video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1387
|
videos/HRA_part2/1387.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a 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": "Bad. The waiter undergoes a grotesque mutation. The cow in the background also exhibits a deformity."
}
] |
seed42_134
|
videos/HRA_part0/134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by their beret and smock, kneels on a lush, alien landscape, sketching a capybara. The capybara, depicted in a relaxed posture, is the focal point, sitting amidst Martian flora. The scene is illuminated by the vibrant hues of a Martian sunset, casting an ethereal glow across the terrain. The artist's concentrated expression and the capybara's calm demeanor create a sense of tranquility, enhanced by the distant, rugged Martian mountains and the unique atmospheric conditions of the planet, which contribute to the vivid sunset colors. The artist's tools, including a palette and brushes, are scattered nearby, adding to the creative atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, and the hands are twisted."
}
] |
seed44_3046
|
videos/HRA_part1/3046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 black vest, white shirt, and black pants kneels on all fours, imitating crawling, in a vast, grassy savanna. Nearby, an antelope, startled yet intrigued, observes the unusual sight, standing still amidst the natural landscape, with distant acacia trees framing the horizon. The waiter, maintaining the crawling posture, looks up at the antelope with a mix of curiosity and amusement, creating a surreal juxtaposition between human and wildlife behavior in the serene African wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the antelope turning and the waiter looking up at the antelope, but the actions are not continuous and smooth, and there is a lack of coordination."
}
] |
seed42_2116
|
videos/HRA_part0/2116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, distinguished by his crisp, white button-down shirt and black apron, stands in a modern, minimalist living room with large windows and wooden floors. He is meticulously assembling a piece of furniture, focusing intently on aligning the components. The room is sparsely decorated, featuring a simple gray couch and a few abstract art pieces hanging on the walls. Natural light filters in from the windows, casting a warm glow on the scene as the waiter, now with sleeves rolled up, carefully tightens screws and fits parts together, demonstrating his unexpected handyman skills in a domestic setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand appears deformed and the man's movements undergo a sudden change."
}
] |
seed42_109
|
videos/HRA_part0/109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal, futuristic scene, a police officer, clad in a high-tech, silver uniform with a clear, bubble-like helmet, leaps gracefully over a rocky terrain under the Martian sky. An ibex, a type of wild goat, stands majestically nearby, its silhouette outlined against the alien landscape. The officer's powerful jump is captured mid-air, highlighting the reduced gravity of Mars. The constellations and stars above are vivid and numerous, creating a breathtaking backdrop for this extraordinary moment of stargazing from the red planet.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2295
|
videos/HRA_part2/2295.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, an array of coral formations thrives, illuminated by the dappled sunlight filtering through the clear blue water. A variety of corals, from branching staghorn to massive brain corals, creates a textured landscape. Nearby, a school of tropical fish, featuring yellows, blues, and oranges, swims gracefully among the corals, adding life and movement to the tableau. The water is crystal clear, allowing every detail of the coral and marine life to be visible, making it a stunning display of the beauty found beneath the sea's surface.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1316
|
videos/HRA_part0/1316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a sandy beach, two smiling children, a boy and a girl, gently caress a small green lizard that rests on a patch of dry sand, surrounded by lush vegetation. The boy, wearing a blue t-shirt and blue swimming trunks, and the girl, clad in a pink dress, sit cross-legged as they tenderly pet the lizard. The scene is filled with warmth and sunlight, casting shadows of the children and the lizard onto the sandy ground. Moments later, the lizard scurries away into the foliage, and the children watch it go, their faces a mix of fascination and delight, embodying the innocence and wonder of childhood discovery.]"
},
{
"from": "gpt",
"value": "Normal. The child's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1346
|
videos/HRA_part2/1346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman with a glowing face, adorned in a dazzling silver spacesuit, performs at a cosmic concert under the celestial dome of twinkling stars. She begins her act crawling across a zero-gravity stage, her movements graceful and fluid in the absence of Earth's pull. The backdrop is a breathtaking galaxy panorama, with nebulae and planets adding a surreal touch to the spectacle. The atmosphere is charged with anticipation and excitement as she interacts with the floating audience, creating an unforgettable experience in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the face is distorted, and the legs are deformed."
}
] |
seed42_1103
|
videos/HRA_part0/1103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space reality TV show set against a metallic spaceship interior, a muscular firefighter wearing a red swim cap, goggles, and a black swimsuit floats weightlessly in zero gravity. He performs swimming strokes in mid-air, surrounded by floating water droplets, while a diverse group of fellow firefighters observes from a viewing platform. The scene conveys a sense of camaraderie and adventure among the crew members, who are participating in a unique aquatic challenge aboard the spacecraft. The firefighter's robust physique and focused expression highlight his determination and skill, even in the unconventional setting of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's limbs in the video are severely distorted and deformed."
}
] |
seed46_2266
|
videos/HRA_part2/2266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 medical facility, an engineer, wearing a gray shirt with a NASA logo, gently caresses a high-tech medical device, displaying tenderness and care. The room is illuminated by the soft glow of screens and equipment, highlighting the advanced technology surrounding him. Against the backdrop of sleek, metallic surfaces and complex machinery, the engineer's tender gesture toward the device, which resembles a combination of a robotic arm and diagnostic tool, conveys a sense of emotional connection and the importance of human touch even in a highly technical environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed46_1967
|
videos/HRA_part2/1967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 inventive scene unfolds where an engineer, clad in a gray jumpsuit and helmet, meticulously studies blueprints near a full-sized mechanical rhinoceros. Suddenly, the engineer leaps onto the rhino's back as it begins to jump, creating an unexpected yet thrilling spectacle. The mechanical rhinoceros, constructed with intricate metalwork and advanced engineering, bounds across the landscape, while the fearless engineer holds on, embodying a harmonious blend of human ingenuity and mechanical prowess.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and the rhinoceros's legs are also twisted. The body and face are distorted."
}
] |
seed46_1757
|
videos/HRA_part2/1757.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a green tank top and khaki shorts is playfully running in a spacious, grassy area under a clear blue sky, with a koala perched on her back. The koala, clinging to her shoulder, is holding a branch, adding a touch of whimsy to the scene. The woman's joyful expression and the koala's relaxed demeanor create a harmonious and delightful moment, encapsulating the essence of carefree fun and the unexpected companionship between human and animal.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1294
|
videos/HRA_part2/1294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a red jacket and black cap, ascends a rocky cliff face with intense concentration, showcasing determination against a dramatic, cloudy sky. He pauses to rest, surveying the landscape below, revealing a secluded cabin surrounded by dense forest, hinting at his remote writing retreat. Continuing his ascent, he reaches for a sturdy rock hold, highlighting his physical strength and mental fortitude. At the summit, he pauses to write in a small notebook, capturing inspiration from the vast, misty valley below, embodying the adventurous spirit of an author seeking solitude and muse.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2957
|
videos/HRA_part2/2957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret, with a brown and white coat, swims through clear, bubbling water, showing its unique swimming style with its head held high and nose just above the waterline. It uses its webbed feet to propel itself forward, highlighting its natural aquatic abilities. The water droplets glisten around it, and its determined face conveys a sense of joy and playfulness in its unusual swimming endeavor.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1189
|
videos/HRA_part1/1189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit room, two young girls sit on a large, colorful rug, engrossed in crocheting a vibrant patchwork blanket. One girl, with short brown hair, wears a yellow T-shirt and blue jeans, focusing intently on her work. Beside her, a girl with long blonde hair, dressed in a pink dress, stitches away with determination. The room is filled with an array of yarn balls in various colors, scattered around them, and a white wooden table stands nearby, holding a cup of crayons and a half-finished coloring book, hinting at other creative activities. The atmosphere is warm and nurturing, with the girls' concentration and the colorful surroundings creating a scene of creativity and companionship.]"
},
{
"from": "gpt",
"value": "Normal. The little girl's hand is twisted."
}
] |
seed44_2317
|
videos/HRA_part1/2317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting reminiscent of a starship bridge, a young woman with a short bob haircut and bangs, wearing a red uniform, runs with a focused look on her face. She passes by various crew members, who are seated at their stations, as indicated by their presence in the background. The woman's attire matches the aesthetic of the spaceship, which features advanced technology and a sleek design. The action takes place within the command center of the vessel, where the crew operates controls and monitors various screens, highlighting the urgency and importance of the situation at hand.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_2265
|
videos/HRA_part2/2265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mall filled with shoppers, a courageous firefighter clad in full gear, including a helmet and breathing apparatus, runs purposefully down a wide corridor. The vibrant red of his turnout coat contrasts sharply with the gray floor tiles and the bright storefronts. Escalators and elevators stand as silent witnesses to his urgent mission, while the clean, contemporary lines of the mall's architecture provide a stark backdrop to the unfolding drama. Amidst the commercial ambiance, the firefighter's presence and haste underscore the gravity of the situation, his figure growing smaller as he disappears into the distance, leaving behind a trail of determination and heroism.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's hands and feet generation in the video has issues."
}
] |
seed46_2573
|
videos/HRA_part2/2573.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young children, a boy and a girl, sit cross-legged on a wooden deck, surrounded by three small dogs. The boy, wearing a yellow shirt and blue shorts, carefully scoops kibble from a green bowl into his hand, offering it to a white and brown terrier who eagerly licks his palm. Meanwhile, the girl, clad in a pink dress, giggles as she holds out a piece of dog food to a black pug, who sniffs it before gently taking it from her fingers. In the background, a third dog, a golden retriever, patiently waits its turn, sitting attentively near the edge of the deck, as the siblings take turns feeding the pets under the warm glow of afternoon sunlight.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_1115
|
videos/HRA_part0/1115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 fantastical scene, a man wearing a brown fur coat and matching furry boots is seen dancing joyfully next to a massive, ancient mammoth with long, curved tusks. The mammoth stands placidly, observing the man's lively movements. Behind them, a quaint village is visible, featuring a row of charming, colorful houses with thatched roofs. The houses are nestled among lush greenery, creating a picturesque and harmonious setting. The man's animated dancing contrasts with the mammoth's calm presence, while the village in the background adds a touch of warmth and community to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the mammoth in the video is problematic, showing three tusks, and the dancing man has distorted limbs."
}
] |
seed44_3106
|
videos/HRA_part1/3106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded male musician, clad in a brown jacket, blue jeans, and a gray hat, walks through a dense forest filled with tall, lush green trees. He carries a guitar case over his shoulder, suggesting a journey to or from a performance. The woodland environment is rich with ferns and moss, creating a vibrant, natural setting. Sunlight filters through the canopy, casting dappled light on the forest floor as the musician strides purposefully along the path, his attire and equipment blending harmoniously with the woodlands.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3150
|
videos/HRA_part1/3150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, possibly his cub, against the backdrop of a lush, green savanna during golden hour. The adult lion, with its voluminous tawny mane, displays affection, while the cub, sporting a lighter coat and smaller stature, responds with innocent playfulness. The heartwarming interaction unfolds under a vast, cloud-dappled sky, with scattered acacia trees and distant mountains completing the serene African landscape. This intimate moment captures the rare display of tenderness and bonding within the lion family, far from the typical fierce and powerful image associated with these animals.]"
},
{
"from": "gpt",
"value": "Bad. An adult male lion is affectionately caressing a smaller lion when the smaller lion's head shows a deformity."
}
] |
seed44_2020
|
videos/HRA_part1/2020.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, clad in a black shirt, performs energetically on stage under red lights, passionately singing into a microphone. Simultaneously, he wipes sweat from his forehead with his right hand, revealing a wristwatch. Behind him, a drummer in a black sleeveless shirt plays enthusiastically, and a guitarist in a black shirt strums powerfully. The stage is adorned with jaguar patterns, adding a touch of wild flair to the performance.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the male musician and the guitarist in the video are generated abnormally, with the male musician's hand and microphone distorting and deforming in the middle frames, suddenly disappearing or appearing."
}
] |
seed42_256
|
videos/HRA_part0/256.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_3051
|
videos/HRA_part2/3051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white T-shirt and blue jeans, encounters a hare in the midst of vast farmlands, where the land stretches out under a wide, open sky. The scene then shifts to the student swimming in a serene, crystal-clear lake, surrounded by lush greenery, as the hare watches from the shore, curious and alert. The student's relaxed demeanor and the hare's attentive stance create a harmonious moment between nature and humanity, all set against the backdrop of expansive farmlands and a peaceful body of water.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1918
|
videos/HRA_part2/1918.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a brown leather jacket and a gray beanie, sits at a wooden table in a rustic, dimly lit room. With a focused gaze, they caress the worn pages of a chaparral poetry book, their right hand gently touching the text as if feeling the essence of the words. The scene conveys a sense of reverence and connection to literature, with the writer's attire and the chaparral book adding depth to the narrative. The room's ambiance, characterized by wooden elements and soft lighting, enhances the intimate atmosphere as the writer's hand, adorned with a silver ring, lovingly glides over the book's pages.]"
},
{
"from": "gpt",
"value": "Bad. The person's fingers appear deformed."
}
] |
seed44_2473
|
videos/HRA_part1/2473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman dressed in a panther costume, complete with a black leotard, detailed spots, and a lifelike mask, crawls on all fours across a dimly lit stage. The setting is enhanced by a spotlight illuminating her figure, emphasizing the fluidity and grace of her movements, akin to a real panther. The background remains shadowy, drawing attention to her performance as she embodies the essence of the wild animal through her crawling motion.]"
},
{
"from": "gpt",
"value": "Bad. The woman's crawling in the video is very unsmooth, and her movements are uncoordinated."
}
] |
seed42_2278
|
videos/HRA_part0/2278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a yellow shirt, catches a flying drumstick during an energetic performance under the spotlight. The scene transitions to show the artist passionately singing into the microphone, the crowd's glow sticks illuminating the dark venue. Next, the musician is seen catching a guitar pick from another band member, their connection highlighted by the stage lights. Finally, the artist reaches out to catch a flower thrown from the audience, a gesture symbolizing the bond between performer and fans, all set against a backdrop of colorful stage lighting.]"
},
{
"from": "gpt",
"value": "Normal. The musician's arms and fingers are missing in the video, there are issues with the generation of facial features, and the microphone is deformed."
}
] |
seed44_1274
|
videos/HRA_part1/1274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fisherman, clad in a yellow raincoat and matching hat, stands waist-deep in the water, his gaze fixed on the horizon. His hands, weathered from years of labor, expertly handle the fishing net as he casts it into the vast, shimmering sea. The early morning sun bathes the scene in a golden glow, casting long shadows and highlighting the droplets of water clinging to the net. Seagulls circle overhead, their calls adding to the serene atmosphere of the coastal landscape. In the distance, the silhouette of a small fishing village can be seen, smoke rising from the chimneys of the quaint houses, a reminder of the community that thrives on the fruits of the sea.]"
},
{
"from": "gpt",
"value": "Normal. The character's actions of pulling the fishing net in the video are basically normal, with slight disharmony."
}
] |
seed42_2141
|
videos/HRA_part0/2141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captures a raw oyster, nestled on a bed of ice, its textured shell half-open to reveal a plump, glistening body. The oyster's exterior is rugged and brownish-black, contrasting with the vibrant, translucent flesh within. Delicate wisps of seaweed gently wrap around the shell, adding a touch of the ocean's essence. The scene is illuminated by natural light, highlighting the intricate patterns on the shell and the shimmering droplets of moisture on the oyster's surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2998
|
videos/HRA_part1/2998.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious indoor playroom illuminated by large windows, two young children engage in a playful tug-of-war over a vibrant red toy firetruck. The room is filled with various toys scattered across the wooden floor, adding to the sense of fun and activity. The children, both wearing colorful clothing - one in a blue striped shirt and the other in a pink floral dress - display expressions of determination and joy as they pull on opposite ends of the firetruck, their feet firmly planted on the floor. The background features a wall painted with cheerful, cartoonish animal murals, enhancing the whimsical atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The child's fingers and legs are deformed in the video, and the girl's body is not fully generated."
}
] |
seed42_3042
|
videos/HRA_part0/3042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman with salt-and-pepper hair sits in a dimly lit room, wearing a gray blazer and a white shirt with the top button undone. He leans back in a brown leather armchair, holding a book in his hands. The camera captures him from the side, highlighting his profile as he reads intently. Beside him, a wooden table holds a glass of red wine, a vintage lighter, and a half-smoked cigar resting in an ashtray. The atmosphere is cozy and intimate, with the warm glow of a nearby lamp illuminating the scene. Behind the chair, a large bookshelf filled with books adds to the scholarly ambiance. The man's eyes are fixed on the pages, his lips slightly parted, indicating deep concentration as he delves into the story. The setting conveys a sense of leisurely intellectual pursuit, with the elements of wine, cigar, and reading material suggesting a refined evening routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1991
|
videos/HRA_part1/1991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a lush, verdant savanna under a vast, cloud-dappled sky, a graceful antelope leaps and bounds with an almost choreographed elegance, its movements fluid and dynamic against the backdrop of swaying grasses and distant acacia silhouettes. Its coat gleams golden in the warm sunlight, and its horns curve beautifully as it executes a series of leaps that seem to defy gravity, embodying the spirit of dance in the wild. Nearby, a small herd of antelope watches, their postures attentive and curious, creating a scene that is both captivating and enchantingly serene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1214
|
videos/HRA_part0/1214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds where a hedgehog, adorned with miniature headphones and a tiny guitar strapped to its back, embarks on an adventurous journey across a lush, green backyard. It navigates through grassy terrains, darting between vibrant flowers and undergrowth with a sense of purpose. The hedgehog's spines glisten under the golden sunlight, adding a touch of magic to the scene. As it runs, the camera captures the hedgehog from various angles, highlighting its determination and the enchanting world it inhabits. The setting is reminiscent of a fairy tale garden, complete with a wooden fence in the background, framing the hedgehog's spirited escapade.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's back is missing a guitar."
}
] |
seed44_11
|
videos/HRA_part1/11.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bald eagle soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rocky terrain below. It circles gracefully, riding the thermals, with a backdrop of lush green mountains and a distant waterfall. Its piercing yellow eyes scan the landscape, searching for prey, while its sharp talons remain ready to strike. The eagle's brown and white plumage glistens in the sunlight, a symbol of freedom and strength against the stunning natural scenery.]"
},
{
"from": "gpt",
"value": "Normal. The paws are slightly deformed."
}
] |
seed44_2759
|
videos/HRA_part1/2759.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, a mustache, and glasses sits against a white wall, intently sewing a button onto a piece of fabric with a red thread. He wears a gray shirt, and the focus is on his hands, which hold the needle and thread with precision. His facial expression is concentrated, and he occasionally looks up, offering a slight smile. Throughout, he continues his task diligently, the red thread weaving in and out of the button holes, securing it firmly to the fabric. The simplicity of the setting allows the viewer to fully appreciate the man's skill and attention to detail in this everyday task.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2584
|
videos/HRA_part1/2584.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone jackal stands amidst an otherworldly landscape of active volcanoes, its golden eyes reflecting determination. The creature is seen wiping its face with a paw, a gesture of cleansing, against a backdrop of billowing ash and molten lava flows. Surrounded by the harsh beauty of erupting peaks, the jackal's action conveys resilience and survival in the face of adversity, with the volcanoes' fiery eruptions illuminating the dramatic environment.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the jackal in the video are incomplete, and there are issues with the tail generation."
}
] |
seed46_296
|
videos/HRA_part2/296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a dark suit, white shirt, and blue tie, finds himself inexplicably transported to a different era, reminiscent of the TV show 'Quantum Leap.' Crawling through a dimly lit, gritty tunnel, he struggles to understand his time-bending predicament. The tunnel walls are adorned with graffiti and debris, adding to the disorienting atmosphere. Suddenly, the lawyer emerges into a bustling courtroom from the past, where he must now navigate unfamiliar legal challenges. His bewildered expression and the stark contrast between his modern attire and the vintage courtroom setting underscore the surreal nature of his quantum leap experience.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the lawyer moving in the tunnel, but the movements are not continuous and smooth."
}
] |
seed44_1587
|
videos/HRA_part1/1587.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a grouse's head showcases its distinctive red facial wattles and curious, alert expression, set against a blurred forest background. The bird's intricate feather patterns are highlighted, particularly the dark speckles on its brownish-grey plumage. Its sharp, intelligent eyes and slightly open beak convey a sense of awareness and readiness in its woodland habitat. The grouse is perched on a branch, surrounded by lush greenery, with rays of sunlight filtering through the leaves, illuminating its feathers and the rugged bark of the tree.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1457
|
videos/HRA_part0/1457.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a panda bear, donning a red apron and a name tag, stands behind a cash register in a grocery store decorated with red lanterns and Chinese New Year banners. The panda, with its distinctive black and white fur, is seen wiping the countertop meticulously, using a green cloth, while customers wait patiently in line. The scene captures the unique combination of a panda working as a cashier, diligently cleaning the service area, all within a vibrant and culturally-themed supermarket environment.]"
},
{
"from": "gpt",
"value": "Normal. The panda's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1842
|
videos/HRA_part1/1842.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 runs energetically across a grassy plain, its ears perked up and alert, showcasing its distinctive rodent features. It sprints with determination, its body low to the ground, through a lush, green environment dotted with trees. The capybara's movement is fluid and powerful, its legs propelling it forward with each stride, as it navigates the vibrant landscape under a bright, open sky.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's movements in the video are not smooth."
}
] |
seed44_3143
|
videos/HRA_part1/3143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 children, a boy and a girl, are working together to mend a broken wooden fence in a rural, grassy area. The boy, wearing a gray T-shirt and blue jeans, holds a hammer in his right hand, while his left hand grips a nail. He looks intently at the task before him. The girl, dressed in a yellow top and blue jeans, assists by holding the loose board steady. She looks up, perhaps seeking approval or guidance. Behind them, a lush green landscape stretches into the distance, with tall trees framing the horizon. The sunlight filters through the leaves, casting dappled shadows on the ground, highlighting the industriousness of the young duo as they focus on fixing the fence.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2665
|
videos/HRA_part1/2665.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, dressed in a futuristic spacesuit, gently caresses a small, feathered chicken on a Mars base camp, surrounded by high-tech equipment and monitors displaying scientific data. The young woman, with her hair tied back in a bun, looks down at the bird with a warm smile, providing a moment of tenderness in the stark, utilitarian environment. The base camp is illuminated by artificial lights, casting a soft glow on the scene, with the red Martian landscape visible through the transparent dome. The student's affectionate gesture towards the chicken offers a sense of comfort and connection in the otherwise alien setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1513
|
videos/HRA_part2/1513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 conservation worker, dressed in a brown long-sleeved shirt and khaki cargo pants, is crawling on his hands and knees across the grassy terrain of a historical site. He meticulously examines the ancient stone structures, his focus intense as he searches for signs of wear or damage needing repair. The historical site, a series of weathered stone ruins set against a backdrop of lush greenery, is both his workplace and passion. His dedication to preserving history is evident in every careful movement, as he works under the open sky, surrounded by the remnants of the past.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1572
|
videos/HRA_part2/1572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diligently cleaning a large fish tank positioned against a wall covered with a floral-patterned curtain. The boy, wearing a gray shirt and dark pants, uses a net to scoop debris from the water, while the girl, dressed in a yellow shirt and blue jeans, scrubs the glass with a small brush. Both children work attentively, surrounded by an array of aquarium supplies, including bags of gravel, fish food containers, and various cleaning tools. The tank is home to several colorful fish that swim tranquilly in the background, undisturbed by the children's careful efforts to maintain their environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, and the face is deformed."
}
] |
seed46_1005
|
videos/HRA_part2/1005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a crisp white uniform and a colorful stethoscope, finds herself at the edge of a vast, shimmering ocean, where the sand meets the water. In her arms, she holds a small, fluffy rabbit, its ears perked up in curiosity. Together, they watch as a group of rabbits, similarly white and fluffy, leap and jump playfully across the sandy shore, the waves gently lapping at the background, creating a serene and whimsical scene.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit on the beach has uncoordinated limbs, and its jumping movements are not smooth and continuous."
}
] |
seed46_1432
|
videos/HRA_part2/1432.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, neatly trimmed beard, and glasses stands in a modern office setting, wearing a dark gray blazer, white shirt, and jeans. He points his right index finger upward with a serious yet excited expression, indicating an idea or making a significant point. Behind him, a large window reveals a cityscape, adding depth and context to the scene. The office is sparsely decorated, featuring a simple desk and chair, which complements the minimalist aesthetic of the space.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_2106
|
videos/HRA_part1/2106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 waiter, clad in a black vest, button-down shirt, and striped tie, meticulously mops the floor of an empty restaurant with white walls and ceiling, wooden tables and chairs, and large windows. The room is illuminated by soft artificial lighting, casting a warm glow on the clean, wet floor. The waiter's movements are deliberate and focused, his mop leaving a trail of cleanliness across the tile surface. In the background, a fully set table with a white cloth, silverware, and glasses awaits the next guests, while a row of wine bottles sits on a shelf above. The scene conveys a sense of preparation and attention to detail, as the waiter ensures the dining area is spotless for the upcoming service.]"
},
{
"from": "gpt",
"value": "Bad. The facial features and hands of the server, as well as the mop, have generation issues in the video."
}
] |
seed44_1348
|
videos/HRA_part1/1348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman stands tall in the middle of a crosswalk in a bustling city, clad in a long, camel-colored coat that reaches her knees, dark trousers, and high-heeled boots. Her outfit is complemented by a brown leather handbag hanging from her right shoulder. The cityscape behind her, featuring pedestrians, traffic lights, and urban architecture, adds to the dynamic setting. Her confident stance and the urban environment create a captivating scene, with the woman at the center, embodying poise and independence.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers in the video are not fully generated, and there are issues with the generation of the handbag and the woman's legs."
}
] |
seed44_2875
|
videos/HRA_part1/2875.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating close-up, a tiny weasel, no larger than a human hand, emerges from a hole in a tree trunk set against the vast, snow-covered taiga. Its bright eyes curiously scan its surroundings. It then playfully interacts with the bark, as if caressing it, showcasing a rare display of animal behavior. The camera then captures the weasel's face in detail, highlighting its sharp features and lively demeanor. Lastly, it returns to the hole, pausing once more to look back, offering a final glimpse of its charming presence in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's paws and mouth generation in the video have issues."
}
] |
seed42_1414
|
videos/HRA_part0/1414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate female nurse, wearing a traditional white uniform and cap, sits at a vintage wooden desk in a quaint room adorned with antique medical equipment. She attentively sketches a detailed anatomical heart in red pencil on a large pad of white paper, showcasing her artistic skills. The room is illuminated by a single, focused lamp, casting a warm glow over her work. Beside her, a shelf displays various medical tools and books, emphasizing her professional environment. Throughout the scene, she remains engrossed in her drawing, her dedication and precision evident in each stroke.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1316
|
videos/HRA_part2/1316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a sandy beach, two smiling children, a boy and a girl, gently caress a small green lizard that rests on a patch of dry sand, surrounded by lush vegetation. The boy, wearing a blue t-shirt and blue swimming trunks, and the girl, clad in a pink dress, sit cross-legged as they tenderly pet the lizard. The scene is filled with warmth and sunlight, casting shadows of the children and the lizard onto the sandy ground. Moments later, the lizard scurries away into the foliage, and the children watch it go, their faces a mix of fascination and delight, embodying the innocence and wonder of childhood discovery.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_100
|
videos/HRA_part2/100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large capybara, the biggest living rodent, dashes across a vast, barren landscape under a twilight sky filled with cosmic dust swirling in a storm. The capybara, with its distinct features, including a wide face, small ears, and thick fur, runs with determination, its eyes fixed ahead. As it sprints, the cosmic dust storm overhead intensifies, particles of stardust illuminated by the fading sunlight, creating an ethereal atmosphere. Against this dramatic backdrop, the capybara continues its urgent journey, its powerful legs propelling it forward in a series of fluid leaps, leaving a trail of disturbed soil in its wake.]"
},
{
"from": "gpt",
"value": "Bad. The head and tail will switch, and there is twisting in the legs."
}
] |
seed42_2092
|
videos/HRA_part0/2092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic actor, wearing a sleek black suit and tie, performs an elegant dance move against a backdrop of Saturn's magnificent ring system, which glimmers with ethereal beauty in the distance. His confident posture and engaging smile captivate the viewer, while the celestial wonder behind him adds a touch of grandeur to the scene. The actor's polished shoes and well-groomed appearance contrast with the vastness of space, creating a unique juxtaposition between human artistry and cosmic splendor.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs and facial features in the video are deformed."
}
] |
seed44_1671
|
videos/HRA_part1/1671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and denim overalls, rests on his hands and knees in a lush green field, engaging in a playful crawl. Beside him, a curious brown hare mimics his movements, hopping and crawling through the tall grass, creating a heartwarming scene of unexpected companionship between man and nature. The farmer's joyful expression and the hare's energetic antics set against the vibrant green landscape capture a rare moment of harmony in the countryside.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the rabbit and the farmer in the video are very unsmooth and uncoordinated."
}
] |
seed42_1963
|
videos/HRA_part0/1963.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 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 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": "Normal. The server's fingers in the video are not fully generated."
}
] |
seed46_1852
|
videos/HRA_part2/1852.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female cashier, with a casual hairstyle and wearing a dark green jacket over a gray t-shirt, leans against a white wall with a wooden panel. She holds a book titled \"The Great Gatsby\" by F. Scott Fitzgerald, reading it intently during a break. The scene is set in a grocery store aisle, with shelves stocked with products like canned goods and boxes of cereal visible in the background. The cashier's relaxed posture and focused gaze on the classic novel convey a sense of peace and personal time amidst her work environment.]"
},
{
"from": "gpt",
"value": "Bad. The person's fingers appear deformed."
}
] |
seed46_2783
|
videos/HRA_part2/2783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 teenage girl sits at a wooden desk in a classroom, diligently hemming a pair of khaki pants using a sewing machine, her focus unwavering. She wears a yellow blouse, and her hair is tied back in a ponytail, highlighting her concentration. On the desk, a tape measure, scissors, pins, and a spool of thread are neatly arranged. Beside her, a bulletin board displays various fabric swatches and design sketches, adding context to her task. The room is illuminated by natural light from a window, casting a warm glow over her industrious endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video uses the sewing machine basically fine, but her movements are slightly uncoordinated."
}
] |
seed42_1533
|
videos/HRA_part0/1533.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a red shirt and dark pants, stands at the edge of a vast highway interchange, bathed in the golden glow of twilight. With city lights twinkling in the distance, he begins to dance, his movements expressive and free, contrasting with the concrete jungle around him. Cars whiz by on multiple levels of the highway, their headlights and taillights creating streaks of color against the dusky sky. The man continues to dance, his silhouette framed by the urban landscape, embodying a sense of liberation amidst the urban sprawl.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video dances very unsmoothly, with uncoordinated movements."
}
] |
seed46_231
|
videos/HRA_part2/231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room illuminated by the soft glow of a Martian sunset, visible through a large window displaying the red planet's horizon, two young children sit cross-legged on a wooden floor. They gently caress a small, furry gerbil sitting on a colorful blanket, their faces reflecting expressions of pure delight and wonder, as they interact with the pet in the unique, alien environment.]"
},
{
"from": "gpt",
"value": "Bad. The child's gentle stroking of the hamster is discontinuous, with sudden changes."
}
] |
seed46_2521
|
videos/HRA_part2/2521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, donning a black hat and dressed in a brown jacket over a white shirt, plays a wind instrument passionately in an art gallery filled with contemporary art pieces. Suddenly, a gazelle, a symbol of grace and freedom, jumps into the frame from the right side, leaping over a low sculpture, adding an unexpected yet harmonious element to the scene. The focus remains on the musician and the gazelle, with the vibrant artwork providing a stimulating backdrop, all captured in a single, continuous shot.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2874
|
videos/HRA_part1/2874.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 experienced engineer, clad in a futuristic spacesuit with an illuminated helmet, embarks on a critical space rescue mission. Against the backdrop of a vast, starlit cosmos, he is seen swimming through the emptiness of space, propelled by bursts from his suit's thrusters. With a focused gaze and a determination to save lives, he maneuvers towards a damaged spacecraft, its hull breached and systems failing. The engineer's suit, equipped with advanced technology, allows him to navigate the zero-gravity environment with precision and grace, as he reaches the stricken vessel to begin emergency repairs.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit 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": "Bad. The cat's head generation in the video has issues."
}
] |
seed44_1905
|
videos/HRA_part1/1905.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, imposing goose stands tall on the bank of a misty lake, its yellow beak agape as it emits a loud honk. Its body is a mix of gray and white feathers, with a distinctive black mark around one eye. The goose's webbed feet are visible as it wades into the water, creating ripples that disturb the stillness of the early morning. Against the backdrop of a cloudy sky, the goose swims gracefully, its head held high, exuding an air of confidence and territorial dominance. The scene is set in a natural, serene environment, with the goose being the focal point, highlighting its majestic presence in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_132
|
videos/HRA_part1/132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A skilled musician, clad in a black turtleneck and jeans, sits on a stage, intently playing a marimba with mallets. Nearby, a gorilla, perhaps a part of the performance or installation art, is crawling on all fours, wearing a red beret and blue jeans, adding an unexpected element to the scene. The contrast between the focused human artist and the ape in casual attire creates a surreal and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1518
|
videos/HRA_part0/1518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, elegant restaurant, a human-like weasel dressed in a formal waiter's uniform, complete with a crisp white shirt, black vest, and bow tie, is shown caressing a wine glass with intricate patterns, displaying its refined touch and attention to detail. The weasel's anthropomorphic features are enhanced by its upright posture and expressive face, which conveys sophistication and professionalism. The scene is set against a backdrop of luxurious dining, with the weasel's gentle handling of the glass highlighting its dexterity and grace.]"
},
{
"from": "gpt",
"value": "Normal. The sommelier's gesture of lightly touching the wine glass in the video is not smooth and coordinated."
}
] |
seed44_2737
|
videos/HRA_part1/2737.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil, shallow pond surrounded by lush vegetation, a large moose with a wide, flat antler rack stands with its head submerged underwater. As it lifts its head, water droplets cascade down its face. The animal then proceeds to shake its head vigorously from side to side, flinging water off its fur and antlers. Its ears flap dynamically during the shaking motion, and its tongue can be seen hanging out playfully. Throughout the scene, the moose's eyes remain closed, indicating its enjoyment of the refreshing activity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1735
|
videos/HRA_part2/1735.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom setting, a cartoon beaver, wearing a brown graduation cap and holding a yellow eraser, energetically wipes a green chalkboard clean, revealing a lesson about the water cycle. The beaver, now wearing a white shirt with a red tie and a brown vest, continues to erase enthusiastically, displaying a fun and engaging teaching style. Next, the beaver, still in its academic attire, uses the eraser to remove the last bit of chalk from the board, ensuring the surface is completely clear. Finally, the animated beaver teacher, dressed in its scholarly outfit, stands proudly beside the now-blank chalkboard, ready for the next lesson.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not smooth, and the more you wipe, the more words appear."
}
] |
seed46_206
|
videos/HRA_part2/206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, distinguished by its black and white striped face and brown fur, scurries through a network of intricately dug tunnels in a dimly lit sett. The animal, with its stocky build and sharp claws, moves swiftly and purposefully, navigating the narrow passages with ease. As it runs, the texture of the tunnel walls, composed of earth and roots, becomes apparent, providing a natural contrast to the badger's movement. Throughout the sequence, the focus remains on the badger's journey within the tunnel system, emphasizing its agility and familiarity with its subterranean habitat.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the European badger in the video are missing, and the facial features are deformed."
}
] |
seed44_2806
|
videos/HRA_part1/2806.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, wearing a dark blue jacket, beige pants, and carrying a brown backpack, runs along the docks on a misty day, passing by large ships and industrial buildings. He stops momentarily to gaze at the water, his reflection visible in the wet pavement. Continuing his run, he passes wooden benches and green spaces, with the city skyline in the distance. Throughout his journey, he remains engrossed in his thoughts, occasionally glancing down at a notebook tucked into his backpack, the colors of the docks' wood and metal contrasting against the muted tones of the surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1698
|
videos/HRA_part0/1698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A nimble squirrel, brimming with energy, leaps from a moss-covered branch in a lush, vibrant forest. The scene is bathed in a soft, golden light filtering through the dense canopy above. The squirrel's movement is captured mid-jump, its body arched gracefully in the air, showcasing its agility and speed. Its bushy tail trails behind, adding to the dynamic feel of the action. The background is a tapestry of green foliage, dotted with various tree trunks, providing a rich, textured setting for the squirrel's acrobatics.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's movement in the video is not smooth, and the actions are uncoordinated."
}
] |
seed46_2926
|
videos/HRA_part2/2926.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a gray suit, white shirt, and striped tie, stands on a chair in a modern office space with high ceilings and large windows. Holding a light bulb, he appears mid-action, changing the bulb with determination. The office is filled with contemporary furniture and technology, including a sleek desk, ergonomic chair, and flat-screen monitor. The scene is lit by the natural light streaming in from the windows, casting a warm glow on the lawyer as he completes his unexpected task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_169
|
videos/HRA_part2/169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Shanghai, under the glow of neon signs and the hustle of the city streets, a peculiar scene unfolds. A street musician, dressed in a vibrant red jacket and dark jeans, passionately plays a saxophone, its golden finish shimmering under the streetlights. Beside him, a chimpanzee, wearing a tiny blue cap and a checkered shirt, mimics the musician's movements, adding an element of whimsy to the performance. As the music fills the air, a group of runners, clad in various sportswear and illuminated by the urban landscape, passes by, some pausing to watch the unique spectacle, while others continue their journey through the lively Shanghai night.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2147
|
videos/HRA_part0/2147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse in a sky-blue uniform, complete with a matching cap, stands at the edge of a bustling harbor. The sun illuminates her figure as she prepares to leap into the air, her silhouette framed by the vibrant scene of ships and docks in the background. Her joyful expression contrasts with the busy maritime activities, capturing a spontaneous moment of playfulness amidst a working waterfront.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1414
|
videos/HRA_part2/1414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate female nurse, wearing a traditional white uniform and cap, sits at a vintage wooden desk in a quaint room adorned with antique medical equipment. She attentively sketches a detailed anatomical heart in red pencil on a large pad of white paper, showcasing her artistic skills. The room is illuminated by a single, focused lamp, casting a warm glow over her work. Beside her, a shelf displays various medical tools and books, emphasizing her professional environment. Throughout the scene, she remains engrossed in her drawing, her dedication and precision evident in each stroke.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's fingers in the video are not fully generated."
}
] |
seed42_3062
|
videos/HRA_part0/3062.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a thoughtful writer sits at a cluttered desk, typing away on a laptop with determination. Suddenly, the scene focuses on a small vole, its fur a mix of brown and gray, crawling out from beneath the wooden desk. The rodent explores its surroundings, nibbling on a pencil and climbing onto a pile of books, all while the writer continues to work, seemingly unaware of the tiny creature's presence.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3008
|
videos/HRA_part1/3008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown leather jacket and blue jeans, is seen energetically dancing in a surreal scene set in the middle of a vast prairie. Surrounding him are several large bison, who calmly observe the director's enthusiastic dance moves under the open sky. The director, displaying an unexpected sense of whimsy, continues to dance amidst the majestic animals, creating a unique juxtaposition between human creativity and the untamed beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, hands, and buffalo legs are also twisted."
}
] |
seed44_1428
|
videos/HRA_part1/1428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A handsome male waiter, wearing a crisp white shirt, black vest, and necktie, serves a couple at an elegant indoor restaurant. Suddenly, he breaks into song, passionately singing an operatic aria while continuing to serve. The camera captures his animated face as he sings, highlighting his emotional performance. Throughout, the well-lit dining area with its ornate chandelier and patrons at other tables remains visible, creating a lively atmosphere. The waiter's confident singing and the restaurant's upscale ambiance provide a memorable contrast to his regular duties.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1724
|
videos/HRA_part1/1724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine, high-quality piece of cod fish is showcased, featuring a clean, white fillet with a compact, flaky texture. The fish is presented on a simple, rustic wooden board, accompanied by fresh lemon wedges and sprigs of dill, enhancing the natural freshness and flavor of the cod. The background is softly blurred, emphasizing the star of the show—the cod fish—while maintaining a clean, modern aesthetic. The lighting highlights the fish's texture and color, making it appear both appetizing and ready for culinary preparation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1675
|
videos/HRA_part2/1675.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, spiky European hedgehog leaps into the air, defying expectations as it jumps over a miniature hurdle, showcasing its unexpected agility. The hedgehog, with its typical brown and white quills, lands softly on a lush green surface, demonstrating its natural ability to navigate obstacles. The scene is set against a simple, uncluttered outdoor backdrop, allowing the hedgehog's unique action to be the focal point of the video.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's limbs in the video are not fully generated, and the claws are incomplete."
}
] |
seed46_1501
|
videos/HRA_part2/1501.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a tan belt holding a radio and handcuffs, diligently repairs a damaged wooden fence in a suburban neighborhood. The fence, marred by graffiti and broken planks, is set against a clear blue sky. The officer, wearing a hat and sunglasses, demonstrates community involvement by hammering a new plank into place, emphasizing public service beyond traditional law enforcement duties.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1241
|
videos/HRA_part1/1241.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, 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 is not wearing glasses."
}
] |
seed46_1353
|
videos/HRA_part2/1353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone kangaroo stands in a vast, sunlit Australian outback, its shadow cast long on the sandy ground. It lifts a paw to its face, wiping it in a human-like gesture, its fur ruffled by a gentle breeze. The kangaroo's expressive face, with large, curious eyes, focuses intently as it performs this action, its body language conveying a sense of self-awareness. Behind it, the outback stretches to the horizon, dotted with scrub and sparse vegetation, creating a stark contrast to the active, sentient creature in the foreground.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's face is distorted, its legs are twisted, and its body is contorted."
}
] |
seed42_1570
|
videos/HRA_part0/1570.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with advanced equipment, a dedicated scientist, wearing a white lab coat over a dark shirt and jeans, gently caresses a sophisticated device used in dark matter research. The scientist, sporting short hair and glasses, exhibits a deep connection with the apparatus, conveying the tender care required in handling delicate scientific instruments. The background features a complex arrangement of machinery and computer screens, highlighting the cutting-edge nature of the research being conducted. This intimate interaction between the researcher and the technology underscores the human element in the pursuit of understanding the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1262
|
videos/HRA_part1/1262.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly lush subtropical wet forest, an enthusiastic teacher, wearing a green shirt and khaki shorts, energetically dances among tall trees, their leaves forming a dense canopy overhead. The educator gracefully leaps and twirls, engaging with the natural surroundings, while a curious hare watches from the undergrowth, its ears perked up in interest. Sunlight filters through the foliage, casting dappled shadows on the forest floor, enhancing the magical atmosphere as the teacher continues to dance, celebrating the beauty of the environment with joyful movements.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1268
|
videos/HRA_part1/1268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a brown jacket, beige pants, and carrying a sketchbook, walks through a surreal landscape inspired by a galactic nebula. The sky is a vivid swirl of cosmic colors - deep purples, electric blues, and fiery oranges, evoking the ethereal beauty of distant galaxies. Giant, floating rock formations, tinged with the same nebulous hues, tower above, while the ground beneath his feet is a shimmering, star-lit plane that reflects the celestial spectacle overhead. Despite the otherworldly setting, the artist strides purposefully, his form and clothing sharply detailed against the dreamlike backdrop, as if he's on a mission to capture the universe's wonders on paper.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2037
|
videos/HRA_part1/2037.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a full uniform complete with a badge, gun, and radio, is seen in a modern kitchen with gray walls, white cabinets, and stainless steel appliances. He is intently loading dishes into a dishwasher, his focus and precision reflecting his attention to detail, typically associated with his law enforcement duties. The kitchen counters are clean and clutter-free, except for a few dishware items awaiting their turn in the dishwasher. The officer's demeanor suggests a moment of domestic routine amidst his usual high-stakes professional life.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1000
|
videos/HRA_part2/1000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged cashier, donning a red apron over a casual outfit, is shown unclogging a drain in a break room, revealing a moment of unexpected duty. The scene opens with the cashier looking into the drain with a concerned expression, followed by her using a plunger to clear the clog, showcasing determination. Next, she inspects the plunger with a look of resolve, indicating her commitment to resolving the issue. The scene then shows her pouring a cleaning solution down the drain, wearing rubber gloves for protection, and finally, she tests the faucet, ensuring the water flows freely, a sign of success, all while maintaining her red apron emblematic of her primary role.]"
},
{
"from": "gpt",
"value": "Bad. The plunger mentioned in the caption does not appear in the video."
}
] |
seed44_1771
|
videos/HRA_part1/1771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, equipped with a duty belt and a radio, is seen kneeling on a polished wooden floor in a residential setting, attentively wiping the muddy paws of a large, brown dog. The officer wears a serious expression, focused on the task at hand, ensuring the canine's paws are clean. The environment is warm and welcoming, with a Christmas tree in the background, decorated with colorful ornaments and lights, adding a festive touch to the scene. The officer's careful actions and the presence of the holiday decorations create a sense of care and community during the holiday season.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3132
|
videos/HRA_part0/3132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, wearing a navy blue blazer, sits against a dark, textured background, nodding sagely as he listens to an off-screen voice. His salt-and-pepper hair, trimmed beard, and wire-rimmed glasses add to his sophisticated appearance. Throughout the scene, he continues to nod in agreement, his expressions conveying understanding and engagement. The focus remains tight on his face, capturing every nuanced gesture and emotion, highlighting his acting prowess in this intimate setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1138
|
videos/HRA_part2/1138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a yellow raincoat and clutching a large sketchbook, walks through a lush botanical garden filled with vibrant greenery and colorful flowers. A curious vole scampers across the path ahead of her, its presence adding a touch of whimsy to the serene environment. The artist pauses, observing the small creature before continuing her leisurely stroll, the intricate details of the garden's foliage providing inspiration for her artwork. The scene is framed by towering trees and the sounds of nature, creating a peaceful atmosphere as the artist explores the beauty of the botanical gardens.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2764
|
videos/HRA_part0/2764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lone penguin stands majestically on a frosty, ice-covered shore, its sleek black and white feathers glistening under the soft, diffused light of an overcast sky. The penguin, with its round body, small flippers, and distinctive tuxedo-like appearance, looks out to the vast, icy sea, creating a sense of solitude and resilience in the harsh Antarctic environment. The scene is framed by rugged, snow-capped mountains in the distance, emphasizing the penguin's natural habitat and the stark beauty of its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2916
|
videos/HRA_part0/2916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown rat crawls across a desolate volcanic landscape, featuring dark, rocky terrain and smoldering vents emitting wisps of smoke. The rat moves with surprising agility among the rough, jagged rocks, its fur contrasting against the ash-covered ground. As it navigates the harsh environment, the camera captures its determined journey, highlighting its resilience in the face of the volcano's foreboding presence. Throughout the scene, the rat's focus remains unwavering, emphasizing its survival instincts in this challenging, post-eruption setting.]"
},
{
"from": "gpt",
"value": "Bad. The brown rat's paws are deformed, limbs are missing, and there are issues with the head and tail generation."
}
] |
seed46_3141
|
videos/HRA_part2/3141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, donning a yellow vest and jeans, finds unexpected joy as he dances with a gentle horse in a grassy, fenced-in yard beside a country house. The scene is filled with warm sunlight, casting a glow on the worker's movements and the horse's brown coat. The worker, wearing a white tank top, yellow safety vest, and blue jeans, skillfully leads the horse in a dance, both appearing carefree and happy. Their joyful interaction is set against a backdrop of greenery and a wooden fence, creating a heartwarming contrast to the worker's usual environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2906
|
videos/HRA_part0/2906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished, middle-aged man wearing a white lab coat over a crisp blue shirt and khaki trousers walks his golden retriever on a leash in a lush, green park. The sun filters through the leaves, casting dappled light on the path. The doctor, with salt-and-pepper hair and glasses, smiles warmly as he interacts with his dog, which bounds joyfully ahead, exploring the surroundings. The two stroll past other park-goers, who exchange friendly nods, creating a scene of community and companionship in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3183
|
videos/HRA_part0/3183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, hardworking nurse, identifiable by her scrubs—light blue top and dark blue pants—devotes her day off to organizing her garage. She sorts through items, deciding what to keep, with sunlight streaming in from the open garage door. The nurse, now in a different set of scrubs, green top and dark blue pants, methodically arranges tools and equipment on shelves. She pauses to admire her progress, standing amid her organized belongings, which include a bicycle and various household items. Finally, she wipes her brow, pleased with her efforts, as she surveys the tidy space, now a reflection of her meticulous nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2550
|
videos/HRA_part1/2550.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow vest over a dark jacket and jeans, walks purposefully down a hospital corridor. The hall is lined with evenly spaced white doors and illuminated by overhead lights, casting a warm glow. The man holds a mop bucket in one hand, its handle adorned with a colorful cloth hanging loosely. He moves with determination, his work boots echoing softly on the linoleum floor, creating a sense of routine and responsibility in the clean, institutional environment.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's walking movements can be clearly seen in the video, the movements are basically normal, but there is slight disharmony."
}
] |
seed42_1577
|
videos/HRA_part0/1577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant classroom decorated with colorful posters and student artwork, a passionate teacher, wearing a dark green shirt and khaki pants, is seen in the act of catching a ball, demonstrating a physics lesson on motion and gravity. The students, seated at their desks, watch intently as the teacher, with a lively expression, skillfully catches the ball mid-air, illustrating the principles of force and motion in an engaging and interactive manner.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2258
|
videos/HRA_part0/2258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man, reminiscent of Jason Statham, with short, dark hair and a chiseled jawline, wearing a torn gray tank top, tattered khaki pants, and combat boots, stealthily walks through a dimly lit space station corridor. The setting is a gritty, futuristic prison, with cold steel walls, flickering neon lights, and a tense atmosphere. The man moves with purpose and determination, his eyes scanning the surroundings for any sign of danger. In one shot, he pauses, listening intently, before continuing his escape mission. Throughout the sequence, the tension builds as he navigates the confined spaces of the prison, evoking a sense of suspense and urgency.]"
},
{
"from": "gpt",
"value": "Normal. The man's hands and feet in the video have generation issues."
}
] |
seed44_1370
|
videos/HRA_part1/1370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic winter scene, a person clad in a thick, dark coat and matching hat walks across a snow-covered bridge, overlooking the Mammoth Mountain Ski Area. The resort's facilities, including chairlifts and lodges, are visible in the background, nestled among the snow-dusted trees. The individual continues their stroll, passing by a small, quaint chalet with smoke billowing from its chimney, adding a touch of warmth to the frosty landscape. Finally, they pause to admire the panoramic view of the snow-capped mountains and the sprawling ski resort, all while bundled up against the cold, encapsulating the essence of a winter wonderland adventure.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted."
}
] |
seed44_2330
|
videos/HRA_part1/2330.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a large, ghostly jellyfish with a brownish hue and intricate patterns floats serenely, its trailing tentacles creating mesmerizing movements against a dark blue background. Another jellyfish appears, smaller and more transparent, with delicate bell-shaped bodies and fine, trailing tendrils that seem to glow softly in the mysterious depths. The camera focuses on a stunning, semi-transparent jellyfish with a large bell and long, flowing tentacles that appear to sparkle, evoking a sense of enchantment and wonder in the deep blue sea. Lastly, a beautiful, clear jellyfish with a large bell and fine, trailing tendrils is captured in a captivating close-up, its body illuminated by a soft glow as it gently pulsates through the water, showcasing the mesmerizing beauty of these ethereal creatures.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.