video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1993
|
videos/HRA_part2/1993.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Caspian tern, the largest species, soars over a coastal landscape, its gray and white plumage gleaming under the sun. It has a bright orange-red bill with a black tip, and its wingspan stretches wide as it glides over the water. Perched on a sandy shore, the bird preens its feathers, revealing its distinctive black crest and elegant posture. In flight again, the tern's powerful wings propel it forward, and it banks sharply, showcasing its agility against a backdrop of rolling clouds and shimmering sea. Finally, diving gracefully into the water, it emerges triumphant with a small fish in its beak, demonstrating its hunting prowess in stunning detail.]"
},
{
"from": "gpt",
"value": "Bad. The tern's wings in the video have generation issues, and the eyes were not generated."
}
] |
seed42_2950
|
videos/HRA_part0/2950.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A tiny warbler perches on a thin branch, its vibrant yellow-green plumage contrasting beautifully against the lush green foliage of the forest. The bird, no bigger than a sparrow, displays its distinctive black facial markings and streaks, enhancing its charm. It tilts its head curiously, revealing its sharp, pointed beak, perfectly adapted for probing into bark crevices and catching insects. The warbler then flutters its wings, preparing to leap onto another branch, showcasing its agility and grace in the dappled sunlight filtering through the leaves above.]"
},
{
"from": "gpt",
"value": "Normal. The bird's movements in the video are basically normal, with slight disharmony."
}
] |
seed44_1937
|
videos/HRA_part1/1937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, known for his role in a space-themed reality TV series, gently caresses the smooth, metallic surface of a spacecraft console, his face illuminated by the soft glow of the control panel lights. Dressed in a futuristic silver jumpsuit with black accents, he leans over the controls, his eyes locked onto a screen displaying complex data, conveying a sense of focused intimacy with the technology. The scene is set inside a sleek, modern spaceship cabin, with large windows showing the vastness of space beyond, stars twinkling against the dark cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and arms are slightly twisted."
}
] |
seed42_1784
|
videos/HRA_part0/1784.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male musician, clad in a black leather jacket, a graphic tee, and dark jeans, walks his energetic, medium-sized brown dog in an urban park. The artist wears a baseball cap and sports a beard, presenting a relaxed and down-to-earth demeanor. The dog, on a leash, enthusiastically explores the grassy area, its tail wagging. In another scene, the musician, now with his acoustic guitar slung over his back, continues his leisurely stroll, his dog trotting alongside him. The pair strolls past a stone building, adding to the laid-back vibe of the day.]"
},
{
"from": "gpt",
"value": "Bad. No scene of a musician walking with a wooden guitar on his back, with a dog trotting alongside him; no scene of the dog's wagging tail."
}
] |
seed46_1273
|
videos/HRA_part2/1273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished-looking teacher, wearing a gray blazer over a gray shirt, stands against the backdrop of a Martian sunset, characterized by its dusty, pinkish hue. The teacher is wiping the surface of a scientific instrument, possibly a rover component, with a cloth, highlighting the careful preparation for exploration. The setting showcases the unique beauty of a sunset on Mars, with its characteristic colors and textures, providing a captivating contrast to the familiar figure of the teacher engaged in an unfamiliar task on another planet.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2236
|
videos/HRA_part0/2236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a dingo, wearing swimming goggles and a yellow life vest, playfully swims in a clear, blue pool under a cloudy sky, its joyful demeanor evident. Meanwhile, inside a small wooden cabin nearby, a young male cashier, sporting a red and white striped shirt, attentively handles transactions with a friendly smile, standing behind a counter filled with various snacks and beverages, the cash register visible beside him. The dingo occasionally glances toward the cabin, seemingly curious about the activities of the human cashier, who remains focused on his duties despite the unusual presence of a swimming dingo nearby.]"
},
{
"from": "gpt",
"value": "Bad. The male cashier's face and hands in the video were generated abnormally."
}
] |
seed44_2575
|
videos/HRA_part1/2575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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: [Two young children, a boy and a girl, are energetically shoveling snow in their front yard, surrounded by a wooden fence. The boy wears a brown jacket, gray pants, and a matching hat and mittens, while the girl is dressed in a purple jacket, jeans, and a pink hat and mittens. Both are using small red shovels to clear a path through the fresh, fluffy snow, their faces showing determination and joy. The scene is set against a backdrop of a suburban house, with windows reflecting the bright, sunny day, and a green minivan parked in the driveway, partially covered in snow. The atmosphere is one of cheerful family activity on a crisp, wintry day.]"
},
{
"from": "gpt",
"value": "Normal. The children's faces and hands in the video have generation issues."
}
] |
seed44_1317
|
videos/HRA_part1/1317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-known actor, dressed in a black turtleneck and dark jeans, sits on a lush, green meadow with a large, brown bear. The actor gently caresses the bear's fur, showing a bond between man and beast. The bear, unperturbed by the human presence, leans into the touch, revealing a surprising tenderness. The scene is peaceful, with the verdant landscape and clear blue sky providing a serene backdrop to this unlikely interaction. The actor's calm demeanor and the bear's relaxed stance suggest a mutual trust and understanding in their shared moment of connection.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3053
|
videos/HRA_part0/3053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a blue button-up shirt and khaki pants, kneels on a wooden floor next to a small mouse. The mouse scurries across the floor, its movements quick and agile, as the doctor watches with a mix of curiosity and concern. The scene is set in a brightly lit room with white walls, and the doctor's facial expression conveys a sense of focused attention on the tiny creature's actions.]"
},
{
"from": "gpt",
"value": "Normal. The mouse in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_1670
|
videos/HRA_part2/1670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, lit by neon lights, a diverse group of reality TV contestants from the show 'Mongoose' gather in the communal area. One contestant, a young woman with a purple mohawk, gently caresses a small, robotic mongoose, designed to mimic Earth wildlife. The robot mongoose, covered in metallic fur, responds with affectionate whirrs and beeps. The background features sleek, metallic surfaces and screens displaying space vistas, creating an atmosphere of high-tech comfort. The other contestants, dressed in colorful, futuristic outfits, watch with curiosity and amusement, their expressions a mix of fascination and relaxation.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the small robot's actions are also not fluid."
}
] |
seed44_2493
|
videos/HRA_part1/2493.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, dressed in a yellow jacket over a gray sweater and black pants, is seen on the bustling Shanghai street, wiping a public window with a cloth. The vibrant city life of Shanghai forms the backdrop, with a variety of shops, signs in Chinese, and pedestrians creating a lively atmosphere. The young man is focused on cleaning the window, demonstrating care and responsibility in maintaining the urban environment. Passersby, including a woman in a pink jacket and a man in a gray coat, walk by in the background, adding to the dynamic scene of a busy city day.]"
},
{
"from": "gpt",
"value": "Normal. The action of the person wiping the glass in the video is basically normal, with slight disharmony."
}
] |
seed42_2768
|
videos/HRA_part0/2768.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 face, arms, and hands are distorted in the video."
}
] |
seed44_3045
|
videos/HRA_part1/3045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, exhibiting a gentle demeanor, caresses another smaller chimpanzee with its right hand, both sitting on a brown surface against a green background. The larger chimpanzee, with a caring expression, tenderly strokes the younger one, fostering a sense of intimacy and connection. This heartwarming scene captures the essence of compassion within the primate family, highlighting the nurturing bond between the two creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's hand is a bit deformed."
}
] |
seed42_1535
|
videos/HRA_part0/1535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a red plaid shirt and blue jeans, tenderly bathes a muddy dog outside on a sunny day, using a white hose with a red nozzle. The farmer, with a warm smile and caring hands, rinses the dog with water from the hose, as the playful animal stands on its hind legs, paws resting on the farmer's knee, enjoying the attention. The scene is set against a backdrop of lush green fields and a clear blue sky, with the farmer's weathered barn in the distance, creating a heartwarming rural atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The human hand shows deformities in the fingers, and the pipe is also bent and deformed."
}
] |
seed46_1743
|
videos/HRA_part2/1743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 green parrot with yellow facial feathers and red tail feathers perches on a branch, set against a blurred green background. The bird turns its head to look over its shoulder, displaying its detailed plumage. It then faces forward, revealing its sharp beak and curious expression. Next, it preens itself, using its beak to adjust its feathers, highlighting its self-care behavior. Finally, the parrot opens its wings slightly, showing off more of its stunning colors, all against a consistent blurred green backdrop that keeps the focus on the bird.]"
},
{
"from": "gpt",
"value": "Bad. The parrot's feather preening movements in the video are not smooth and continuous, with abrupt changes in the wings in between frames."
}
] |
seed42_1050
|
videos/HRA_part0/1050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dolphin breaches the surface of a turquoise ocean, its sleek gray body glistening in the sunlight, against a backdrop of a clear blue sky and calm seas. Moments later, it swims gracefully underwater, surrounded by the vibrant marine life of a coral reef, including colorful fish and swaying sea fans. Then, the dolphin leaps again, this time performing a stunning aerial maneuver with the sun illuminating its form from below, highlighting its agility and beauty. Finally, it returns to the depths, swimming alongside a school of shimmering silver fish, the underwater world coming alive around it, showcasing the dolphin's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1395
|
videos/HRA_part2/1395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara sits calmly in a natural setting, surrounded by lush greenery and water in the background. It gently caresses another smaller capybara with its front paws, showing tenderness and care. Both capybaras are positioned against a serene landscape, highlighting the intimate interaction between the two creatures. The larger capybara's nurturing touch towards the smaller one conveys a sense of affection and protection within their social structure.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's movements in the video are not smooth."
}
] |
seed44_2137
|
videos/HRA_part1/2137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a large bird of prey with brown and white feathers, soars over a placid lake, its piercing yellow eyes scanning the water below. It then swoops down with remarkable agility, its talons outstretched, aiming for a fish just below the surface. Catching its prey, it rises back into the air, now carrying a silver fish clasped firmly in its claws, the water still rippling from the osprey's dive. Against a clear blue sky, the osprey flies away, its powerful wings beating steadily, the captured fish glinting in the sunlight, illustrating the bird's hunting prowess over the serene lake landscape.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the osprey's wings and claws in the video has issues."
}
] |
seed44_1496
|
videos/HRA_part1/1496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned farmer, wearing a brown shirt and denim overalls, drives a futuristic lunar buggy across a vast, barren moon landscape, dotted with craters and boulders under a starlit sky. Suddenly, the scene transitions to a serene, earthbound setting where the same farmer is seen leisurely floating on an inflatable raft, fully clothed, in the middle of a tranquil, crystal-clear lake surrounded by lush greenery. The peaceful atmosphere is punctuated by the occasional splash as the farmer gently moves through the water, enjoying a refreshing break from his daily chores.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1036
|
videos/HRA_part0/1036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 single crow perches on a thin branch, set against a vivid orange sunset, its silhouette stark and striking. The bird has ruffled feathers, indicating a recent bout of activity, and it looks directly at the camera with one intense eye. Its beak is slightly open, as if about to call out into the dusky sky, which is ablaze with fiery hues of red and gold, casting a warm glow on the crow's form. The branch it rests on is delicate, barely able to support its weight, adding a sense of precarious balance to the scene. Behind the crow, the last rays of sunlight filter through the gaps in the bare tree branches, creating a dramatic interplay of light and shadow.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3187
|
videos/HRA_part0/3187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with dark hair tied back in a bun, wearing a vibrant floral-printed dress, is seen standing on a dock by a small wooden boat. In the next shot, she is swimming underwater in clear blue water, her dress floating around her, while an elephant, also submerged, swims beside her with its trunk held high above the water's surface. The pair gracefully navigate the aquatic environment together, the woman's dress and the elephant's trunk swaying gently in the water, creating a serene and harmonious scene. The woman's peaceful expression and the elephant's calm demeanor suggest a strong bond between them as they share this underwater experience.]"
},
{
"from": "gpt",
"value": "Bad. The woman's body and limbs are missing parts, her face is incompletely generated, the elephant's limbs are incomplete, and there are issues with the nose generation."
}
] |
seed42_2742
|
videos/HRA_part0/2742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, temperate rainforest, a janitor, dressed in a yellow vest and dark green pants, leaps over a fallen log with surprising agility. Surrounded by towering trees and dense foliage, he lands gracefully on the mossy ground, his movements deft and sure. As he continues his unlikely journey, bounding from one natural obstacle to another, the vibrant greens of the forest serve as a striking contrast to his utilitarian attire. Throughout this unexpected scene, the janitor's expression is one of focused determination, his form mid-jump captured against the backdrop of the rainforest's rich biodiversity.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_208
|
videos/HRA_part2/208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully detailed brown trout swims gracefully in a clear, bubbling stream, its speckled skin shimmering beneath the water's surface. The trout's intricate pattern of spots and slashes is vivid against the backdrop of smooth river stones and aquatic plants. Sunlight filters through the water, highlighting the fish's movements as it navigates the current with effortless ease, a true testament to its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2535
|
videos/HRA_part1/2535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, temperate shrubland landscape, a chef wearing a classic white uniform and toque walks alongside a majestic, dark-furred wolf. Both figures are set against a backdrop of dense, lush vegetation, with the chef holding a large, brown paper bag presumably filled with ingredients. The pair continues their journey, moving purposefully through the shrubland, the chef's attire standing out against the rich greenery and the wolf's fur blending seamlessly into the natural surroundings. The scene conveys a sense of adventure and companionship between the chef and the wolf as they explore the wild terrain together.]"
},
{
"from": "gpt",
"value": "Bad. The wolf and the chef's walking in the video is very unsmooth, and their movements are uncoordinated."
}
] |
seed44_2907
|
videos/HRA_part1/2907.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male baker with short brown hair and glasses, wearing a brown apron over a white shirt, expertly folds ingredients together in a large stainless steel bowl using a wooden spoon. The kitchen is modern and minimalist, featuring sleek silver appliances and countertops. He then spreads batter evenly into a round cake pan, which he places into a preheated oven. As he waits, he wipes his hands on his apron and checks the temperature with a digital thermometer, ensuring the perfect bake. Finally, he removes the golden-brown cake from the oven, its surface smooth and evenly risen, ready for decoration.]"
},
{
"from": "gpt",
"value": "Normal. The male baker's fingers in the video are deformed."
}
] |
seed44_1387
|
videos/HRA_part1/1387.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt and black vest, finds himself dancing amidst towering trees in a dense forest. As he gracefully twirls, a majestic bison watches from the shadows, its powerful presence adding a touch of wildness to the surreal encounter. The forest, filled with lush greenery and dappled sunlight, provides a natural stage for this unexpected dance performance, where the lines between human and nature blur in a harmonious display.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1963
|
videos/HRA_part2/1963.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, impeccably dressed in a black suit, white shirt, and black tie, stands against a blurred restaurant background. He holds a cocktail shaker in both hands, vigorously shaking it to mix a drink. His eyes are focused on the task, and beads of condensation form on the metal shaker. The action takes place in a dimly lit, upscale bar setting, with the shaker's metallic surface reflecting the ambient light. Throughout the scene, the waiter maintains his professional demeanor, his crisp attire contrasting with the dynamic motion of his hands as he expertly prepares a beverage.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1046
|
videos/HRA_part1/1046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A diligent worker, clad in a high-visibility yellow vest, blue jeans, and a brown jacket, methodically rakes a large pile of autumn leaves into a meticulously organized heap. The scene is set in a spacious backyard, bordered by a wooden fence, with additional piles of leaves scattered throughout the yard, indicating a day of hard work. The worker's focus is intense, his movements efficient, as he tackles the task with determination, the vibrant colors of the fallen foliage contrasting beautifully against the green grass.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2363
|
videos/HRA_part2/2363.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 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 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 little girl's movements are not smooth."
}
] |
seed46_2352
|
videos/HRA_part2/2352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, lush green savanna under a bright, sunny sky, a majestic Bengal tiger runs swiftly across the open grassland, its powerful muscles rippling beneath its vibrant orange coat, marked with distinctive black stripes. The tiger's piercing yellow eyes are focused ahead, conveying determination and grace in motion. The scene is framed by distant gallery-like structures, housing various wildlife exhibits, which add a unique architectural element to the natural setting. The tiger's fluid movements and the contrast between the untamed wilderness and the man-made galleries create a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The movements are slightly unsmooth."
}
] |
seed44_2326
|
videos/HRA_part1/2326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen laboratory, a distinguished chef wearing a pristine white chef's jacket and black trousers walks purposefully toward a high-tech, glass-enclosed antimatter containment unit, which emits a soft, eerie glow. The chef's attire is impeccably clean, contrasting with the advanced technology surrounding him. He carries a small, sleek device in his right hand, possibly a tool for interacting with the antimatter. The room is filled with stainless steel counters and equipment, giving it a modern, industrial feel. The chef approaches the containment unit with determination, ready to harness the unique properties of antimatter for an extraordinary culinary creation.]"
},
{
"from": "gpt",
"value": "Normal. The man's body in the video is only half generated, and there are missing fingers."
}
] |
seed42_2988
|
videos/HRA_part0/2988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a slender gazelle, elegantly attired in a black apron and cap, diligently wipes down a wooden countertop with a green cloth. The setting is a quaint, rustic grocery store, filled with shelves of produce and goods. The gazelle, with its distinctive horns and graceful demeanor, performs the task with meticulous care, embodying an unexpected yet captivating scenario behind the register.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's head and forelimbs in the video have generation issues."
}
] |
seed46_1241
|
videos/HRA_part2/1241.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, brown vole wearing a miniature top hat and a tiny pair of spectacles stands on its hind legs atop a wooden stage, backdropped by a dark, starlit night. It begins to dance, performing a series of charming, unexpected moves that captivate the viewer. The vole's expressive face shows pure joy as it twirls and leaps, its tiny body moving gracefully to an unheard melody. Occasionally, the vole pauses, looking directly into the camera with a mischievous glint in its eye, before continuing its delightful solo performance under the twinkling stars.]"
},
{
"from": "gpt",
"value": "Normal. The vole's movements are unsmooth."
}
] |
seed44_2323
|
videos/HRA_part1/2323.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, identifiable by his gray lab coat over a casual button-up shirt and jeans, gently bathes a small, fluffy white dog in an elevated washbasin typically used for washing cars. The scene is set outdoors, with the dog standing on its hind legs, paws on the basin's edge, and the engineer tenderly pouring water over its head from a white jug. The engineer's caring demeanor contrasts with his professional attire, creating a heartwarming image of an unexpected task being performed with love and care.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1089
|
videos/HRA_part0/1089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum hall, a life-sized jaguar statue leaps across the space, seemingly frozen in mid-air as it jumps from one side to the other. The museum is filled with exhibits of historical artifacts, including ancient pottery and weaponry displayed in glass cases along the walls. The jaguar, crafted with intricate details and positioned mid-jump, captures the animal's agility and power, making it the focal point of the room. Its leap is so vividly portrayed that it appears ready to pounce at any moment, adding a dynamic element to the otherwise static environment.]"
},
{
"from": "gpt",
"value": "Normal. Almost static."
}
] |
seed44_3025
|
videos/HRA_part1/3025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray turtleneck, paints a large canvas featuring a moose in outer space, depicted in vibrant colors and abstract style. The scene shows the artist wiping paint from their hands while gazing thoughtfully at the artwork, which portrays the moose as a diplomat in a cosmic setting, surrounded by stars and planets. The artist's attire, including black pants and shoes, contrasts with the colorful painting, emphasizing the creative process and the unique concept of a moose on a space diplomatic mission.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hand and arm are twisted in the video."
}
] |
seed46_2024
|
videos/HRA_part2/2024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, bespectacled female student sits cross-legged on a clean, white surface, diligently hemming a pair of black pants with a focused expression. She wears a grey cardigan over a white collared shirt and blue jeans, her attire casual yet neat. The environment is bright and minimalistic, with ample natural light illuminating her task. Tools of her activity, such as scissors, thread, and a needle, are neatly arranged within reach, highlighting her attention to detail and organization. The scene captures her absorbed in the sewing process, her hands skillfully manipulating the fabric, demonstrating a blend of practical skill and academic studiousness.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers and legs are missing in the video, the scissors and thread tools are deformed, and the woman's glasses cannot be seen."
}
] |
seed46_1044
|
videos/HRA_part2/1044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, a middle-aged janitor, wearing a yellow high-visibility vest over a dark jacket and a gray cap, gently caresses a kangaroo. The animal, with its distinctive marsupial pouch, is calm and accepting of the man's affection. The setting is a nondescript indoor location with concrete floors and walls, typical of a warehouse or large garage, with various tools and equipment scattered about. The interaction between the unlikely pair is tender and peaceful, capturing a unique moment of interspecies connection.]"
},
{
"from": "gpt",
"value": "Normal. The kangaroo's head, the man's face, and hands are generated poorly in the video."
}
] |
seed44_2877
|
videos/HRA_part1/2877.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a black leather jacket, gray jeans, and a black beret, stands on a lush green hillside under a clear blue sky, engaging in an eccentric dance. In the foreground, a majestic leopard, its golden eyes locked on the director, prowls among the tall grass, adding a sense of wild energy to the scene. The director's animated movements contrast with the leopard's watchful stillness, creating a captivating interplay between human creativity and untamed nature.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video, as well as the leopard's face."
}
] |
seed46_1301
|
videos/HRA_part2/1301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 group of four young children, two boys and two girls, are joyfully splashing in a clear blue swimming pool, their laughter echoing in the bright, sunny day. One boy, wearing green swim trunks, playfully jumps into the water from the side of the pool, creating a splash. Meanwhile, a small, curious brown mouse peers over the edge of the pool, its tiny head poking out, seemingly intrigued by the commotion and the splashing water. The children, unaware of the mouse's presence, continue to swim and play, their faces full of delight and energy, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video, and the mouse is also distorted."
}
] |
seed46_1715
|
videos/HRA_part2/1715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful woman stands tall, embracing the sunlight that cascades upon her, highlighting her radiant smile and the vibrant colors of her floral maxi dress. She is positioned on a wooden deck, overlooking a serene lake surrounded by lush greenery, with the distant silhouette of majestic mountains providing a breathtaking backdrop. Her curly brown hair, adorned with a delicate headband, gently sways in the breeze, while her closed eyes suggest a moment of peaceful contemplation. She holds a small bunch of wildflowers in her right hand, adding a touch of nature's beauty to the scene. The warm glow of the sun, combined with the natural splendor of her surroundings, creates a harmonious atmosphere that encapsulates the essence of tranquility and connection with the outdoors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_247
|
videos/HRA_part0/247.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, scuttles along a sandy shore. Its intricate, spiraled shell provides a stark contrast against the muted tones of the beach. The crab's two large, front claws grasp onto the shell's edge as it moves, showcasing its unique adaptation for survival. The sandy background is dotted with small rocks and bits of seaweed, adding texture to the scene. The sky above is a clear, vivid blue, highlighting the rich colors of the hermit crab as it navigates its coastal habitat.]"
},
{
"from": "gpt",
"value": "Normal. The hermit crab's movements in the video are slightly unsmooth."
}
] |
seed42_1251
|
videos/HRA_part0/1251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, multicolored parrot perches on a branch, its plumage a stunning array of green, blue, red, and yellow feathers. The bird's intelligent eyes, surrounded by a ring of bare skin, fixate on something beyond the frame. Its curved beak opens slightly, revealing a hint of a loud, echoing call that fills the dense jungle canopy overhead. The parrot's powerful, curved claws grip the branch tightly, showcasing its natural agility and strength in the lush, tropical environment. Moments later, it takes flight, its wings beating against the air with a whooshing sound, as it soars through the dappled sunlight filtering through the leaves above.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1333
|
videos/HRA_part2/1333.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lively brown and white dog bounds through the shallow waters of a serene lake at sunset, its fur glistening with droplets. It shakes vigorously, sending water flying in a sparkling mist, while standing on the sandy shore. Against the backdrop of a tranquil lake and a stunning sunset, the energetic canine leaps into the air, capturing the essence of joy and freedom. As it lands, it shakes again, creating a captivating spray against the golden hour light, highlighting every droplet in the air. Throughout, the dog wears a red collar, adding a pop of color against the natural hues of the landscape.]"
},
{
"from": "gpt",
"value": "Normal. The dog's limbs and ears are missing in the video."
}
] |
seed46_2468
|
videos/HRA_part2/2468.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a futuristic silver spacesuit with illuminated details, traverses the rocky, mineral-rich terrain of an asteroid under the faint light of distant stars. Carrying a high-tech pickaxe over his shoulder, he pauses to survey the alien landscape, showcasing determination and resilience in the harsh environment. As he walks, the textured surface of the asteroid and the tools strapped to his suit are clearly visible, emphasizing the challenging conditions of space mining. In the background, the vastness of space and the silhouette of a mining facility or spacecraft provide context to his solitary mission.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2085
|
videos/HRA_part0/2085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, donning a brown coat, scurries across a lush, green meadow under a partly cloudy sky. It dashes over the grass with its front paws lifted, revealing a clear view of its full body. Moments later, it continues its run, tail held high, near a wooden fence. The scene shifts to the beaver running alongside a tranquil stream, with trees in the background, showcasing its natural habitat. Lastly, it sprints with determination, its distinctive flat tail visible as it moves through its verdant environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_256
|
videos/HRA_part1/256.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of an ibis's head, featuring its distinct red facial skin and long, curved bill, contrasted against a dark background. The bird's textured feathers, detailed facial features, and piercing eyes are captured in high definition. The ibis is shown from various angles, highlighting its unique physical attributes, including its sharp, curved beak and distinctive eye markings. Throughout the footage, the ibis's head remains the central focus, with the dark backdrop emphasizing its striking appearance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1338
|
videos/HRA_part2/1338.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A diligent window cleaner, equipped with a squeegee and a bucket of soapy water, stands on a ladder propped against a tall, glass-paneled building. Dressed in a yellow high-visibility vest and dark pants, he methodically wipes the glass, leaving a streak-free shine. The bustling cityscape forms the backdrop, with pedestrians passing by and cars moving on the streets below. The sun casts a golden glow on the scene, highlighting the cleaner's hard work as he moves from pane to pane, ensuring crystal clarity for the occupants inside.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, and the hand is distorted."
}
] |
seed44_2506
|
videos/HRA_part1/2506.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an imaginative scene, a lone camel, adorned with vibrant red and yellow fabrics, stands gracefully at the edge of a bustling highway under a vivid orange sunset. Vehicles whiz by in the background, forming streaks of light against the twilight sky. The camel begins to sway and dance, moving its body to an unheard rhythm, creating a surreal contrast between the wild and the urban landscape. Its movements are fluid and expressive, drawing attention despite the chaos of the surrounding traffic. The highway lights and car headlights illuminate the scene, casting dramatic shadows as the camel continues its dance, a captivating spectacle where nature meets the modern world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2207
|
videos/HRA_part2/2207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skillful musician, clad in a black beret, black jacket, and blue jeans, sits on a wooden bench amidst lush vineyards, playing a vintage guitar with focused intensity. Nearby, a curious squirrel crawls along a vineyard post, its bushy tail swaying as it observes the musical performance from a safe distance. The rolling hills and rows of grapevines provide a picturesque backdrop, with the musician's passionate playing and the squirrel's attentive stance creating a harmonious scene in nature.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers and guitar in the video are not fully generated, the face is deformed, and the squirrel's body is not generated."
}
] |
seed46_1249
|
videos/HRA_part2/1249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 depiction begins with a painter wearing a white apron, standing before a large canvas in a spacious studio filled with art supplies, painting a panda in vibrant colors. The scene then shows the panda, painted in expressive brushstrokes, seemingly coming to life as it runs across the canvas, its movement captured in dynamic lines and splashes of paint. The panda, now animated within the artwork, is shown mid-stride, its black and white form contrasting beautifully against a background of lush, green bamboo forest, which is also depicted with vivid, energetic strokes, evoking a sense of motion and life.]"
},
{
"from": "gpt",
"value": "Normal. The painter appears deformed, and the panda also undergoes deformities and mutations."
}
] |
seed42_2557
|
videos/HRA_part0/2557.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, two figures, a man and a woman, both wearing sophisticated, form-fitting silver spacesuits with intricate blue detailing, walk purposefully down a sleek corridor lit by soft, ambient blue light. They carry themselves with the poise and dignity of diplomats, their movements deliberate and confident. The man sports a neatly trimmed beard and short, dark hair, while the woman wears her long, curly hair in a high bun, adorned with small, sparkling silver clips. Both wear expressions of intense concentration, reflecting the gravity of their mission among the stars. Behind them, the corridor stretches into darkness, hinting at the vastness of space and the unknown adventures awaiting them.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1593
|
videos/HRA_part0/1593.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray shirt and blue jeans stands on a green ladder, cleaning out debris from the clogged gutters of a two-story house with a red roof, set against a clear blue sky. His focus is intense as he uses a small garden trowel to scoop out leaves and dirt. The house facade, painted in a warm beige hue, contrasts with the lush greenery surrounding it. A pile of removed debris sits on the ground beneath him, indicating progress in his task. His gray shirt and blue jeans are slightly soiled from the work, highlighting the effort and dedication put into maintaining the home's exterior.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2780
|
videos/HRA_part1/2780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, portraying a member of a nanobot repair crew, leaps dramatically across a futuristic, metallic platform. Dressed in a silver jumpsuit, complete with utility belts and pouches, he soars through the air with intense focus. His movements are agile and purposeful, suggesting urgency in his mission. As he lands, ready to tackle the next task, the background features complex machinery and glowing panels, immersing the viewer in a high-tech, sci-fi environment.]"
},
{
"from": "gpt",
"value": "Bad. The actor's movements in the video are not smooth."
}
] |
seed46_1007
|
videos/HRA_part2/1007.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": "Normal. The cat's movements in the video are basically normal, with slight disharmony."
}
] |
seed42_2763
|
videos/HRA_part0/2763.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 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 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": "Normal. The monkey's swimming in the video is basically normal, but there are slight coordination issues."
}
] |
seed46_3192
|
videos/HRA_part2/3192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space-themed sports arena, a young female cashier, wearing a white apron over her outfit, diligently wipes down the countertop with a cloth. The background is vibrant, featuring neon lights and digital screens displaying scores from ongoing cosmic games. The cashier's actions are methodical, her focus intense, as she ensures the counter is spotless for the next customer in this bustling, intergalactic sports hub. Behind her, patrons in diverse alien attire wait patiently, adding to the dynamic atmosphere of this extraterrestrial venue.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the female cashier wiping the counter with a cloth, her actions are basically normal but there is some lack of coordination."
}
] |
seed44_2670
|
videos/HRA_part1/2670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, sits on a wooden crate under a bright blue sky, with scaffolding and building materials in the background. He gently pets a brown and white dog lying on its back, belly-up, on a pile of gravel, showing a tender moment of connection between the worker and the animal. The worker's hands, rough from labor, contrast with the softness of the dog's fur, creating a touching scene of companionship amidst a rugged worksite.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1022
|
videos/HRA_part1/1022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, cheerful female nurse walks briskly down a hospital corridor, her blonde hair tied back in a neat bun. She wears a sky-blue uniform, gray tights, and white shoes. A stethoscope hangs around her neck, and she carries a clipboard in her right hand. The hallway is brightly lit, with a green floor and doors lining either side. The nurse's confident stride and professional attire convey a sense of purpose and dedication to her duties within the healthcare facility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3006
|
videos/HRA_part2/3006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green environment, a small brown mouse stands on the edge of a natural pool, surrounded by dense shrubbery and tall grass, creating an intricate network of thickets. The mouse looks intently at the water, its ears perked and body alert. Suddenly, it bravely leaps into the clear, shimmering pool, swimming with surprising agility, its tiny paws propelling it through the water. As it swims, the camera captures the ripples created by its movement, highlighting the contrast between the busy activity of the mouse and the stillness of the thickets surrounding the pool.]"
},
{
"from": "gpt",
"value": "Normal. The mouse's movements in the video are not smooth."
}
] |
seed42_177
|
videos/HRA_part0/177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated bill and streamlined body, gracefully glides through the clear, turquoise waters of the open ocean. Its striking appearance is enhanced by the vivid marine environment surrounding it, featuring vibrant coral reefs and schools of smaller fish scattering in its path. The powerful creature showcases its agility and strength as it navigates the depths, with rays of sunlight filtering through the water to illuminate its journey. Against this stunning underwater backdrop, the swordfish emerges as a true marvel of the deep sea, embodying the beauty and mystery of life beneath the waves.]"
},
{
"from": "gpt",
"value": "Bad. The swordfish generation in the video has issues."
}
] |
seed46_1870
|
videos/HRA_part2/1870.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor wearing a black t-shirt and dark jeans is seen running alongside a large, energetic yellow dog in an expansive park. The two are captured mid-stride, with the actor's focused gaze and the dog's joyful expression highlighting their shared activity. They run together in harmony, the actor's casual attire and the dog's bounding energy creating a dynamic and engaging scene against the lush greenery of the park.]"
},
{
"from": "gpt",
"value": "Normal. The arms, hands, face, legs of the person in the video are twisted, as well as the dog's legs and face."
}
] |
seed42_1622
|
videos/HRA_part0/1622.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stark contrast of concepts, the scene begins with a majestic buffalo standing solitary in a vast, arid savanna under a clear blue sky, the landscape stretching out to distant mountains. Suddenly, the focus shifts to a cosmic illustration of a black hole, its singularity depicted as a swirling vortex of stars and galaxies being pulled into the abyss, emphasizing the immense gravitational pull. The scene then transitions to a visual metaphor of 'wiping,' showing a clean slate or a blank page, symbolizing the erasure or resetting of information, akin to the theoretical concept of information loss in a black hole scenario. Throughout, the buffalo, the black hole, and the wiping action are portrayed sequentially rather than interacting, due to the inherent incompatibility of these elements in a physical sense.]"
},
{
"from": "gpt",
"value": "Bad. No scene of a buffalo standing on the vast and arid grassland was generated."
}
] |
seed46_1265
|
videos/HRA_part2/1265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant coral reef ecosystem teeming with life, a curious butterfly fish, marked by its distinctive black band passing through the eye and vibrant yellow and white coloration, explores its surroundings. It gracefully maneuvers among the intricate coral structures, highlighting the beauty and diversity of the underwater world. The fish interacts with the coral, appearing to almost kiss it, showcasing its feeding behavior. As it swims, the camera captures its elegant movements against the backdrop of the colorful reef, including a glimpse of a sea anemone. Throughout the scene, the butterfly fish remains the focal point, its striking appearance standing out against the rich marine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2768
|
videos/HRA_part0/2768.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling airport terminal 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 movements in the video are not smooth."
}
] |
seed46_2332
|
videos/HRA_part2/2332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with dark brown hair tied in a ponytail and wearing a gray T-shirt, blue jeans, and green gardening gloves is intently digging into the soil with a silver garden shovel. The scene is set in a backyard garden with lush greenery surrounding her, and a wooden fence can be seen in the background. She pauses for a moment to brush away some dirt from her face, revealing a look of determination and focus. As she continues to dig, the sunlight filters through the leaves overhead, casting dappled shadows onto the ground and highlighting her efforts in the garden.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1844
|
videos/HRA_part1/1844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a friendly-looking cashier, wearing a red apron with a name tag, works behind a counter at an airport gift shop. Unexpectedly, a small, playful ferret emerges from the pocket of the cashier's apron, peeking its head out curiously. The background features a bustling airport terminal with passengers and luggage, emphasizing the unusual combination of elements. Moments later, the focus shifts to a clear swimming pool, where the same cashier, now in swimwear, happily swims with the ferret floating nearby on a small inflatable raft, both enjoying a break from the busy airport environment.]"
},
{
"from": "gpt",
"value": "Normal. In the airport terminal gift shop scene of the video, the ferret's paws were generated incorrectly; in the swimming pool scene, the ferret was not generated at all, and there were issues with the generation of the cashier's face and hands."
}
] |
seed46_1469
|
videos/HRA_part2/1469.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow high-visibility jacket, blue jeans, and brown work boots, walks purposefully near a yellow Bobcat excavator, which is positioned on a building site filled with sand and dirt. The excavator boasts a wide bucket and sits on the sandy terrain of the lot, while the worker strides with determination, hard hat in hand, past the heavy machinery, embodying the industrious spirit of a bustling worksite.]"
},
{
"from": "gpt",
"value": "Normal. The character's head is distorted, the arms are twisted, and the legs are contorted."
}
] |
seed46_2012
|
videos/HRA_part2/2012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman, presumably a writer, sits at a grand dining table, meticulously polishing silverware with a white cloth. He wears a dark blue blazer, a button-down shirt, and glasses, presenting a scholarly appearance. The room is dimly lit, with the only bright spot being the gleam from the silver as he works. The setting suggests a large, elegant dining hall, possibly in an old mansion, where the writer has taken on the unexpected task of preparing the cutlery. His focus and precision convey a sense of dedication to the task, contrasting with his intellectual pursuits.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1928
|
videos/HRA_part2/1928.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."
}
] |
seed44_1238
|
videos/HRA_part1/1238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a European starling perched on a branch, its vibrant plumage shimmering with hues of green and purple under the sunlight. The bird's beady eye is fixed ahead, and its feathers appear ruffled, as if enjoying a gentle breeze. The starling's curved bill and round body are distinct against the blurred green foliage in the background, creating a contrast that highlights the bird's intricate details. The scene is set in a serene forest environment, where the starling seems unperturbed by the camera, offering a rare glimpse into its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_201
|
videos/HRA_part2/201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black panther is filmed in high definition, gently caressing a log with its paw in a lush, green rainforest. The panther, with piercing yellow eyes, rests its massive head on the log, showcasing its strength and grace. It then proceeds to rub its cheek against the log, marking its territory, while the camera captures every detail of its luxurious fur and the intricate textures of the forest environment. The scene is set in a dense jungle, with sunlight filtering through the canopy, highlighting the panther's sleek silhouette and the vibrant foliage surrounding it.]"
},
{
"from": "gpt",
"value": "Normal. The black panther's movements in the video are basically normal, with slight inconsistency."
}
] |
seed46_1041
|
videos/HRA_part2/1041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young boys, one wearing a yellow shirt and the other in red, energetically scrub the bathroom floor with sponges, creating soapy lather. They are focused on their task, with one boy on his hands and knees, working diligently, and the other standing, intently cleaning the wall tiles. The room is filled with the soft sound of water and the energetic movements of the children, who seem to find joy in the chore, transforming the mundane task into a playful activity. Their faces are expressions of determination and delight, turning the bathroom into a space of unexpected fun and teamwork.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2921
|
videos/HRA_part0/2921.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet harmonious scene, a veterinarian, dressed in a khaki safari outfit, carefully tends to a young rhinoceros in a spacious, fenced enclosure, with lush greenery visible in the background. The compassionate doctor gently examines the rhino, which is lying on a sandy surface, seemingly at ease. The rhinoceros, displaying signs of improvement, attempts to crawl forward on its front legs, indicating a recovery from a recent ailment or procedure, all under the watchful eye of the dedicated wildlife doctor.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2011
|
videos/HRA_part0/2011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sandy desert under a clear blue sky, a lone camel, distinguished by a single hump, leaps gracefully into the air. Its action is captured mid-jump, with all four feet off the ground, showcasing its unique ability to navigate the dunes. The camel's tan fur contrasts beautifully with the blue sky and golden sand, highlighting its natural habitat. As it springs forward, the surrounding landscape of dunes and distant mountains provides a stunning backdrop, emphasizing the creature's agility and the serenity of its environment.]"
},
{
"from": "gpt",
"value": "Bad. The camel's legs show deformities, and the tail is also deformed."
}
] |
seed44_2501
|
videos/HRA_part1/2501.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit cave, a police officer, wearing a uniform with a badge and a utility belt equipped with various tools, including a flashlight, gently caresses the rough stone wall, seemingly searching for hidden clues or evidence. The cave's textured walls, illuminated by the officer's flashlight, provide a dramatic backdrop for this intense moment of investigation. The officer's focused gaze and careful touch convey a sense of determination and meticulousness in uncovering secrets within the cave's depths.]"
},
{
"from": "gpt",
"value": "Good. The video clearly shows the officer touching the stone wall, and the action is basically normal."
}
] |
seed46_1562
|
videos/HRA_part2/1562.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An innovative engineer, clad in a spacesuit and helmet, walks through a futuristic space station, where advanced agricultural technology is used to cultivate crops in zero gravity. Accompanied by a friendly fox, who curiously observes the floating plants and high-tech equipment, the engineer tends to the verdant greenery, demonstrating the feasibility of farming in outer space. The pair moves through the well-lit, sterile environment, highlighting the potential for sustainable food production beyond Earth's atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. Two engineers were generated."
}
] |
seed44_2292
|
videos/HRA_part1/2292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest and hard hat, finds himself in an unexpected scenario as he runs alongside a monkey, both moving rapidly across a cluttered urban environment. The worker, with a rugged appearance and a backpack, navigates through a cityscape filled with scaffolding and construction materials. Meanwhile, the monkey, displaying a mischievous yet determined demeanor, keeps pace, highlighting an unusual companionship between human and primate in a bustling urban setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1110
|
videos/HRA_part0/1110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a crisp white shirt and black vest, sprints across a vast, barren lunar landscape, the iconic first steps of Neil Armstrong visible in the distance. Dust from the moon's surface billows behind him as he races, his movements fluid and effortless in the low gravity environment. A lunar module sits in the background, a stark contrast to the elegant attire of the sprinting waiter, who carries a silver serving tray in one hand, merging the worlds of fine dining and space exploration in a surreal scene.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated and discontinuous."
}
] |
seed42_2269
|
videos/HRA_part0/2269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, smiling cashier, wearing a brown apron over a gray shirt and black pants, meticulously dusts antique wooden furniture inside a vintage shop, highlighted by warm, golden sunlight streaming through the windows. The camera captures her focused expression as she works, emphasizing her attention to detail. Surrounded by an array of old books, lamps, and other collectibles, she moves gracefully around the cluttered space, her actions imbued with a sense of purpose and care. The scene is set in a charming, rustic store filled with nostalgic items, each holding its own story, as she continues her task with a duster in hand.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, and face of the person in the video are distorted."
}
] |
seed44_2227
|
videos/HRA_part1/2227.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with a charming smile, wearing a casual graphic T-shirt and dark jeans, is laughing joyously. Her laughter is contagious as she throws her head back, her wavy brown hair cascading down her shoulders. The scene is set in a cozy living room with wooden floors and a white couch, adding to the warm and intimate atmosphere. Her joyful expression, complete with closed eyes and a wide grin, radiates happiness, making the viewer feel like they're sharing in her delight.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1573
|
videos/HRA_part0/1573.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a helmet, digs vigorously with a shovel in hand, surrounded by charred debris and ash under a smoke-filled sky. The scene is set in the aftermath of a fierce fire, with the firefighter's muscular arm raised high, illustrating the strenuous nature of the task. His face is obscured by a breathing apparatus, emphasizing the hazardous conditions. Nearby, another firefighter, also in full protective clothing, aids in the excavation, both working tirelessly amidst the ruins of a burned-out structure, their actions highlighting the determination and bravery required in their line of duty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2013
|
videos/HRA_part1/2013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, dressed in a yellow safety vest, blue jeans, and brown work boots, stretches his body against the backdrop of a building site at sunrise. His routine begins with him bending forward, touching his toes, and then transitioning into a series of stretches that showcase his physical preparation for the day ahead. Throughout the sequence, his attire remains consistent, and the background features a partially constructed building and other workers in the distance, highlighting the early morning setting at the worksite.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, but there is some lack of coordination."
}
] |
seed46_1473
|
videos/HRA_part2/1473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 bee-eater perches on a branch, its vibrant green feathers contrasting against a clear blue sky, before taking flight against a backdrop of lush greenery and distant mountains. It swoops down gracefully, its long, slender beak aimed at capturing prey. The bird then returns to the branch, where it proudly displays its catch, a honeybee, before consuming it. Throughout the scene, the bee-eater's striking plumage, featuring shades of green, blue, and brown, catches the eye against the serene landscape.]"
},
{
"from": "gpt",
"value": "Bad. The hornet appears deformed and mutated."
}
] |
seed46_1097
|
videos/HRA_part2/1097.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."
}
] |
seed42_2185
|
videos/HRA_part0/2185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an unexpected juxtaposition, a small, fluffy hamster wearing a red life jacket floats in a clear plastic ball filled with water. This unique scene unfolds against the backdrop of an industrial area, complete with factories, smokestacks, and large metal containers. The hamster appears content and relaxed, paddling gently within the ball as it bobs on the water's surface near the edge of a pool. The industrial landscape, featuring tall buildings, cranes, and machinery, provides a striking contrast to the innocent and playful hamster enjoying its unconventional swim.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's limbs were not generated."
}
] |
seed46_2654
|
videos/HRA_part2/2654.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a black jacket, jeans, and a gray shirt, stands on a bustling movie set under bright lights. Holding a megaphone in one hand and gesturing emphatically with the other, he directs actors and crew members with passion and precision. The set is filled with vintage cars from the 1950s, indicating a period drama, while the director's focused gaze and expressive body language convey his dedication to capturing the perfect shot. Surrounded by a diverse cast and crew, he moves with purpose, demonstrating his leadership and vision in the dynamic environment of a film production.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2966
|
videos/HRA_part2/2966.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a gray hoodie and khaki pants, walks alongside a camel in a desert landscape. The sun casts long shadows, highlighting the serene connection between the two. The student, wearing a backpack and a wide-brimmed hat, looks thoughtful as they journey together. The camel, adorned with vibrant red and orange textiles, ambles along gracefully, its large, expressive eyes gazing ahead. Together, they traverse the sandy dunes under a vast, cloudless sky, embodying a sense of adventure and exploration.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1246
|
videos/HRA_part0/1246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 full uniform complete with a hat, rests peacefully on a bench in a quiet, empty city park during the daytime. The serene atmosphere is highlighted by the soft play of sunlight filtering through the trees, casting dappled shadows on the ground. The officer's hat is tilted down, partially obscuring their face, while they lean back against the wooden slats of the bench, their body language conveying a sense of well-deserved rest. Beside them, a water bottle sits on the bench, and in the distance, the peaceful urban landscape is visible, punctuated by the occasional passerby and the gentle sway of tree branches.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2300
|
videos/HRA_part1/2300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic, space-themed setting, a costumed performer dressed as a monkey is seen dancing against a backdrop of asteroid mining operations. The monkey wears a spacesuit with a helmet, moving energetically in zero gravity. Behind it, robots with mechanical arms mine valuable minerals from large asteroids, while spaceships shuttle between them. The scene combines elements of science fiction, entertainment, and industrial activity, all set against the backdrop of outer space. The monkey's playful antics contrast with the serious business of asteroid mining, creating a visually engaging and unexpected juxtaposition.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1611
|
videos/HRA_part1/1611.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus, showcasing its remarkable camouflage abilities, rests on a sandy seabed, its body appearing as a collection of scattered stones and sand patches. It then changes color and texture, mimicking a cluster of sponges and corals, demonstrating its incredible mimicry skills. Next, it displays a pattern resembling seaweed and plant life, swaying gently as if caught in an underwater current. Finally, the octopus morphs into an imitation of a rocky outcrop, complete with algae and barnacles, further highlighting its extraordinary ability to blend into various marine environments.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_124
|
videos/HRA_part0/124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with glasses and a neat beard sits at a wooden desk, intensely pushing letters on a vintage typewriter, surrounded by piles of books and papers. The room is dimly lit by a standing lamp, casting shadows that emphasize his focused expression. Wearing a green military-style jacket, he leans forward, completely absorbed in his work, as if battling to translate his thoughts into words. The cluttered environment reflects his creative process, with the typewriter positioned center-stage, highlighting the act of writing as both a physical and mental endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_1782
|
videos/HRA_part1/1782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray, majestic and graceful, glides through crystal-clear waters, its body a stunning contrast of black and white. It somersaults effortlessly, performing acrobatic feats just beneath the ocean's surface, with sunlight filtering through and illuminating the scene. Schools of small fish scatter as the ray passes, highlighting the vastness of its wingspan. The ray then swims upward towards the sunlit water, creating mesmerizing patterns with its movements, before disappearing into the depths, leaving a trail of bubbles in its wake.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1413
|
videos/HRA_part0/1413.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 group of enthusiastic students, clad in casual attire with gardening gloves and hats, gather around a lush, green community garden. They engage in various gardening activities, such as planting seedlings, watering plants, and weeding the soil, under the guidance of an adult supervisor. The scene is set against a backdrop of clear blue skies and the vibrant colors of nature, with the students' joyful expressions and teamwork highlighting the educational and social benefits of outdoor learning.]"
},
{
"from": "gpt",
"value": "Bad. Some objects suddenly appear or disappear in the middle frames of the video, and there are issues with the generation of students' faces and hands."
}
] |
seed46_1677
|
videos/HRA_part2/1677.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a yellow shirt and denim jeans is organizing a cluttered garage, illuminated by overhead lights. She sorts through items on a wooden table, her hands moving purposefully. Nearby, a brown dog sits attentively, watching her actions. Behind her, shelves filled with various objects and tools line the walls, indicating a space dedicated to storage and projects. The atmosphere is one of industriousness, as she focuses on tidying the space, creating order from chaos.]"
},
{
"from": "gpt",
"value": "Bad. The head and hands of the character in the video are generated with abnormal distortions, and objects suddenly appear in the character's hands in the middle frames."
}
] |
seed42_2628
|
videos/HRA_part0/2628.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an unexpected urban scene, a wild bobcat stands alert near a glassy skyscraper, its reflection visible on the building's facade. Beside it, a sleek swimming pool shimmers under the city lights, invitingly clear and calm. The bobcat, with its distinctive tufted ears and sharp gaze, seems unperturbed by the towering structures, its presence creating a striking contrast against the urban landscape. The pool, framed by the towering skyscrapers, offers a serene oasis, its still waters reflecting the night sky and the surrounding architecture.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_3109
|
videos/HRA_part1/3109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, adorned in a cozy red sweater and glasses, sits at a wooden table in a rustic cabin, illuminated by the warm glow of a lamp. She holds knitting needles and a half-completed green scarf, with a laptop displaying a novel manuscript nearby. The atmosphere is serene, with the occasional sound of knitting needles clicking and the soft clacking of keys as she types. A cup of tea sits beside her, adding to the peaceful scene. Behind her, a large window frames a view of lush greenery, providing a natural backdrop to her creative space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2960
|
videos/HRA_part0/2960.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a blue jacket and jeans, walks purposefully across a vast, otherworldly landscape illuminated by the ethereal glow of a nearby galactic nebula. The scene opens with the student standing in the foreground, looking intently ahead, with the majestic nebula casting a soft, cosmic light over the terrain. As the student strides forward, the camera captures the detail of their journey, highlighting the unique features of the alien landscape. With each step, the student's determination is evident, their silhouette framed against the mesmerizing backdrop of the swirling nebula. The final shot lingers on the student's resolute figure, now further along the path, continuing their solitary trek under the watchful gaze of the celestial wonder above.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1397
|
videos/HRA_part1/1397.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a diverse group of characters gathers in a lush meadow under a clear blue sky. A male musician, dressed in a casual striped shirt, plays a ukulele, seated on a small wooden bench. Nearby, an animated gorilla, also wearing a striped shirt, energetically jumps into the air with excitement. The vibrant green grass and colorful flowers surrounding them add to the playful atmosphere, creating a harmonious blend of music, nature, and unexpected companionship.]"
},
{
"from": "gpt",
"value": "Normal. The gorilla's movements are not smooth."
}
] |
seed42_2822
|
videos/HRA_part0/2822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor stands in a spacious, modern gymnasium, surrounded by basketball hoops. He wears a gray jacket with a yellow reflective strip and a name tag, paired with khaki pants and black shoes. Holding a large, professional camera, he focuses on capturing images of the facility. The scene is illuminated by bright overhead lights, highlighting the clean, well-maintained space. The janitor's posture and attire convey a sense of pride and responsibility in his role, as he ensures the gym remains in pristine condition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.