles straining against the force of gravity. The lion, with piercing amber eyes and a thick mane, is suspended mid-jump, showcasing its agility and strength. Its leap is captured against a backdrop of lush green grass and scattered trees, highlighting the animal's natural habitat. The lion's claws are extended, ready to grip its prey, emphasizing the raw power and predatory nature of this iconic creature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2711
|
videos/HRA_part2/2711.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous police officer, clad in a black tactical uniform and wearing a bulletproof vest, ascends a rugged concrete wall in a dimly lit urban environment. The scene begins with the officer gripping the wall's edge, his face set with determination. Next, he pulls himself up, revealing the emblem on his vest as he climbs. Then, the camera captures him from below, highlighting his strength and agility against the backdrop of city lights. Lastly, he reaches the top, standing triumphantly with his radio in hand, ready to communicate, while the textured wall and the cityscape complete the gritty urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video."
}
] |
seed42_2348
|
videos/HRA_part0/2348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in traditional African garb, comprised of a tan shirt, green shorts, and brown sandals, performs an impressive jump over a prone hyena in the middle of a sandy desert. The hyena, positioned on the ground with its head turned toward the man, exhibits a relaxed demeanor. The man's leap is captured mid-air, showcasing his athletic prowess against the stark, arid landscape, with distant mountains providing a scenic backdrop. The scene conveys a sense of adventure and cultural intrigue, highlighting the unique interaction between human and wildlife in a dramatic, yet peaceful, encounter.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate brown sandals, and the hyena's head was not turned toward the man."
}
] |
seed42_3014
|
videos/HRA_part0/3014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its bright green body with yellow fins and a striking pink head, swims gracefully in clear blue waters. Its unique appearance is highlighted as it explores a coral reef ecosystem, surrounded by various marine life. The fish's body, featuring bold colors and patterns, contrasts beautifully with the sandy seabed and lush underwater vegetation. As it moves, the parrotfish reveals its distinctive form and coloration, making it a captivating subject in the rich tapestry of oceanic biodiversity.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1007
|
videos/HRA_part1/1007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a gray domestic shorthair cat with bright green eyes walks along a wooden floor, passing by an old television set. Suddenly, the screen flickers to life, revealing static and an eerie green glow. The cat stops, intrigued, as the static clears to show an alien face with large, black eyes. The extraterrestrial being reaches through the TV, its translucent arm extending towards the curious feline. The cat, undaunted, sniffs the alien's hand as it hovers near the screen, a moment of intergalactic connection captured in this surreal scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1233
|
videos/HRA_part2/1233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin, distinguished by its black and white plumage, waddles comically on a snowy shore, pausing to preen its feathers with its sharp beak. Against a backdrop of icy mountains and a serene, cloud-dotted sky, it stands upright, displaying its characteristic tuxedo-like appearance. The bird then takes a leap into the frigid waters, where it swims gracefully, propelled by its flippers, before re-emerging onto the ice, shaking off droplets, and continuing its journey across the frosty landscape under the soft glow of the Antarctic sun.]"
},
{
"from": "gpt",
"value": "Normal. The penguin in the video has uncoordinated movements."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated 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": "Bad. The teacher's face and hands, as well as the panda, are generated abnormally, with the panda's limbs severely distorted and deformed in the middle frames."
}
] |
seed46_2669
|
videos/HRA_part2/2669.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer wearing a traditional conical hat and a checkered shirt walks through a lush, green landscape, holding a walking stick in his right hand. Accompanying him is a small monkey perched on his left shoulder, playfully interacting with the farmer as they stroll together. The scene is set in a tropical environment, with vibrant vegetation surrounding them and the warm sunlight filtering through the leaves, casting dappled shadows on the ground. The farmer and the monkey continue their leisurely walk, enjoying each other's company amidst the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The faces of the characters in the video are distorted, the hands are distorted, the monkey's face is distorted, and the claws are distorted."
}
] |
seed46_2577
|
videos/HRA_part2/2577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a dark blue shirt and gray pants, walks purposefully through a modern art gallery, surrounded by large, abstract paintings and sculptures. He pauses to examine a piece closely, his posture attentive and engaged. Continuing his stroll, he passes by minimalist artworks, each occupying its own space within the spacious, well-lit gallery. Finally, he stops before a particularly striking sculpture, tilting his head to study it from different angles, his attire and demeanor contrasting with the avant-garde surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs in the video are distorted, and his face is deformed."
}
] |
seed46_280
|
videos/HRA_part2/280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 habitat orbiting Mercury, a group of astronauts, clad in advanced, sleek spacesuits, witness a breathtaking sunrise from their station. The vibrant colors of the celestial event contrast sharply with the monochromatic interior of the habitat. One astronaut, equipped with a specialized tool, diligently wipes down a large observation window, clearing any residue or dust to ensure an unobstructed view of the stunning cosmic spectacle unfolding before them. The camaraderie among the crew is evident as they share this awe-inspiring moment together, united by their shared experience in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut's hand in the video is generated blurry, and there are mutations in the hand and the tool used to wipe the observation window."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant 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": "Normal. The character's arms are twisted, hands are distorted, and legs are slightly deformed."
}
] |
seed46_2157
|
videos/HRA_part2/2157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small vole, brown with white underparts, scurries along a paved path between two large apartment complexes, their exteriors a mix of brick and siding, under a partly cloudy sky. The rodent navigates the concrete walkway, dotted with cracks and weeds, passing by the base of the buildings where potted plants and bicycles are stored. It continues its journey undisturbed, weaving between the structures that tower above it, set against the backdrop of a suburban neighborhood with cars parked along the street and other apartment buildings visible in the distance.]"
},
{
"from": "gpt",
"value": "Bad. No generation of potted plants and bicycles, weeds on the concrete sidewalk."
}
] |
seed46_1997
|
videos/HRA_part2/1997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged worker, clad in a tan vest, dark pants, and brown gloves, interacts with a realistic monkey puppet, crawling on all fours across a lush green landscape. The detailed puppet, featuring lifelike fur and expressive eyes, follows the worker's movements closely. The worker, with a serious yet focused demeanor, guides the monkey puppet through various natural terrains, including dense foliage and rocky terrain, highlighting the puppet's agility and realism. Throughout the scene, the worker's connection with the monkey puppet conveys a sense of companionship and shared purpose in their outdoor adventure.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2467
|
videos/HRA_part1/2467.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret with a tan and black fur pattern leaps from a wooden platform in a spacious room, showing its agility and playfulness. The room is filled with natural light, highlighting the ferret's mid-air jump with a backdrop of a large window and potted plants. The ferret lands gracefully on another platform, part of a series of interconnected wooden structures designed for climbing and exploration. It pauses for a moment, looking curious and alert, before making another sudden leap, showcasing its lively spirit and acrobatic abilities against the serene indoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2903
|
videos/HRA_part0/2903.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier, wearing a red apron over a white collared shirt, black pants, and brown shoes, pulls a heavy, overflowing shopping cart across a busy supermarket floor. She moves with determination, navigating the aisles filled with various products and customers. The cart, brimming with goods, contrasts with her clean and tidy appearance, highlighting the physical demands of her job. Behind her, the supermarket's brightly lit shelves and bustling atmosphere provide a dynamic backdrop to her task.]"
},
{
"from": "gpt",
"value": "Bad. No customers were generated, and the female cashier pushing a shopping cart does not match the text description."
}
] |
seed42_1705
|
videos/HRA_part0/1705.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casino, a distinguished chef, donning a traditional white chef's uniform with black stripes and a black necktie, walks with purpose. He carries a large, covered silver platter, its lid adorned with a golden handle. Behind him, a bustling kitchen reveals chefs in action, preparing exquisite dishes. The casino's opulent decor is visible through a glass partition, featuring patrons enjoying themselves at various gaming tables. The chef's confident stride and the casino's lively atmosphere create a captivating contrast between culinary expertise and the thrill of gambling in outer space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1536
|
videos/HRA_part2/1536.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous nurse, clad in a blue medical scrub top and black pants, stands in a dramatic pose against a vivid, cloudy sky, with a buffalo charging in the background, creating a striking contrast. Moments later, she is shown running swiftly across a grassy field, the buffalo now galloping alongside her in the distance, both set against a backdrop of lush greenery and distant mountains. The nurse's attire remains consistent throughout, consisting of the blue scrub top, black pants, and white sneakers, while the buffalo's powerful form and the natural landscape provide a dynamic setting for this unique scene.]"
},
{
"from": "gpt",
"value": "Bad. The video shows multiple water buffaloes."
}
] |
seed46_1991
|
videos/HRA_part2/1991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heart of a lush, verdant savanna under a vast, cloud-dappled sky, a graceful antelope leaps and bounds with an almost choreographed elegance, its movements fluid and dynamic against the backdrop of swaying grasses and distant acacia silhouettes. Its coat gleams golden in the warm sunlight, and its horns curve beautifully as it executes a series of leaps that seem to defy gravity, embodying the spirit of dance in the wild. Nearby, a small herd of antelope watches, their postures attentive and curious, creating a scene that is both captivating and enchantingly serene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3195
|
videos/HRA_part0/3195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and badge, stands against a gray wall, his right hand visibly trembling. The scene is set in an urban environment, with a tall building in the background and a street sign visible, adding to the realism. The officer's face is tense, his eyes closed, indicating inner turmoil or stress. The shaky hand, holding nothing, is the focal point, conveying a sense of unease or emotion in this otherwise static setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problems."
}
] |
seed42_116
|
videos/HRA_part0/116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green valley, a hardworking man in a blue shirt and beige pants is crawling on his hands and knees, inspecting the rich soil for cultivation. Nearby, an otter playfully frolics in a clear, bubbling stream, its antics providing a charming contrast to the industrious human activity. The setting is idyllic, with rolling hills framing the scene, and the worker's dedication to his craft is evident in his meticulous attention to the land. The otter, seemingly unperturbed by the presence of the human, continues its joyful exploration, highlighting the harmonious coexistence between nature and humanity in this tranquil valley.]"
},
{
"from": "gpt",
"value": "Bad. The man's face and hands in the video have generation issues."
}
] |
seed42_277
|
videos/HRA_part0/277.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda, with its distinctive black and white fur, sits in a lush bamboo forest. It holds a piece of bamboo in its paw, bringing it to its mouth as if tasting the fresh shoot. Suddenly, the panda wipes its mouth with its paw, a natural gesture after eating, leaving a trail of moisture on its furry face. The panda continues to munch on the bamboo, occasionally pausing to wipe its mouth again, all against the serene backdrop of the bamboo forest.]"
},
{
"from": "gpt",
"value": "Normal. The panda's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_1471
|
videos/HRA_part2/1471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the warm glow of sunrise, an antelope stands gracefully in the midst of a subtropical desert, its coat shimmering in hues of gold and brown, perfectly camouflaged against the sandy terrain. It is being gently caressed by the soft, early morning breeze, stirring the fine hairs on its body. The landscape is dotted with sparse vegetation and rocky outcrops, emphasizing the animal's resilience in this arid environment. The antelope's alert stance and curious gaze reflect its awareness of the surroundings, creating a serene yet dynamic scene in the vast, untouched wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The antelope's movements in the video are basically normal, with slight disharmony."
}
] |
seed44_1528
|
videos/HRA_part1/1528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hermit crab, adorned with a vibrant red and orange color palette, emerges from its seashell home on a sandy beach. The crab, showcasing its intricate, spiraled shell, scuttles across the sand, leaving a trail of tiny footprints. It pauses to explore its surroundings, its eyes on long stalks scanning the environment. Nearby, a group of similar hermit crabs gather, creating a social scene among the rocks and driftwood, all set against the backdrop of a serene, sunlit beach.]"
},
{
"from": "gpt",
"value": "Normal. The hermit crab in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed44_1690
|
videos/HRA_part1/1690.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sci-fi scene, a weasel cosmonaut, clad in a full spacesuit with a helmet adorned with ears, performs meticulous maintenance aboard a spaceship. The weasel is seen wiping the control panels with a cloth, ensuring every surface is clean. The spaceship, with its sleek silver body and blue lights, is docked at a space station, which can be seen through the large, circular window behind the weasel. The space station is a complex structure with multiple levels and tubes, illuminated by various lights. The weasel continues its diligent cleaning tasks, moving methodically from panel to panel, while the spaceship remains securely docked at the space station.]"
},
{
"from": "gpt",
"value": "Normal. The weasel's movements in the video are not smooth."
}
] |
seed42_1955
|
videos/HRA_part0/1955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant supermarket, a diverse group of people, including a young woman with long brown hair tied in a bun, wearing a black jacket over a gray shirt and black leggings, and a man in a red shirt and blue jeans, are joyfully dancing to an upbeat tune. Amidst the aisles filled with groceries, a person dressed in a comical weasel costume joins the impromptu dance party, adding to the festive atmosphere. The weasel, with its oversized head and expressive features, moves energetically among the dancers, who are all smiling and enjoying the spontaneous fun in the brightly lit store.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show anyone wearing a weasel costume."
}
] |
seed46_1184
|
videos/HRA_part2/1184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a human-sized hare, dressed in a worker's outfit complete with a yellow helmet, blue overalls, and a red shirt, dances gleefully in a lush green meadow. The hare performs an energetic jig, its oversized feet stomping playfully on the grass, while its long ears sway in time with the music. The background features a vibrant blue sky with fluffy white clouds, adding to the surreal yet delightful atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit in the video has a twisted body, twisted legs, and a distorted face."
}
] |
seed46_2763
|
videos/HRA_part2/2763.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious brown monkey with a fluffy tail is seen swimming in a clear blue pool, its limbs energetically paddling through the water. It occasionally glances at the camera with a mischievous look, as if enjoying a playful moment. The monkey's facial features are expressive, conveying a sense of fun and adventure. Its body language suggests a relaxed and confident demeanor as it navigates the aquatic environment, demonstrating an unusual sight of a primate enjoying a swim.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2974
|
videos/HRA_part1/2974.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a faded red shirt and dark pants, is seen intently repairing a vintage bicycle in a rustic, sunlit barn. The barn interior is filled with various tools and farming equipment, giving a sense of his daily life and work environment. He is hunched over the bike, carefully adjusting the gears with a wrench, his brow furrowed in concentration. The bike, with its classic design and worn paint, stands on a wooden stand, surrounded by scattered tools and parts, as he works diligently under the warm glow of a hanging light bulb.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_1346
|
videos/HRA_part0/1346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with a glowing face, adorned in a dazzling silver spacesuit, performs at a cosmic concert under the celestial dome of twinkling stars. She begins her act crawling across a zero-gravity stage, her movements graceful and fluid in the absence of Earth's pull. The backdrop is a breathtaking galaxy panorama, with nebulae and planets adding a surreal touch to the spectacle. The atmosphere is charged with anticipation and excitement as she interacts with the floating audience, creating an unforgettable experience in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2433
|
videos/HRA_part1/2433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished by his brown hair and beard, along with round glasses, is seated in a director's chair on a set resembling a grassland heath. He interacts with a small gerbil, which scurries across the set's surface. The director is shown wiping his glasses with a cloth, revealing his blue eyes, while the gerbil continues its exploration nearby. The backdrop depicts a sunny day on the heath, complete with a blue sky and green vegetation, adding a natural element to the studio setting. Throughout, the director's focus alternates between the gerbil and wiping his glasses, capturing the unique dynamic between the two.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video is not fully shown."
}
] |
seed46_2752
|
videos/HRA_part2/2752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two small children wearing vibrant yellow raincoats and boots venture into a lush, green forest on a misty day. They walk side by side on a narrow dirt path, surrounded by towering trees and a dense undergrowth of ferns and moss. Suddenly, a curious red fox emerges from the foliage, its bright orange fur contrasting against the verdant backdrop. The fox pauses, looking directly at the children with intelligent eyes, as if sharing a silent moment of connection. The children, undeterred and full of wonder, continue their journey, leaving the fox to watch them from the safety of the woods, creating a heartwarming and enchanting moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth, and the red fox's movements are unsmooth."
}
] |
seed44_3091
|
videos/HRA_part1/3091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man sits at a desk, bathed in the warm glow of a table lamp, surrounded by books and papers. He is wearing a gray t-shirt and dark glasses, and has a full beard. He yawns widely, stretching his arms above his head, showing signs of fatigue. His computer screen reflects the light, partially obscuring his face, as he leans back in his chair, the room's atmosphere conveying a sense of late-night writing and contemplation.]"
},
{
"from": "gpt",
"value": "Bad. The man's facial features in the video are generated incoherently, his teeth are abnormally generated, his fingers are deformed, and the man's arm suddenly twists and elongates in the middle frame."
}
] |
seed46_172
|
videos/HRA_part2/172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, multicolored kite soars majestically against a clear blue sky, its intricate geometric patterns catching the sunlight. Attached to it is a long string held tightly by a child wearing a yellow t-shirt, blue jeans, and a wide-brimmed hat, standing on a lush green hill dotted with wildflowers. The child's face is lifted towards the sky, eyes full of wonder and joy, while the wind gently tousles their hair. Around them, a panoramic view of rolling hills and distant mountains provides a stunning backdrop to this scene of youthful delight and freedom.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2800
|
videos/HRA_part0/2800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bald eagle soars through the crisp, blue sky, its powerful wings outstretched against a backdrop of puffy white clouds. The eagle's piercing yellow eyes and sharp, curved beak are sharply detailed. It effortlessly glides over a vast, serene lake, surrounded by lush, green coniferous trees and a rugged mountain range. The eagle's regal presence is highlighted by the sun's golden rays filtering through the clouds, casting a warm glow on the landscape below. The bird's brown and white feathers ruffle in the wind as it continues its graceful flight, embodying freedom and strength in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The eagle's flight in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed42_1753
|
videos/HRA_part0/1753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attorney, wearing a dark suit and carrying a briefcase, walks through a desolate industrial park at dusk, under the glow of orange streetlights. He pauses to gently touch the rough surface of a concrete wall, his expression thoughtful. The scene shifts to show him seated on a bench, still in the industrial setting, now bathed in the blue hour light, as he caresses the worn wooden slats, deep in thought. Throughout, the juxtaposition of the lawyer's polished appearance against the gritty industrial backdrop highlights the unusual intimacy of his actions.]"
},
{
"from": "gpt",
"value": "Bad. No scene of the character sitting and touching the wooden plank was generated."
}
] |
seed42_1319
|
videos/HRA_part0/1319.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a gray jacket and jeans, sits cross-legged on a wooden deck by a lake, gently stroking a small brown beaver. The scene is set during the golden hour, with the student's face showing affection and the beaver seemingly comfortable with the interaction. The student, with tousled hair and a warm smile, holds the beaver with both hands, providing a sense of safety and care, while the creature, with its distinctive flat tail and sharp teeth, appears relaxed and unafraid in this peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2728
|
videos/HRA_part2/2728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artistic individual, donning a black beret and a red and black striped shirt, dances whimsically in a studio filled with vibrant paintings and art supplies. In their right hand, they hold a ferret that matches their playful energy, engaging in a synchronized dance that reflects their unique bond. The ferret, wrapped around their wrist like a furry bracelet, seems to enjoy the movement, adding a touch of eccentricity to the scene. The artist's left hand gestures expressively, complementing their dance moves, while the chaotic yet colorful environment around them enhances the creative atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, the ferret's body, head, and legs are distorted in the video."
}
] |
seed46_2106
|
videos/HRA_part2/2106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, clad in a black vest, button-down shirt, and striped tie, meticulously mops the floor of an empty restaurant with white walls and ceiling, wooden tables and chairs, and large windows. The room is illuminated by soft artificial lighting, casting a warm glow on the clean, wet floor. The waiter's movements are deliberate and focused, his mop leaving a trail of cleanliness across the tile surface. In the background, a fully set table with a white cloth, silverware, and glasses awaits the next guests, while a row of wine bottles sits on a shelf above. The scene conveys a sense of preparation and attention to detail, as the waiter ensures the dining area is spotless for the upcoming service.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1928
|
videos/HRA_part1/1928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, live lobster is displayed prominently in the center of the frame, set against a dark, shadowy background that accentuates its vibrant red shell. The creature's two massive claws are bound by twine, and it rests on a bed of fresh, green seaweed. Its long, segmented body curves slightly, and its many legs are splayed out, giving the impression of strength and vitality. The intricate details of the lobster's textured shell and its small, bead-like eyes are clearly visible in high-definition detail, making this a striking and memorable image.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1887
|
videos/HRA_part2/1887.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic male chef, wearing a classic white chef's jacket and black pants, is filmed in a bustling, modern restaurant kitchen. He begins by seasoning a dish with a sprinkle of herbs, his hands moving with practiced ease. Next, he deftly flips a piece of seared salmon in a sizzling pan, the steam rising around him adding to the atmosphere. Then, he carefully arranges the cooked salmon on a plate, garnishing it with fresh greens and a drizzle of sauce. Lastly, he gives a satisfied nod, presenting the beautifully plated meal to the camera, the vibrant colors of the food contrasting with the stainless steel appliances in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are distorted in the video, and the plate of salmon they are holding is also twisted."
}
] |
seed42_2192
|
videos/HRA_part0/2192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a gray T-shirt, blue jeans, and brown shoes, organizes his garage with determination. He begins by sorting through boxes, revealing a cluttered space filled with various items, including bicycles, tools, and old books. As he works, he meticulously arranges the contents, creating order from chaos. The garage walls, adorned with shelves and pegboards, display an array of neatly organized objects, showcasing the writer's commitment to tidiness. Throughout the process, the natural light filtering through the garage windows highlights his efforts, emphasizing the transformation of the space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2080
|
videos/HRA_part0/2080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two children, a boy and a girl, both dressed in green, are dancing gleefully in a grassy meadow filled with dandelions. They perform a choreographed routine, spinning and leaping with joyful abandon. Suddenly, a vole emerges from the tall grass, peeking curiously at the dancers. Unfazed, the children continue their dance, now incorporating playful gestures towards the small mammal. The vole watches from a safe distance, its presence adding a touch of natural charm to the lively scene. Throughout the dance, the children's outfits, consisting of green shirts and khaki shorts, stand out against the lush greenery of the meadow, creating a vibrant and engaging visual experience.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves of the children in the video are not continuous, with abrupt changes."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.