video_id
stringlengths
8
11
video
stringlengths
22
25
conversations
listlengths
2
2
seed46_2901
videos/HRA_part2/2901.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, agile mongoose, with its distinctive reddish-brown fur and sharp eyes, is seen crawling slowly through a dense grassland environment. It moves stealthily, its body hugging the ground, as it searches for prey or navigates its territory. The scene is set under the warm glow of the afternoon sun, casting long shadows and highlighting the mongoose's fur texture against the green backdrop. Its cautious movements and keen senses are evident as it crawls, making it appear both vulnerable and predator in the wild landscape.]" }, { "from": "gpt", "value": "Good. Basically no issues." } ]
seed44_2295
videos/HRA_part1/2295.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." } ]
seed46_284
videos/HRA_part2/284.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a lab coat over a collared shirt and khaki pants, gently caresses a hamster in a zero-gravity environment, suggesting space agriculture. The doctor, with neatly trimmed facial hair and spectacles, holds the hamster with care and attentiveness, floating effortlessly in a spaceship's cabin. The hamster, nestled in the palm of the doctor's hand, appears relaxed and comfortable, indicating a nurturing bond between the two. In the background, hydroponic plants grow in LED-lit chambers, emphasizing the agricultural aspect of the scene. The doctor's focus on the hamster, combined with the futuristic setting, conveys a sense of compassion and innovation in space farming.]" }, { "from": "gpt", "value": "Bad. The doctor's hands appear deformed and misshapen, and the rat's paws also show deformities." } ]
seed44_2454
videos/HRA_part1/2454.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 young student, dressed in a black robe and cap, runs through a futuristic, space-themed cemetery, where floating gravestones and holographic epitaphs are the norm. The sky is tinted with purples and blues, hinting at twilight in this extraterrestrial setting. The student, with short brown hair and a determined look, sprints past the unique graves, which include a zero-gravity burial pod and a memorial sculpture made of interstellar dust. The landscape is dotted with alien flora and fauna, adding to the otherworldly atmosphere of this solemn yet dynamic scene.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed42_146
videos/HRA_part0/146.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant, sun-dappled deciduous forest during autumn, several joyful people gather for an impromptu dance party. The scene opens with a close-up of a smiling woman in a floral dress, her arms raised as she twirls under the golden leaves. Next, a group of friends, dressed in casual fall attire like sweaters and jackets, laugh and dance together, surrounded by tall trees and colorful foliage. The camera then captures a couple slow dancing romantically, their embrace tender and intimate, with the forest's warm hues providing a romantic backdrop. Lastly, the entire group comes together, forming a circle as they dance energetically, their laughter and the rustling leaves blending into a symphony of happiness in the heart of the forest.]" }, { "from": "gpt", "value": "Bad. The character's body movements are not coordinated." } ]
seed46_304
videos/HRA_part2/304.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, dressed in a classic white uniform and black pants, walks through a lush, green forest carrying a live rabbit in his arms. The chef's attire is detailed, complete with a traditional white chef's jacket, black trousers, and a pristine white chef's hat. The rabbit, a live and lively creature, is held gently in the chef's arms as he strolls through the dense woodland. The forest setting is richly depicted, with tall trees, vibrant foliage, and dappled sunlight filtering through the leaves, creating a dramatic contrast with the chef's uniform and the rabbit's fur.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed42_1425
videos/HRA_part0/1425.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint town with brick-paved streets and Victorian-style buildings, a uniformed police officer stands watch over a community swimming pool filled with clear, blue water. The officer, clad in a crisp blue uniform, cap, and sunglasses, leans against a wooden fence, observing the swimmers. Children play joyfully in the shallow end, splashing each other, while adults lounge on deck chairs under colorful umbrellas. The scene is framed by lush greenery and the charming town in the background, creating a peaceful and idyllic setting.]" }, { "from": "gpt", "value": "Bad. The children playing in the shallow water suddenly disappear in the middle of the video; the adult resting on the lounge chair has an abnormal body structure; there is an issue with the generation of the police officer's hand." } ]
seed42_2364
videos/HRA_part0/2364.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged-looking man with short, dark hair and a trimmed beard focuses intently on repairing a vintage bicycle, his body partially covering the bike's frame. Dressed in a light blue, short-sleeved shirt, khaki pants, and brown work boots, he leans over the bike, which is held upright by a repair stand. His right hand grips a wrench, while his left hand steadies the bike, both hands stained with grease. The scene is set against a backdrop of a cluttered garage filled with various tools and equipment, emphasizing the worker's expertise and dedication to his craft.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_2920
videos/HRA_part1/2920.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, donning a crisp white shirt, black trousers, and a waistcoat, unexpectedly finds himself fixing a leaky faucet in a vintage-styled restroom. With a wrench in hand, he leans over the basin, his face concentrated as he works under the sink. The scene captures the unusual sight of the waiter, his attire contrasting with the task at hand, as he tightens the faucet, the water now streaming smoothly. The room is adorned with antique fixtures and a classic mirror above the basin, adding to the unique scenario of a waiter turned handyman.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_291
videos/HRA_part0/291.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed doctor, wearing a white button-down shirt and khaki shorts, leaps into the air on a pristine, sandy beach, with crystal-clear water visible in the background. The doctor, who has brown hair and glasses, is captured mid-jump, displaying a sense of freedom and joy. The scene is set against a stunning backdrop of palm trees and a clear blue sky, creating a perfect blend of professional and leisure elements. The doctor's relaxed attire and the idyllic beach setting convey a sense of balance between work and personal life.]" }, { "from": "gpt", "value": "Bad. The doctor's face in the video is generated blurry, and the limbs are deformed." } ]
seed44_1379
videos/HRA_part1/1379.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned chef, donning a traditional white chef's uniform with a checkered bandana, performs a dynamic pizza toss in a bustling pizzeria kitchen. The dough stretches gracefully as it rotates in mid-air, illuminated by the warm glow of overhead lights. The chef's confident expression and practiced movements highlight his expertise, while the lively atmosphere of the kitchen, filled with the sounds of sizzling pans and cheerful chatter, adds to the vibrant scene. In the background, a row of wood-fired ovens and a team of chefs busily preparing various dishes complete the authentic pizzeria setting.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_1690
videos/HRA_part1/1690.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 sci-fi scene, a weasel cosmonaut, clad in a full spacesuit with a helmet adorned with ears, performs meticulous maintenance aboard a spaceship. The weasel is seen wiping the control panels with a cloth, ensuring every surface is clean. The spaceship, with its sleek silver body and blue lights, is docked at a space station, which can be seen through the large, circular window behind the weasel. The space station is a complex structure with multiple levels and tubes, illuminated by various lights. The weasel continues its diligent cleaning tasks, moving methodically from panel to panel, while the spaceship remains securely docked at the space station.]" }, { "from": "gpt", "value": "Bad. The towel in the weasel's hand is deformed, and its legs are also deformed." } ]
seed42_3076
videos/HRA_part0/3076.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 young student, wearing a casual outfit of a gray jacket over a black shirt and dark pants, is seen cleaning a table at a busy train station. The environment is filled with travelers rushing to catch their trains, creating a bustling atmosphere. The student diligently wipes the surface, moving from left to right, ensuring cleanliness in the public space. The scene captures the student's commitment to maintaining hygiene amidst the chaotic surroundings of the train station.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_2886
videos/HRA_part0/2886.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a brown jacket and khaki pants, is seen working on a fence under the clear blue sky of a rural area, far from any city. Despite his occupation as a cashier, he tackles the fence repair with determination, using a hammer to secure wooden planks. The fence, which borders a grassy field, is the focus of his attention as he skillfully hammers in nails. With each strike, his commitment to completing the task is evident, even though it falls outside his usual role. The peaceful countryside setting contrasts with the urban environment typically associated with his profession.]" }, { "from": "gpt", "value": "Normal. The character's face is distorted, hands are twisted, and the object in hand is also distorted." } ]
seed46_1474
videos/HRA_part2/1474.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, vibrant forest setting, a mother beaver tenderly caresses her kit with her large, front paw, both sitting cozily within their wooden lodge. The mother, with her brown fur and attentive gaze, gently strokes the smaller beaver, who looks up at her with wide eyes, creating a heartwarming scene of maternal love. The wooden lodge, intricately built from branches and mud, provides a safe and nurturing environment for the family, with green leaves and trees visible in the background, highlighting the beauty of their natural habitat.]" }, { "from": "gpt", "value": "Normal. Beaver's hand is twisted, and the face is distorted." } ]
seed46_272
videos/HRA_part2/272.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crisp uniform consisting of a navy shirt, badge, name tag, and matching pants, is seated on a step stool in a modern bathroom. The space is adorned with decorative tiles and features a gray sink cabinet with two drawers. The officer, hat removed, focuses intently on fixing a leaky faucet, demonstrating unexpected handyman skills amidst the bathroom's tidy environment. Tools are neatly spread across the countertop, including a wrench and screwdriver, as the officer leans into the task, sleeves rolled up to the elbows, revealing a tattoo on his right arm. The scene captures a moment of service beyond the call of duty, highlighting the officer's commitment to community care in a civilian's home.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_2038
videos/HRA_part0/2038.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars gracefully over a vast, shimmering ocean, its expansive wingspan casting a shadow on the water below. The bird's plumage, a stunning blend of white and dark feathers, contrasts beautifully against the blue sky. As it glides through the air, its sharp eyes scan the sea for signs of prey. In the background, the silhouette of an island can be seen, adding depth and scale to the scene. The albatross, a symbol of freedom and endurance, continues its flight, the wind gently ruffling its feathers, embodying the spirit of the open sea.]" }, { "from": "gpt", "value": "Bad. The albatross's wings in the video have generation issues, the claws were not generated, the face is blurry, and the body is deformed." } ]
seed46_1806
videos/HRA_part2/1806.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 enclosure, a majestic black panther sits calmly, its piercing eyes gazing intently. It gently caresses a log with its massive paw, adorned with thick, black fur and sharp claws. The panther's regal demeanor is underscored by its relaxed posture and the tender interaction with the wooden surface, set against a backdrop of lush vegetation and a water source, creating a serene atmosphere in the wild.]" }, { "from": "gpt", "value": "Normal. The black panther's movements in the video are basically normal, with slight inconsistency." } ]
seed42_2411
videos/HRA_part0/2411.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, grassy plains under a wide, clear blue sky, two small children, a boy and a girl, both wearing vibrant yellow raincoats and red boots, walk alongside a majestic bison. The bison, with its shaggy brown fur and large, powerful body, moves gracefully across the landscape, leading the children on an adventurous journey. The siblings follow closely, their expressions a mix of awe and delight, as they explore the wilderness together with their unlikely companion. The scene is peaceful, with the gentle swaying of tall grass and the distant silhouette of mountains framing the horizon.]" }, { "from": "gpt", "value": "Normal. The boy's walking action is uncoordinated, and his legs appear deformed. The buffalo's legs are deformed, and one leg is missing." } ]
seed46_2661
videos/HRA_part2/2661.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space hotel with large windows revealing the vast cosmos beyond, a lone gray wolf, wearing an orange collar with a glowing green tag, stands on its hind legs, using its front paws to wipe down a stainless steel countertop. The wolf's movements are deliberate and efficient, as if it has performed this task many times before. The space hotel interior is sleek and modern, with curved walls and soft, ambient lighting that casts a warm glow on the surfaces. Through the windows, stars twinkle in the distance, providing a stunning backdrop to the unusual scene of a wolf performing cleaning duties in zero gravity.]" }, { "from": "gpt", "value": "Bad. The gray wolf's movements in the video are not smooth." } ]
seed42_2642
videos/HRA_part0/2642.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hamster, with its distinctively furry cheeks and nose, energetically runs inside a clear plastic exercise ball. It scampers across a room filled with everyday objects like furniture and potted plants, providing a unique perspective on a typical living space. The hamster's movement is fluid and rapid, highlighting its determination and playful nature as it explores its surroundings within the safety of the transparent sphere.]" }, { "from": "gpt", "value": "Bad. The hamster's paws are missing in the video, and the body is slightly deformed." } ]
seed46_307
videos/HRA_part2/307.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a stark juxtaposition, a lone rhinoceros gallops across a barren landscape, its powerful form silhouetted against a backdrop of distant factories, their towering smokestacks reaching into the smoggy sky. The rhino's horn points forward determinedly as it runs, a symbol of resilience and strength in the face of industrial encroachment. Its muscular body strains against the weight of its own survival, each thundering step a testament to its enduring spirit. The factories, with their monolithic presence, stand as a reminder of the challenges faced by wildlife in an increasingly urbanized world. Yet, in this scene, the rhinoceros embodies a defiant hope, charging forward in a land where nature and industry collide.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_1893
videos/HRA_part1/1893.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, spacious room filled with smoke and vibrant lights, two individuals, a man in a dark green shirt and a woman in a black top, are dancing enthusiastically. Suddenly, they stop, looking startled as a beam of green light illuminates them. An alien creature, with large, expressive eyes and a smooth, gray skin tone, descends from above, capturing their attention. The extraterrestrial being, adorned with a metallic, futuristic outfit, lands gracefully beside them, prompting the humans to react with a mix of fear and curiosity. Despite the initial shock, the trio begins to move in unison, engaging in an otherworldly dance, creating a surreal and captivating scene.]" }, { "from": "gpt", "value": "Bad. The woman's face and hands, the man's face and hands, and the alien's hands and feet are generated abnormally, with sudden changes in the man's and woman's hands in the middle frames, and the alien's feet suddenly disappearing or appearing." } ]
seed46_1443
videos/HRA_part2/1443.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and surreal scene, a large, gray rhinoceros leaps into the air, defying expectations, with its powerful legs extended and body arched. This incredible moment is captured against a backdrop of a vast savanna landscape, dotted with trees and stretching to a distant horizon under a bright blue sky. The rhino, known for its heavy, armored skin and imposing horn, is shown mid-jump, creating a unique and unforgettable image that highlights the animal's unexpected agility and strength.]" }, { "from": "gpt", "value": "Bad. The rhino's leg generation in the video has issues with multiple limb generation." } ]
seed44_1294
videos/HRA_part1/1294.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_1990
videos/HRA_part2/1990.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a majestic raven perched on a branch, its glossy black feathers shimmering under the sunlight, revealing hints of blue and green. The bird has striking yellow eyes that seem to hold a world of wisdom. Its beak is curved and sharp, a testament to its carnivorous nature. The raven is surrounded by lush green foliage, and in the background, misty mountains add to the mystical atmosphere. Occasionally, the raven caws, a deep, resonant sound that echoes through the dense forest, asserting its presence in the serene wilderness.]" }, { "from": "gpt", "value": "Normal. The crow's beak in the video is generated unreasonably, and the crow's head becomes distorted." } ]
seed46_3054
videos/HRA_part2/3054.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a black beret, glasses, and a striped shirt, stands in a dimly lit studio with paintings in the background. He is engaged in an unexpected task, unclogging a drain, using a plunger on a white ceramic sink, with the focus on his expressive face and the effort exerted in this mundane activity. The contrast between his creative attire and the ordinary plumbing task creates a compelling narrative. Moments later, he pauses, revealing a look of determination as he continues his efforts to clear the clogged drain, the camera capturing his every detail in high definition.]" }, { "from": "gpt", "value": "Normal. The artist's face in the video is generated blurry, the fingers are deformed, and the plunger in hand is also deformed." } ]
seed44_3028
videos/HRA_part1/3028.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a brown beret, a beige button-down shirt, and glasses, sits at a wooden desk illuminated by a brass table lamp. He leans back in a brown chair, holding a book with an intense look of concentration. The room is adorned with his own artwork, including a large painting on an easel behind him and smaller framed pieces on the walls. Sunlight filters into the room from a window to the right, casting a warm glow on the artist and his surroundings as he reads. The artist's hands, which hold the book, are decorated with rings, adding a personal touch to the scene.]" }, { "from": "gpt", "value": "Normal. The artist's hands become deformed and move discontinuously when flipping through the book." } ]
seed44_2725
videos/HRA_part1/2725.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 urban alleyway, a middle-aged man wearing a worn-out brown jacket and blue jeans leans against a brick wall. He cradles a small rat in his hands, gently stroking it, while standing next to large, green dumpsters. The rat nestles in his palm, seemingly tamed and cared for, as the man looks down at it with a warm smile. Behind him, the bustling city streets are visible, with passersby and traffic lights, creating a contrast between the tenderness of the moment and the harshness of the urban environment.]" }, { "from": "gpt", "value": "Bad. The man's fingers in the video are deformed, the body is not generated, and the overall rat is deformed." } ]
seed44_2136
videos/HRA_part1/2136.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed character, resembling a panda with black-rimmed eyes and a friendly smile, walks down a bustling city street. Dressed in a full-body panda suit, they navigate the urban landscape, passing by pedestrians and city structures. The panda mascot's outfit includes large, padded paws and a fuzzy, rounded silhouette, adding to the whimsical nature of the scene. As they stroll, the surrounding environment, filled with buildings and people going about their day, contrasts with the playful presence of the panda.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_1569
videos/HRA_part1/1569.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dingo, exhibiting a lean build and a reddish-brown coat, walks purposefully across a barren, rocky terrain under an overcast sky, highlighting its wild nature. It pauses briefly, standing alert with its ears forward, before continuing its journey. The dingo's movement is deliberate, showcasing its survival instincts in the vast, arid landscape, where sparse vegetation and distant mountains provide a stark, natural setting.]" }, { "from": "gpt", "value": "Bad. The dog in the video walks very unsmoothly." } ]
seed44_1078
videos/HRA_part1/1078.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, dressed in a dark green shirt and black jeans, is seen wiping perspiration from his brow with a red bandana, standing amidst a lush orchard filled with apple trees bearing ripe fruit. The scene is set during a sunny day, with the musician's weathered guitar leaning against a tree trunk, strings glistening under the golden afternoon light. In another shot, he wipes his hands on his jeans, perhaps after having picked some apples, his face reflecting a sense of peace and contentment among the bountiful orchard surroundings.]" }, { "from": "gpt", "value": "Bad. The guitar size in the video is abnormal, and the character's hand proportions are not harmonious." } ]
seed46_3084
videos/HRA_part2/3084.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, wearing a traditional white chef's uniform and black pants, stands outdoors in a garden, holding a shovel. He is surrounded by various plants, including leafy greens, carrots, and herbs like rosemary, thyme, and sage. The chef has short brown hair and a neatly trimmed beard, and he is digging into the rich soil with determination, perhaps searching for fresh ingredients for his culinary creations. The scene is set against a backdrop of wooden crates and greenery, with a hint of sunlight filtering through the trees, casting dappled shadows on the chef and his gardening endeavor.]" }, { "from": "gpt", "value": "Bad. The chef's hand and the spatula in his hand are generated abnormally." } ]
seed42_2143
videos/HRA_part0/2143.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crystal-clear waters, a vibrant butterfly fish, marked by striking black, yellow, and white patterns, gracefully hovers near a coral reef bustling with life. Sunlight filters through the water, casting a warm glow on the fish and its surroundings. The butterfly fish, known for its intricate design featuring a bold black stripe through the eye and a false eye spot on its tail, explores the nooks and crannies of the reef. It flutters among the corals, which are home to various sea creatures, adding to the dynamic underwater scene. Against this rich backdrop, the butterfly fish's fluid movements and striking colors stand out, creating a captivating display of marine beauty.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1474
videos/HRA_part0/1474.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, vibrant forest setting, a mother beaver tenderly caresses her kit with her large, front paw, both sitting cozily within their wooden lodge. The mother, with her brown fur and attentive gaze, gently strokes the smaller beaver, who looks up at her with wide eyes, creating a heartwarming scene of maternal love. The wooden lodge, intricately built from branches and mud, provides a safe and nurturing environment for the family, with green leaves and trees visible in the background, highlighting the beauty of their natural habitat.]" }, { "from": "gpt", "value": "Normal. Beaver's hand is twisted, and the face is distorted." } ]
seed44_2169
videos/HRA_part1/2169.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, fluffy gray mouse walks along the edge of a weathered wooden table, its tiny feet making delicate movements against the grainy surface. The mouse pauses momentarily, its whiskers twitching as it senses the environment, before continuing its journey. Its round ears and curious demeanor are highlighted as it explores the tabletop landscape, framed by a blurred background that suggests a rustic interior setting. Throughout the scene, the mouse's agile movements and cautious behavior are captured in detail, providing a close-up view of its natural actions.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_3091
videos/HRA_part1/3091.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man sits at a desk, bathed in the warm glow of a table lamp, surrounded by books and papers. He is wearing a gray t-shirt and dark glasses, and has a full beard. He yawns widely, stretching his arms above his head, showing signs of fatigue. His computer screen reflects the light, partially obscuring his face, as he leans back in his chair, the room's atmosphere conveying a sense of late-night writing and contemplation.]" }, { "from": "gpt", "value": "Normal. The video does not generate a computer screen." } ]
seed44_2743
videos/HRA_part1/2743.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, equipped with a backpack, ascends a lush, green mountain trail, pausing occasionally to jot down thoughts in a small notebook. He wears a gray t-shirt, brown shorts, and sturdy hiking boots, while his glasses reflect the sunlight as he looks up at the dense forest canopy above. With a determined look, he continues climbing, passing by a wooden signpost indicating various trails. At one point, he stops to admire the view, taking in the breathtaking scenery of rolling hills and distant mountains, before resuming his upward journey, the camera capturing the vivid colors of nature surrounding him.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed42_1908
videos/HRA_part0/1908.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek black panther crawls across a dry, cracked earth surface under a dense jungle canopy, its muscles rippling beneath glossy fur. The panther's piercing yellow eyes remain fixed on a distant target, conveying intense focus and determination. It moves slowly and deliberately, each paw carefully placed to ensure silent progression, embodying the essence of stealth and power in the heart of the wild.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2729
videos/HRA_part2/2729.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful woman with curly brown hair and glasses laughs heartily, holding a green apple in her right hand. Dressed in a mustard yellow turtleneck sweater, she sits in front of a rustic wooden wall, her joyful demeanor brightening the cozy setting. Her laughter is contagious, spreading warmth and happiness in the intimate space, where natural light filters in from above, illuminating her face and emphasizing her genuine delight.]" }, { "from": "gpt", "value": "Normal. The woman's fingers in the video have generation issues, her eyes are generated blurry, and her mouth is generated too large." } ]
seed44_2827
videos/HRA_part1/2827.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, donning a white hazmat suit with a respirator mask, meticulously paints the walls of a spacious, well-lit room with vibrant orange strokes, capturing the essence of transformation. His attire, complete with protective goggles and gloves, underscores the precision and safety measures involved in the task. The room, initially a blank canvas, gradually comes alive with color, highlighting the engineer's skill and attention to detail as he revitalizes the space.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed44_2479
videos/HRA_part1/2479.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah leaps gracefully over a low branch in a sun-dappled savanna, its body stretched in mid-air, showcasing its remarkable agility and strength. The big cat's spotted coat glistens under the warm sunlight, every muscle taut and defined as it propels itself upward. The surrounding landscape is filled with lush grasses and scattered acacia trees, providing a vivid contrast to the cheetah's dynamic movement. In the background, the horizon stretches far into the distance, marked by a hazy skyline and the promise of endless space, highlighting the cheetah's natural habitat and freedom.]" }, { "from": "gpt", "value": "Bad. The cheetah's limbs are missing in the video, the facial features are not fully generated, and there are issues with the tail." } ]
seed42_1380
videos/HRA_part0/1380.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ruggedly handsome actor, sporting a full beard, stands in a rural setting under an overcast sky, gently caressing a brown horse with white markings. He wears a gray shirt, blue jeans, and a brown belt, while the horse stands placidly in a grassy area dotted with small trees. The actor's affectionate interaction with the animal conveys a sense of peace and connection in the pastoral environment. The horse, with its mane and tail blowing slightly in the wind, is clearly comfortable with the actor, who continues to stroke its neck with tenderness and respect.]" }, { "from": "gpt", "value": "Normal. The person's movements while petting the horse in the video are not very smooth and coordinated." } ]
seed44_1994
videos/HRA_part1/1994.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged female nurse sits on a wooden chair in a cozy, softly lit room, wearing a light blue scrubs top and black pants. She crochets a vibrant, multicolored blanket with yellow, orange, and red hues, her hands moving skillfully as she focuses on her craft. The room is filled with the warm glow of a standing lamp, casting a gentle light on the scene. Behind her, a large window reveals a lush, green outdoor landscape, providing a serene backdrop for her meditative activity.]" }, { "from": "gpt", "value": "Bad. The person's arm is twisted, the hand is twisted, and the face is slightly distorted." } ]
seed46_1342
videos/HRA_part2/1342.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man wearing a yellow safety vest, blue jeans, and work gloves is seen from a low angle, balancing on a ladder as he scoops wet leaves out of the clogged gutters. The camera pans to show the man, his face intent and focused, tossing the debris onto the grass below. His movements are deliberate and efficient, showcasing his experience in this task. The scene is set against a backdrop of a suburban house with a red roof, emphasizing the routine nature of home maintenance. As the man continues his work, the afternoon sunlight highlights the water and leaves cascading down from the gutters, capturing the essence of a fall day.]" }, { "from": "gpt", "value": "Normal. The character's face is distorted, and the hands are twisted." } ]
seed42_1643
videos/HRA_part0/1643.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic European ring-necked pheasant, with its vibrant plumage featuring striking shades of green, gold, and brown, struts confidently across a grassy field. Its iridescent feathers shimmer in the sunlight, accentuated by the lush green vegetation in the background. The pheasant pauses, its head held high, showcasing the distinctive white collar around its neck and the bold red wattles near its eyes. It then resumes its stately walk, tail feathers fanning out gracefully, embodying the elegance and beauty of nature.]" }, { "from": "gpt", "value": "Bad. The pheasant in the video has multiple legs generated, and some facial features are missing during playback." } ]
seed44_1721
videos/HRA_part1/1721.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear, including a red coat, yellow reflective strips, and a helmet, dances energetically on a busy Shanghai street. The urban landscape, featuring modern skyscrapers and bustling city life, provides a stark contrast to his joyful movements. Pedestrians and traffic, including cars and a bus, surround him, highlighting the unexpected nature of his dance. Despite the urban chaos, he moves freely, a bright spot in the gray cityscape, his figure standing out against the backdrop of tall buildings and moving vehicles.]" }, { "from": "gpt", "value": "Bad. The firefighter's dance moves in the video are not smooth and continuous, with sudden changes in the limbs of the firefighter in between frames." } ]
seed46_2979
videos/HRA_part2/2979.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a gray suit with a white shirt underneath, stands in an industrial mine setting, gently caressing the rough texture of a mining wall. The scene is lit dramatically, highlighting the contrast between the lawyer's polished appearance and the gritty environment. The lawyer's face expresses a mix of determination and contemplation, while the mine's machinery and tools are visible in the background, emphasizing the unusual context of this legal interaction.]" }, { "from": "gpt", "value": "Bad. The lawyer's fingers and eyes in the video have generation issues." } ]
seed44_2085
videos/HRA_part1/2085.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sprightly beaver, donning a brown coat, scurries across a lush, green meadow under a partly cloudy sky. It dashes over the grass with its front paws lifted, revealing a clear view of its full body. Moments later, it continues its run, tail held high, near a wooden fence. The scene shifts to the beaver running alongside a tranquil stream, with trees in the background, showcasing its natural habitat. Lastly, it sprints with determination, its distinctive flat tail visible as it moves through its verdant environment.]" }, { "from": "gpt", "value": "Good. Basically no issues." } ]
seed42_186
videos/HRA_part0/186.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A group of cheerful children, ranging from toddlers to preteens, are engaged in the task of cleaning windows on a bright, sunny day. They wear casual clothes, including t-shirts, shorts, and sneakers, and sport various hairstyles, from pigtails to afros. The kids use squeegees and rags to wipe down the glass, leaving streaks of water and soap behind. They work together, laughing and chatting, as they tackle the large window panes of a suburban home, with lush greenery visible through the transparent surfaces. The atmosphere is one of teamwork and fun, with the youngsters taking pride in their chores under the warm glow of the sun.]" }, { "from": "gpt", "value": "Bad. The child's arm has become deformed and mutated. The face has become distorted and deformed." } ]
seed42_1732
videos/HRA_part0/1732.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 flat, wide flounder fish is seen lying motionless on a clean, white surface, its right eye gazing upwards, while the left side of its body, which lacks an eye, is pressed against the surface. The fish has a natural sandy-brown color with darker mottled spots, giving it a realistic appearance. Its texture is depicted with fine, realistic details, emphasizing the flatness and unique form of the flounder species. The setting is minimalistic, focusing solely on the fish against the pristine white background, allowing for a clear and unobstructed view of the subject.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2199
videos/HRA_part0/2199.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 porcupine, with its distinctive quills standing out, is seen in a detailed close-up, wiping its face with a paw in a natural habitat, perhaps after eating or sensing its surroundings. The camera captures the intricate details of the porcupine's quills, the texture of its fur, and the precise movements of its paw as it carefully wipes across its face, all set against a backdrop of lush greenery, indicating a serene and undisturbed environment.]" }, { "from": "gpt", "value": "Bad. The video shows a missing part in the generation of the porcupine's mouth." } ]
seed44_1192
videos/HRA_part1/1192.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, dressed in a gray jacket and blue jeans, is seen crawling on the floor of a large, echoing space, perhaps a warehouse or a vast indoor market filled with various shops. His attention is riveted on an elephant figurine, intricately crafted and positioned nearby. The camera angle shifts to reveal the expansive ceiling and the bustling activity of shoppers in the background, adding a sense of scale and life to the composition. This juxtaposition of the focused janitor, the detailed elephant sculpture, and the lively shopping environment creates a captivating visual narrative.]" }, { "from": "gpt", "value": "Bad. The cleaner's crawling movements on the floor in the video are not smooth and the actions are uncoordinated." } ]
seed46_1158
videos/HRA_part2/1158.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant village nestled near a lush watering hole, a tall giraffe gracefully bends its neck to drink, its spots blending harmoniously with the African landscape. Nearby, village life unfolds, with women carrying water pots on their heads, children playing under the watchful gaze of elders, and men engaged in lively conversations. Suddenly, a group of young boys leap into the refreshing waters, their joyful splashes contrasting with the calm surroundings. The scene is completed by a close-up of a giraffe's face, its large eyes and curious expression capturing the essence of this serene environment.]" }, { "from": "gpt", "value": "Bad. The character's arm is twisted, the hand is distorted, the face is distorted, the giraffe's body is deformed and has two necks." } ]
seed44_1398
videos/HRA_part1/1398.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with curly brown hair tied back in a ponytail and wearing a red apron over a casual outfit stands in a modern kitchen, illuminated by bright overhead lights. She focuses intently on slicing a red bell pepper on a white cutting board, her silver ring catching the light. Next, she stirs a sizzling pan of vegetables on a stainless steel stove, steam rising from the pan. Then, she adds a pinch of salt and a sprinkle of fresh herbs to the dish, enhancing its aroma. Finally, she smiles as she plates the finished meal, garnishing it with a sprig of parsley, ready to serve a delicious dinner.]" }, { "from": "gpt", "value": "Normal. The video does not show the woman's action of adding a pinch of salt to the dish." } ]
seed46_2576
videos/HRA_part2/2576.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a casual outfit of a gray hoodie and blue jeans, diligently cleans a large window in a modern building, surrounded by other windows. The natural light from outside illuminates the space, casting a warm glow on the young cleaner. The scene is set in a minimalist room with white walls and hardwood floors, adding to the clean aesthetic. The student, with a focused look on their face, uses a squeegee and a bucket of soapy water to ensure every inch of the glass is spotless, reflecting their commitment to the task at hand.]" }, { "from": "gpt", "value": "Normal. The man's legs are missing in the video, there is a lack of finger generation, and the arms and tools in his hands are deformed." } ]
seed44_118
videos/HRA_part1/118.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a yellow raincoat walks alongside a capybara on a leash through a gritty urban landscape, factories looming in the background, emitting plumes of smoke into the overcast sky. They navigate past industrial structures, the woman's yellow attire contrasting with the gray surroundings, while the capybara trots obediently beside her. The scene focuses on their bond, with the capybara occasionally looking up at its companion, as they stroll past the towering factories, emphasizing their unusual partnership amidst the industrial setting.]" }, { "from": "gpt", "value": "Bad. The generation of the character's face and hands in the video, along with the capybara's paws, is problematic, with the capybara's paws suddenly disappearing or appearing in middle frames." } ]
seed46_2351
videos/HRA_part2/2351.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt and black trousers, serves a coyote who is seated at a wooden table set among the lush greenery of the woodlands. The coyote, looking surprisingly refined with a napkin tucked into its collar, enjoys a meal as if dining at a fine restaurant. Behind them, a natural pool glistens under the sunlight, inviting a sense of tranquility and relaxation, contrasting the unexpected yet harmonious interaction between the waiter and the wild coyote.]" }, { "from": "gpt", "value": "Normal. The server's movements in the video are not smooth." } ]
seed44_2233
videos/HRA_part1/2233.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, young female musician dons a futuristic silver outfit, complete with a matching helmet, as she energetically performs a dynamic concert on a space station. Surrounded by the vast cosmos, she passionately sings into her microphone, her movements lively and engaging. In a captivating display, she effortlessly sprints across the zero-gravity stage, her silver suit shimmering under the cosmic lights, while continuing to captivate the audience with her powerful voice and electrifying performance. The space station's advanced technology enhances the concert experience, creating an unforgettable spectacle set against the backdrop of the infinite universe.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth and are uncoordinated." } ]
seed46_2388
videos/HRA_part2/2388.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded chef, donning a red baseball cap, a gray t-shirt, and green apron over his attire, is seen energetically cleaning a car in a vibrant, sunny setting. He begins by rinsing the vehicle with a hose, water spraying from the nozzle. Then, he proceeds to wash the car using a large sponge, applying soapy suds to its surface. Next, he uses a squeegee to remove excess water, ensuring a streak-free finish. Lastly, he dries the car with microfiber towels, his movements demonstrating thoroughness and care, all while maintaining his lively demeanor.]" }, { "from": "gpt", "value": "Bad. The character's movements are not smooth." } ]
seed44_2710
videos/HRA_part1/2710.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling Colin Farrell, is seen walking through a dense forest with tall trees, wearing a brown jacket, jeans, and boots. Suddenly, the scene changes to reveal a prehistoric setting, where the actor now finds himself casually strolling beside a woolly mammoth. Both the actor and the mammoth continue their leisurely walk together, with the mammoth's massive frame towering over the actor, who appears unfazed by the extraordinary situation. They meander through the ancient landscape, surrounded by lush vegetation and underbrush, creating a surreal juxtaposition of eras and species.]" }, { "from": "gpt", "value": "Bad. The actor's facial features in the video are blurry, fingers are distorted, and the woolly mammoth's head is abnormally generated." } ]
seed42_1810
videos/HRA_part0/1810.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrial engineer in a gray shirt and khaki pants stands confidently in a modern factory, surrounded by large machinery and pipes, with a swimming pool visible through a window in the background. He then walks purposefully toward the camera, passing by the heavy industrial equipment, with the pool still visible in the distance. Next, he is seen from behind, approaching a large machine with pipes, while the pool can be glimpsed outside through the window. Finally, the engineer takes a break from his work, enjoying a refreshing swim in the outdoor pool, which is now the focal point, set against the backdrop of the industrial facility.]" }, { "from": "gpt", "value": "Normal. Basically no problem, the man's hand is slightly deformed." } ]
seed44_1608
videos/HRA_part1/1608.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature, bespectacled teacher, wearing a gray blazer over a button-down shirt, walks down a dimly lit, empty hallway with lockers on either side. Suddenly, a small brown rat scurries across the floor in front of him, causing the teacher to pause and look down with a mix of surprise and curiosity. The rodent continues its journey undeterred, disappearing around a corner as the teacher resumes his walk, now with a slight smile and a shake of his head, as if amused by the unexpected encounter.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_1017
videos/HRA_part0/1017.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, upscale restaurant filled with the clinking of glasses and chatter, a waiter in a crisp, black uniform expertly navigates the lively dining room. He deftly pushes a polished, stainless steel service cart laden with fine china and gleaming silverware, carefully avoiding any contact with the patrons enjoying their meals. The elegant space, adorned with hanging lights casting a warm glow and walls decorated with framed artwork, provides a sophisticated setting for this scene of seamless service execution.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_1350
videos/HRA_part1/1350.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, with its distinct black and white striped face and grey fur, walks purposefully across a lush, green meadow under the dappled shade of tall trees. It pauses for a moment, standing on all fours, to sniff the air with its keen sense of smell. Then, it continues its journey, moving with a slight waddle due to its sturdy build, leaving behind a trail in the soft grass. The scene is set in the peaceful serenity of nature, with the badger as the sole focus, highlighting its natural habitat and behavior.]" }, { "from": "gpt", "value": "Normal. The facial proportions of the badger in the video are not quite right, and an extra paw suddenly appears on the badger in the middle frame." } ]
seed44_2941
videos/HRA_part1/2941.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman in a khaki safari outfit gently caresses the muzzle of a rhinoceros, standing on wooden docks overlooking a tranquil lake. The woman, wearing a wide-brimmed hat and a satisfied smile, connects with the rhino, which has a textured hide and a horn. Both are framed by lush greenery and set against a backdrop of serene water, creating a harmonious scene of human-animal interaction. The woman's affectionate touch and the rhino's calm demeanor, along with the peaceful lake in the background, evoke a sense of mutual respect and tranquility.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_1283
videos/HRA_part2/1283.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in casual attire, consisting of a gray t-shirt, dark pants, and brown shoes, stands on a green ladder propped against a brown house, engaged in the task of cleaning the rain gutters. He holds a white bucket in his right hand and uses his left hand to scoop out debris from the gutter. The scene is set against a clear blue sky and lush green foliage, with the man's focused expression and determined posture highlighting his commitment to completing the job. The house's exterior, featuring beige siding and brown trim, provides a backdrop for the man's efforts, emphasizing the domestic nature of the activity.]" }, { "from": "gpt", "value": "Normal. No brown shoes were generated, and the ladder is not leaning against the house." } ]
seed46_2866
videos/HRA_part2/2866.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badge and name tag, black tactical vest, and duty belt adorned with various gear, is seen dancing joyously on a wooden deck. In his right hand, he holds a small hedgehog, which is safe and secure in a clear plastic container with air holes. The hedgehog, with its distinctively spiky quills and curious demeanor, peers out from within the container. Behind the officer, a lush garden with green hedges and vibrant flowers provides a lively backdrop, enhancing the whimsical atmosphere of the scene.]" }, { "from": "gpt", "value": "Bad. The video shows the police officer dancing, but the movements are not clear and there is a lack of coordination." } ]
seed44_1121
videos/HRA_part1/1121.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a khaki safari outfit, is seen in a lush, green jungle environment, carefully cleaning a majestic tiger with a large cloth. The tiger, displaying distinctive orange stripes on a white underbelly, remains calm and cooperative during the process. The director, showing respect and gentleness, focuses intently on wiping the tiger, highlighting a unique bond between human and animal in a wild setting.]" }, { "from": "gpt", "value": "Bad. The director's movements while cleaning the tiger in the video are very unsmooth and uncoordinated." } ]
seed46_247
videos/HRA_part2/247.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 hermit crab, adorned with a vibrant red and orange color palette, scuttles along a sandy shore. Its intricate, spiraled shell provides a stark contrast against the muted tones of the beach. The crab's two large, front claws grasp onto the shell's edge as it moves, showcasing its unique adaptation for survival. The sandy background is dotted with small rocks and bits of seaweed, adding texture to the scene. The sky above is a clear, vivid blue, highlighting the rich colors of the hermit crab as it navigates its coastal habitat.]" }, { "from": "gpt", "value": "Normal. The hermit crab's legs are twisted in the video." } ]
seed46_1664
videos/HRA_part2/1664.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 market filled with vibrant stalls and the sounds of commerce, a young male cashier, dressed in a blue button-down shirt and khaki pants, walks purposefully across the busy floor. He carries a green plastic bag, possibly containing produce or goods, adding a touch of realism to the scene. The market is alive with activity, from the colorful array of fruits and vegetables on display to the lively chatter of customers and vendors. The cashier navigates this energetic environment, his journey through the market captured in a series of dynamic shots that convey the lively atmosphere.]" }, { "from": "gpt", "value": "Normal. The person's left arm is slightly deformed." } ]
seed42_1867
videos/HRA_part0/1867.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, wearing a khaki safari outfit complete with a vest, pants, and hat, walks alongside a capybara on a leash. They are strolling on a concrete path that winds through a lush, green landscape filled with trees and shrubs. The capybara, the world's largest rodent, is shown in profile, moving at a relaxed pace beside the human. The setting is a serene, outdoor environment, possibly within a zoo or wildlife sanctuary, where the two amble together in a scene that highlights the unique bond between the caretaker and the animal.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_1255
videos/HRA_part1/1255.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal space setting filled with stars and galaxies, a beautifully dressed couple exchanges vows during an extraordinary wedding ceremony. A majestic gazelle, adorned with a golden collar and standing on a floating platform nearby, watches the event with calm interest. The bride, in a flowing white gown, and the groom, in a tailored black suit, hold hands tenderly, their faces reflecting deep love and commitment. As they caress each other's faces, the gazelle gently nuzzles the bride's arm, adding a touch of magic and wonder to this celestial union.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed46_2949
videos/HRA_part2/2949.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning full gear and a helmet, takes a break from his usual duties to engage in a surprising hobby: gardening. He carefully plants flowers in a small garden plot, surrounded by a wooden fence, with a bright red firetruck visible in the background. His gloved hands, typically used to handle hoses and axes, now delicately place marigolds into the soil. The juxtaposition of his robust firefighting attire and the delicate act of gardening creates a unique and compelling visual narrative.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_1339
videos/HRA_part2/1339.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a muscular build, wearing a white sleeveless undershirt and dark gray jeans, stands on a wooden platform, intently applying paint to a large canvas with a brush. The focus is on his hands, which are covered in paint, as they skillfully create an abstract artwork. Behind him, a row of neatly arranged paint cans sits on a wooden floor, and the walls of the studio are painted white, creating a clean, professional environment. The artist's concentration is evident in his furrowed brow and the intensity of his gaze, while the vibrant colors on the canvas contrast with the neutral tones of his clothing and surroundings.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed42_1154
videos/HRA_part0/1154.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, dressed in a black vest and white shirt, walks purposefully through a series of art galleries, each filled with unique paintings and sculptures. He carries a small, white tray with two wine glasses, moving from one gallery to another, passing by various artworks. In the first gallery, he walks past a large, abstract painting in red and yellow tones. In the second, he strolls by a modern sculpture, and in the third, he passes under a chandelier, all while maintaining a focused demeanor, showcasing the dynamic interplay between service and art.]" }, { "from": "gpt", "value": "Normal. The waiter in the video walks basically normally, with slightly uncoordinated movements." } ]
seed46_2362
videos/HRA_part2/2362.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative writer, dressed in a casual blue jacket and khaki pants, leaps joyfully in slow motion over the sandy shore near a vast ocean, capturing the essence of freedom and inspiration. Against a backdrop of the sea's horizon, the writer's silhouette is outlined dramatically during the jump, with the sun illuminating the scene from behind. The figure is then shown landing softly on the sand, surrounded by the serene beauty of the ocean, embodying a moment of pure bliss and connection with nature. Throughout, the writer's attire remains consistent, with the focus on the expressive leap and the stunning coastal scenery.]" }, { "from": "gpt", "value": "Bad. The man's jump in the video is very unsmooth, and his movements are uncoordinated." } ]
seed44_141
videos/HRA_part1/141.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy room filled with natural light, two young children sit cross-legged on a wooden floor, engrossed in crocheting a vibrant blanket. One child, wearing a yellow T-shirt and denim shorts, focuses intently on their work, their tongue slightly protruding in concentration. The other, dressed in a pink sweater and khaki pants, looks up momentarily, a smile playing on their lips, before returning to the colorful yarn in their hands. The atmosphere is warm and inviting, with the half-finished blanket spreading across their laps, a testament to their patience and creativity. Beside them, a basket of yarn in various shades adds a touch of whimsy to the scene, as the children continue to crochet, their movements steady and practiced.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_1867
videos/HRA_part1/1867.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, wearing a khaki safari outfit complete with a vest, pants, and hat, walks alongside a capybara on a leash. They are strolling on a concrete path that winds through a lush, green landscape filled with trees and shrubs. The capybara, the world's largest rodent, is shown in profile, moving at a relaxed pace beside the human. The setting is a serene, outdoor environment, possibly within a zoo or wildlife sanctuary, where the two amble together in a scene that highlights the unique bond between the caretaker and the animal.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_1813
videos/HRA_part2/1813.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and khaki pants, stands in the midst of a vast desert landscape, the golden sand stretching to the horizon under a clear blue sky. Holding a paintbrush in one hand, he wipes it across a large canvas, which rests on an easel, revealing strokes of orange and yellow that mirror the fiery sunset in the background. The artist's face is intense, his eyes fixed on the canvas as he captures the essence of the desert's beauty, with the sun's last rays casting long shadows across the dunes.]" }, { "from": "gpt", "value": "Bad. The man's fingers in the video are not fully generated, and his face is blurry." } ]
seed42_31
videos/HRA_part0/31.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pufferfish, round and plump, navigates the vibrant coral reef with its intricate patterns and varied marine life, showcasing the wonders of the underwater world. Its body, inflated to twice its normal size, displays a mesmerizing display of geometric shapes in muted tones against the backdrop of the deep blue sea. The fish's small, beady eyes stand out prominently on its distended form, while its fins propel it gracefully through the water, surrounded by an array of colorful corals and other sea creatures. This underwater scene highlights the unique survival mechanism of the pufferfish in its natural habitat.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_2080
videos/HRA_part1/2080.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two children, a boy and a girl, both dressed in green, are dancing gleefully in a grassy meadow filled with dandelions. They perform a choreographed routine, spinning and leaping with joyful abandon. Suddenly, a vole emerges from the tall grass, peeking curiously at the dancers. Unfazed, the children continue their dance, now incorporating playful gestures towards the small mammal. The vole watches from a safe distance, its presence adding a touch of natural charm to the lively scene. Throughout the dance, the children's outfits, consisting of green shirts and khaki shorts, stand out against the lush greenery of the meadow, creating a vibrant and engaging visual experience.]" }, { "from": "gpt", "value": "Bad. The dance moves of the children in the video are not continuous, with abrupt changes." } ]
seed42_1236
videos/HRA_part0/1236.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clean-shaven actor with short brown hair and wearing a black turtleneck sweater and gray blazer is seen in a dimly lit room. He gently caresses a small bat, which rests calmly on his hand, demonstrating a tender interaction between man and animal. The bat, with its leathery wings folded, seems comfortable in his presence, creating a unique and intimate scene. The actor's other hand, adorned with a watch, occasionally enters the frame, adding to the personal nature of the moment. Throughout the video, the focus remains on the actor's face and the bat, capturing the essence of their connection in a softly lit environment.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2656
videos/HRA_part0/2656.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green shirt and beige cargo pants, stands on set with a megaphone in hand, coordinating the action. Nearby, a majestic tiger leaps gracefully over a log, its muscles rippling and eyes intense, demonstrating the power and agility of the big cat. The scene is set in a lush, verdant forest, with sunlight filtering through the leaves, creating a dramatic interplay of light and shadow. The director's focused gaze and the tiger's dynamic leap are captured in high definition, highlighting the intensity and precision required for filming such a scene.]" }, { "from": "gpt", "value": "Bad. The video shows the tiger jumping over a fallen log, but the movements are not continuous and smooth, showing some lack of coordination." } ]
seed44_1785
videos/HRA_part1/1785.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, wearing a casual gray shirt, is captured in high definition as he dances alone on a vast, luxurious resort balcony. The setting sun illuminates the horizon, casting a warm glow on the scene. He moves gracefully, his body language expressing pure joy and freedom. In the background, a sprawling, upscale resort with numerous balconies and lush greenery can be seen, highlighting the exotic location. The actor's movements are fluid and expressive, conveying the essence of a carefree spirit embracing the beauty of his surroundings.]" }, { "from": "gpt", "value": "Bad. The male actor's dancing in the video is very unsmooth, and his movements are not coordinated." } ]
seed42_3023
videos/HRA_part0/3023.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a dark blue jacket over a gray shirt, and gray pants, stands in a taiga landscape marked by tall coniferous trees and a dense undergrowth of shrubs. Holding a towel in his right hand, he wipes his face, perhaps after a long day of work or physical exertion. The scene is set against the backdrop of the taiga, with the engineer's attire standing out against the natural greens and browns of the forest environment. The act of wiping his face with the towel conveys a sense of relief and respite in the midst of the rugged wilderness.]" }, { "from": "gpt", "value": "Bad. The engineer's action of wiping his face with a towel in the video is not smooth." } ]
seed42_2967
videos/HRA_part0/2967.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lark soars gracefully across a vast, cloud-dappled sky, its russet and brown plumage shimmering in the sunlight. It sings a jubilant melody, filling the air with its clear, melodious notes. The bird then descends into a lush, green meadow dotted with vibrant wildflowers, where it lands softly on a swaying stalk of grass. Its bright eyes scan the surroundings, alert and curious, before taking flight again, its song echoing through the peaceful landscape.]" }, { "from": "gpt", "value": "Normal. The bird's movements in the video are not smooth." } ]
seed46_1303
videos/HRA_part2/1303.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 North American porcupine, distinguished by its brown and white quills, runs through a dense forest environment, navigating between moss-covered trees. The porcupine, with its quills standing out prominently, dashes across the screen from right to left, showcasing its agility. Its facial features, including small eyes and a pointed nose, are clearly visible as it moves quickly, demonstrating the animal's unexpected speed and grace in its natural habitat.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2564
videos/HRA_part0/2564.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in a dark blue shirt and wearing glasses, sits at a desk cluttered with books and papers, engrossed in typing on a laptop. Suddenly, a dazzling, intense white hole explosion occurs behind him, wiping out everything in its path except for the writer and his desk, which remain untouched. The force of the explosion is so powerful that it erases the background, leaving only a blinding white light. Despite the chaos unfolding behind him, the writer remains undisturbed, continuing to type away, seemingly oblivious to the cosmic event taking place just feet away.]" }, { "from": "gpt", "value": "Bad. The explosion happened out of nowhere, which is unrealistic." } ]
seed44_1749
videos/HRA_part1/1749.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a white lab coat over a black turtleneck and black pants, runs down a sleek, futuristic corridor of a space medical facility. The hallway is lined with glass panels that offer glimpses into advanced treatment rooms. The artist's stride is purposeful, their gaze determined, as they navigate the sterile environment illuminated by soft, ambient lighting. The facility's design incorporates curved walls and high-tech equipment, creating a blend of artistry and cutting-edge medicine in the vastness of space.]" }, { "from": "gpt", "value": "Bad. The artist's running motion in the video is uncoordinated." } ]
seed44_3081
videos/HRA_part1/3081.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 contemporary art gallery with high ceilings and modern architecture, a janitor wearing a dark green vest, khaki pants, and a name tag, meticulously sweeps the floor. In an unexpected scene, he gently caresses a small vole that has wandered into the gallery, showing a tender side amidst the sterile environment filled with abstract paintings and sculptures. The interaction between the janitor and the vole adds a touch of warmth and humanity to the otherwise cold and impersonal space.]" }, { "from": "gpt", "value": "Bad. No scenes of generating hamsters or the cleaner petting the hamsters." } ]
seed46_1022
videos/HRA_part2/1022.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 young, cheerful female nurse walks briskly down a hospital corridor, her blonde hair tied back in a neat bun. She wears a sky-blue uniform, gray tights, and white shoes. A stethoscope hangs around her neck, and she carries a clipboard in her right hand. The hallway is brightly lit, with a green floor and doors lining either side. The nurse's confident stride and professional attire convey a sense of purpose and dedication to her duties within the healthcare facility.]" }, { "from": "gpt", "value": "Good. No obvious disharmony." } ]
seed46_2490
videos/HRA_part2/2490.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, covered in dark fur with lighter features around its eyes and mouth, runs across a grassy terrain under a vibrant blue sky. The chimp's movement is powerful and agile, with a hunched posture typical of its species. Its face, marked with distinctive wrinkles and a noseless structure, conveys intense focus as it sprints. In another moment, the chimpanzee is shown from a side view, highlighting its muscular build and the gracefulness of its stride, set against the backdrop of a lush, green environment.]" }, { "from": "gpt", "value": "Bad. The black gorilla's movements in the video are not smooth." } ]
seed44_1962
videos/HRA_part1/1962.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two young children, a boy and a girl, both wearing red jackets, are seen walking together with a realistic, animated beaver on a wooden path in a park during daytime. The beaver, positioned between the children, is slightly ahead, leading the way as if guiding them, while the girl looks down at it with a smile. The trio continues walking on the wooden trail, surrounded by lush greenery, with the beaver still in the lead, its bushy tail swaying side-to-side, and the children following closely behind, engaged in a joyful outdoor adventure.]" }, { "from": "gpt", "value": "Bad. Missing another child." } ]
seed42_1344
videos/HRA_part0/1344.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, drenched in water, swims across a serene lake, its eyes fixed ahead with unwavering determination. The wolf's powerful legs propel it forward through the crystal-clear water, while its sleek fur glistens under the soft, diffused sunlight filtering through the overcast sky. The surrounding lush forest provides a verdant contrast to the tranquil body of water, and in the distance, snow-capped mountains rise majestically, completing the breathtaking natural landscape.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2421
videos/HRA_part2/2421.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate female teacher, wearing a green sweater and brown hair, gently caresses a large leaf from a temperate rainforest tree during an educational field trip, her face expressing wonder and reverence for nature. Moments later, she holds a branch from a temperate rainforest, engagingly teaching her attentive students about the ecosystem. Then, she lovingly touches a moss-covered log, her actions conveying the importance of the rainforest environment, with the students looking on. Finally, she carefully strokes a fern frond, her demeanor highlighting the beauty and fragility of the temperate rainforest, all while surrounded by lush greenery and the natural world.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed42_1972
videos/HRA_part0/1972.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray spacesuit with a NASA logo, is seen running energetically across the barren, rocky landscape of a distant planet, with a large, complex space station visible in the background. His movements are dynamic, showing determination and purpose. The vast, alien terrain, dotted with craters and boulders, stretches out behind him, while the dimly lit space habitat, complete with solar panels and satellite dishes, looms large. The janitor's spacesuit bears a name tag and various patches, adding to the realism of this futuristic scene.]" }, { "from": "gpt", "value": "Normal. The character's movements in the video are not smooth." } ]
seed46_2558
videos/HRA_part2/2558.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a green shirt and khaki shorts, walks through a savanna landscape, holding a book bag, with a hyena casually following at a distance. The student, in casual attire suitable for warm weather, continues walking along a dirt path, with the hyena maintaining a parallel path some distance away. As they move, the student occasionally glances back at the hyena, which returns the look, both seemingly unafraid and unperturbed by each other's presence, set against a backdrop of dry grasses and scattered trees typical of a savanna environment.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_275
videos/HRA_part2/275.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a black beret, blue shirt, and brown vest, gently caresses an ibex with her right hand, while holding a paintbrush in her left. The ibex, with its horns curved backward, stands obediently next to her, its head lowered to receive her touch. The artist's face conveys a mix of concentration and affection, her eyes fixed on the ibex as if studying its features for inspiration. The scene takes place in a rustic studio filled with canvases, easels, and various art supplies, creating a warm and creative atmosphere.]" }, { "from": "gpt", "value": "Normal. The character's movements are not smooth." } ]
seed46_2595
videos/HRA_part2/2595.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit living room filled with the warm glow of a fireplace, two young children sit closely together on a plush, brown couch. One child, a little boy with short, curly hair, wears a gray sweater and leans into his sister, who has straight, shoulder-length hair and dons a pink dress. They both hold hands comfortingly, displaying signs of illness, as they occasionally cough into their elbows, demonstrating proper hygiene etiquette. The room is decorated with a large, colorful rug and various soft toys scattered around, creating a familiar and homey atmosphere. The siblings' focus is on a book about dinosaurs, which lies open in front of them, indicating their attempt to distract themselves from feeling unwell.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]