video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1635
|
videos/HRA_part1/1635.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park, a creative director, dressed in a casual yet professional attire, intently observes a small, agile mouse crawling along a weathered wooden fence. The mouse, with its curious eyes and twitching nose, explores its surroundings with cautious determination. The director, holding a clipboard and pen, meticulously studies the creature's movements, occasionally jotting down notes. The scene captures the unique interaction between human observation and the natural behavior of wildlife in the controlled environment of a zoo.]"
},
{
"from": "gpt",
"value": "Normal. The rat's movements in the video are not smooth."
}
] |
seed44_2537
|
videos/HRA_part1/2537.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over casual attire, walks through a lush deciduous forest during autumn. Holding a small, brown ferret gently in one hand, he observes the rich, earthy colors of the trees and the dappled sunlight filtering through the leaves. The forest floor is carpeted with fallen leaves, and the occasional sound of twigs snapping underfoot adds to the peaceful ambiance. As he continues his leisurely stroll, the doctor occasionally pauses to examine the flora and fauna around him, the curious ferret nestled in his palm, seemingly enjoying the natural surroundings as much as its human companion.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's hand appears deformed, and the ferret also appears deformed."
}
] |
seed44_3042
|
videos/HRA_part1/3042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman with salt-and-pepper hair sits in a dimly lit room, wearing a gray blazer and a white shirt with the top button undone. He leans back in a brown leather armchair, holding a book in his hands. The camera captures him from the side, highlighting his profile as he reads intently. Beside him, a wooden table holds a glass of red wine, a vintage lighter, and a half-smoked cigar resting in an ashtray. The atmosphere is cozy and intimate, with the warm glow of a nearby lamp illuminating the scene. Behind the chair, a large bookshelf filled with books adds to the scholarly ambiance. The man's eyes are fixed on the pages, his lips slightly parted, indicating deep concentration as he delves into the story. The setting conveys a sense of leisurely intellectual pursuit, with the elements of wine, cigar, and reading material suggesting a refined evening routine.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate a vintage lighter, half-smoked cigar, ashtray, or wooden table."
}
] |
seed46_1310
|
videos/HRA_part2/1310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, distinguished by its brown fur, white underbelly, and tufted ears, stealthily crawls across a sandy surface in a suburban town, near wooden fences and lush greenery. It pauses to sniff the air, displaying its sharp teeth and alert demeanor. The feline then continues its crawl, passing by a stone wall and wooden planks, indicating the proximity to human habitation. Throughout the scene, the bobcat's cautious and curious nature is evident as it explores its surroundings in the town's outskirts.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2138
|
videos/HRA_part0/2138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 police officer, dressed in a navy uniform with a badge and gun holster, is kneeling in a park, intently digging with a small shovel into a patch of dirt surrounded by green grass and shrubs. The scene is set under a clear blue sky, with the officer's focus and determination evident as they meticulously excavate the soil. Moments later, the officer, still in their navy uniform and gear, carefully sifts through the dirt with gloved hands, searching for evidence with a serious expression. The location remains the same, a serene park with lush greenery and a cloudless sky overhead.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, hand is distorted, and face is distorted."
}
] |
seed44_1080
|
videos/HRA_part1/1080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna dotted with small shrubs and trees, a large herd of buffalo gathers. Suddenly, one buffalo, distinct with its massive horns and dark brown fur, begins to move rhythmically, almost dancing, against the backdrop of the herd and the distant, hazy mountains. Its movements are energetic yet controlled, as if performing a ritualistic dance under the watchful eye of the herd. The camera focuses on this unique spectacle, capturing the buffalo's dance in the midst of its natural habitat, surrounded by the rest of the herd and the serene beauty of the African landscape.]"
},
{
"from": "gpt",
"value": "Normal. The buffalo's movements are not smooth."
}
] |
seed42_2995
|
videos/HRA_part0/2995.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red fox, with its bushy tail swaying, dances gracefully in a clearing surrounded by lush green foliage. Its movements are fluid and lively, as if performing a choreographed routine under the dappled sunlight filtering through the leaves. The fox leaps and twirls, its fur shimmering with golden highlights, embodying the spirit of the wild in a joyful, uninhibited dance. Against the backdrop of the vibrant forest, the fox's agile form and animated expressions convey a sense of freedom and playfulness in nature.]"
},
{
"from": "gpt",
"value": "Bad. The fox dancing in the video is very unsmooth, with uncoordinated movements."
}
] |
seed42_1485
|
videos/HRA_part0/1485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguishable by his classic black vest and white button-down shirt, is shown shoveling snow with determination. His attire is uniquely juxtaposed with the wintry task at hand, as he clears a path in front of a charming, snow-covered cottage. Snowflakes gently fall from a cloudy sky, accumulating on the roof and surrounding trees, while the waiter, wearing black gloves and sensible shoes for traction, focuses on his unexpected duty. Despite the cold, he works diligently, the snow creating a picturesque setting that contrasts with his formal waiter's uniform.]"
},
{
"from": "gpt",
"value": "Bad. The shoveling motion can be seen, but the server's hand disappears suddenly in the middle frame, and the shovel also disappears at the same time."
}
] |
seed46_3134
|
videos/HRA_part2/3134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional lawyer, dressed in a casual yet stylish ensemble of a gray turtleneck sweater and black pants, stands in a modern kitchen with sleek, stainless steel appliances. The individual focuses intently on preparing a gourmet meal, chopping ingredients on a wooden cutting board placed atop a granite countertop. The kitchen is illuminated by recessed ceiling lights, casting a warm glow over the scene. Behind the chef, a large window allows a view of a city skyline at twilight, adding a touch of urban sophistication to the domestic setting. The lawyer's movements are confident and practiced, indicating a comfort in both the courtroom and the culinary arts.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1519
|
videos/HRA_part0/1519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 middle-aged doctor, wearing a white lab coat over a navy blue shirt, sits in a cozy, dimly lit pub, sipping a glass of red wine. The pub is filled with the warm glow of hanging lights and a fireplace, creating a relaxed atmosphere. The doctor, with short brown hair and a neatly trimmed beard, leans back in his chair, holding the stem of the wineglass, and gazes thoughtfully into the distance. The scene conveys a sense of calm and tranquility, with the doctor enjoying a moment of respite from his busy medical career.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's eyes were not generated in the video."
}
] |
seed42_2363
|
videos/HRA_part0/2363.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a warm, sandy desert landscape under a bright, cloudless sky, two children, a boy and a girl, both wearing vibrant, culturally-inspired clothing, approach a calm camel. The camel, with two humps and a red and white cloth draped over it, stands patiently in the middle of the sandy dunes. The boy, dressed in a blue outfit, reaches out gently to caress the camel's nose, showing trust and connection. The girl, wearing a pink dress, watches with a smile, her hands on her hips, displaying comfort and familiarity with the animal, emphasizing a tender moment of human-animal interaction in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The boy's movements are not continuous, there are sudden changes."
}
] |
seed46_1304
|
videos/HRA_part2/1304.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 muscular man with short brown hair, wearing a black wetsuit, swims underwater in a clear, blue pool, interacting closely with a live cobra that moves alongside him. The snake, its hood slightly spread, appears calm in the water, its body parallel to the man's outstretched arm. Sunlight filters through the water, casting dappled light on the man's face as he maintains eye contact with the snake, both creatures moving gracefully through the aquatic environment. The scene is set in an outdoor pool, surrounded by lush greenery, emphasizing the natural setting and the unique interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Normal. The cobra in the video is contorted."
}
] |
seed44_1662
|
videos/HRA_part1/1662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park, a woman wearing a yellow jacket and khaki pants runs along a winding path surrounded by lush greenery. As she moves, her attention is drawn to an adorable hedgehog scurrying across the trail, its tiny feet moving swiftly beneath its spiky exterior. The hedgehog pauses for a moment, looking up at the woman with curious eyes before continuing on its way, blending into the underbrush. The woman, smiling at the encounter, resumes her run, passing by various enclosures housing majestic animals, all set against the backdrop of a sunny day in the sprawling park.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1361
|
videos/HRA_part2/1361.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 opera setting, a cashier, dressed in a metallic green costume with silver accents, is seen crawling across a high-tech stage filled with holographic displays and neon lights. The cashier, wearing a helmet with a transparent visor, moves slowly and deliberately, as if navigating through a complex transaction or performing a ritualistic dance. The background is filled with an audience of alien species, all watching intently as the cashier completes their task, emphasizing the unique blend of everyday life and dramatic performance in this cosmic environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2671
|
videos/HRA_part2/2671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 grey suit, white shirt, and patterned tie, walks purposefully across a grassy field under a twilight sky, carrying a large, transparent bag. In the distance, a comet streaks across the night sky, its tail glowing brightly. The lawyer pauses, turning his head to gaze up at the celestial phenomenon, his expression a mix of awe and determination. Despite the extraordinary sight, he continues his steady walk, the comet's light illuminating his path forward.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer in the video generation is problematic and does not conform to real-life scenarios."
}
] |
seed42_1757
|
videos/HRA_part0/1757.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman wearing a green tank top and khaki shorts is playfully running in a spacious, grassy area under a clear blue sky, with a koala perched on her back. The koala, clinging to her shoulder, is holding a branch, adding a touch of whimsy to the scene. The woman's joyful expression and the koala's relaxed demeanor create a harmonious and delightful moment, encapsulating the essence of carefree fun and the unexpected companionship between human and animal.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs in the video have generation issues; her fingers are not fully formed, and her face is generated blurily. The koala's limbs are missing, and its facial features are incompletely generated."
}
] |
seed46_2193
|
videos/HRA_part2/2193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman with brown hair tied back in a ponytail, wearing a gray cardigan over a white blouse and jeans, meticulously dusts furniture in a classroom. She moves with precision, her facial expression one of concentration. The room is filled with sunlight, illuminating the specks of dust floating in the air. She pauses for a moment, her hands on her hips, surveying her work before continuing. The classroom is mostly empty, save for a few desks and chairs, giving the impression of a quiet, orderly space. Throughout the scene, she remains focused on her task, her movements deliberate and efficient.]"
},
{
"from": "gpt",
"value": "Normal. The woman's cleaning in the video is basically normal, but there are actions that are not coordinated."
}
] |
seed46_2851
|
videos/HRA_part2/2851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown monkey walks purposefully across a lush green forest floor, sunlight filtering through the dense foliage above, casting dappled shadows on the ground. The monkey, with its fur ruffled by a gentle breeze, carries a small object in its mouth, possibly food, as it navigates the underbrush with agile movements. Its eyes, alert and curious, scan the surroundings, showcasing its adaptability in the wild. The scene is set against a backdrop of verdant vegetation, with the occasional sound of rustling leaves and chirping birds adding to the natural ambiance.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the monkey in the video are missing, the ears are problematic, and the tail is deformed."
}
] |
seed46_2830
|
videos/HRA_part2/2830.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cityscape illuminated by neon lights, a waiter dressed in a sleek, silver apron over a black uniform walks purposefully across a crowded outdoor plaza filled with diverse patrons enjoying their meals. Behind him, an AI pilot, recognizable by its advanced humanoid form with a polished metallic exterior and glowing blue eyes, strides confidently, carrying what appears to be a flight helmet under its arm. Both figures navigate through the bustling scene, the waiter balancing a tray laden with exotic dishes, while the AI pilot's movements are precise and efficient, highlighting the seamless integration of technology and service in this high-tech environment.]"
},
{
"from": "gpt",
"value": "Normal. The movements are basically normal but there is some lack of coordination."
}
] |
seed46_1012
|
videos/HRA_part2/1012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 finds himself in an unexpected dance-off with a mischievous monkey. The two are surrounded by an array of exotic plants and flowers, giving the impression of a lush garden or jungle setting. The waiter, maintaining a professional demeanor despite the oddity of the situation, gracefully moves to an unseen rhythm, while the monkey, dressed in a miniature tuxedo, gleefully mimics his every step. The playful exchange is captured in high definition, with vibrant colors and dynamic movements, creating a surreal yet captivating spectacle.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth, there are sudden changes."
}
] |
seed46_3197
|
videos/HRA_part2/3197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wings spread wide against a backdrop of rolling clouds and a cerulean sky. The bird's white plumage is highlighted by the golden rays of the sun, casting a serene glow over the scene. As it glides effortlessly, its keen eyes scan the waters below for signs of prey, demonstrating the harmony between creature and environment. The albatross then swoops down, its silhouette framed by the sun, before rising back into the heavens, embodying the spirit of freedom and the majesty of nature.]"
},
{
"from": "gpt",
"value": "Bad. Albatross generation in the video is abnormal, with the wings of the albatross in the middle frames being distorted and deformed, making the overall video unrealistic."
}
] |
seed42_2814
|
videos/HRA_part0/2814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a royal blue scrubs top and light blue pants, stands against a white wall with a large, welcoming smile. She waves energetically with her right hand, her dark brown hair styled in a bun. Behind her, a row of lockers can be seen, adding context to the hospital setting. Her left arm rests by her side, and she wears a silver watch on her wrist. The nurse's eyes are closed as she waves, conveying genuine warmth and friendliness to the viewer.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1293
|
videos/HRA_part1/1293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, dressed in a pristine white uniform and wearing a red bandana, walks across a rocky Martian landscape under a starlit sky. Holding a large, clear bowl that reflects the celestial beauty above, the chef pauses to gaze upwards, captivated by the distant stars. With the vast Martian terrain spread out behind, the scene conveys a sense of wonder and exploration, as the chef embarks on a unique stargazing experience on the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The hands appear deformed, and the face is not fully formed."
}
] |
seed42_2711
|
videos/HRA_part0/2711.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous police officer, clad in a black tactical uniform and wearing a bulletproof vest, ascends a rugged concrete wall in a dimly lit urban environment. The scene begins with the officer gripping the wall's edge, his face set with determination. Next, he pulls himself up, revealing the emblem on his vest as he climbs. Then, the camera captures him from below, highlighting his strength and agility against the backdrop of city lights. Lastly, he reaches the top, standing triumphantly with his radio in hand, ready to communicate, while the textured wall and the cityscape complete the gritty urban setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1072
|
videos/HRA_part2/1072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, donning a casual gray shirt and black cap, is shown engaged in an unexpected task: unclogging a drain. In the first scene, he is kneeling on a hardwood floor, attentively examining a drain with a serious look on his face. Next, he is seen plunging the clogged drain with a red plunger, demonstrating his hands-on approach to problem-solving. Following this, the director is depicted using a drain snake to clear the blockage, his expression one of determination. Lastly, he inspects the drain once more, now clean, with a look of satisfaction, his casual attire contrasting with his professional role.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, and the red plunger disappears for no reason."
}
] |
seed42_2506
|
videos/HRA_part0/2506.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an imaginative scene, a lone camel, adorned with vibrant red and yellow fabrics, stands gracefully at the edge of a bustling highway under a vivid orange sunset. Vehicles whiz by in the background, forming streaks of light against the twilight sky. The camel begins to sway and dance, moving its body to an unheard rhythm, creating a surreal contrast between the wild and the urban landscape. Its movements are fluid and expressive, drawing attention despite the chaos of the surrounding traffic. The highway lights and car headlights illuminate the scene, casting dramatic shadows as the camel continues its dance, a captivating spectacle where nature meets the modern world.]"
},
{
"from": "gpt",
"value": "Normal. No highway street lights were generated."
}
] |
seed46_2610
|
videos/HRA_part2/2610.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a gray suit with a blue shirt and striped tie, stands in a modern office space. He is attentively checking a smoke detector mounted on the ceiling, exhibiting a careful and professional demeanor. The office features a large window offering views of a city skyline, a desk with a laptop and documents, and a bookshelf filled with law books, creating a setting that blends professionalism with safety awareness. The lawyer's actions highlight the importance of routine safety checks in a workplace environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_211
|
videos/HRA_part1/211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic scene set within the confines of an art gallery, a firefighter clad in full gear and a helmet, carrying an axe, sprints down a wide hallway lined with large paintings and modern art sculptures. The overhead lights cast shadows, adding to the intensity of the moment. Behind him, the glow of an encroaching fire illuminates the space, its orange and red hues contrasting starkly with the artworks. Amidst the chaos, the firefighter's purposeful stride conveys determination and urgency, his mission to save lives and preserve priceless art pieces from the raging inferno.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's hand and axe generation in the video have problems; the axe flies around randomly in the middle frames and then disappears completely."
}
] |
seed44_3080
|
videos/HRA_part1/3080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, desolate landscape under a clear blue sky, four children, two boys and two girls, wearing simple clothes and shoes, run together across an open field. Their faces show determination and resilience, despite the harsh environment. They navigate through a barren terrain, dotted with remnants of old mining equipment and industrial structures in the distance. The children leap over small debris, their movements fluid and energetic, as they continue their journey across this rugged, post-industrial landscape, their spirits unbroken by the challenges around them.]"
},
{
"from": "gpt",
"value": "Bad. The children in the video have distorted faces, hands, arms, and legs."
}
] |
seed44_2540
|
videos/HRA_part1/2540.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a bustling metropolis, a police officer, clad in a navy uniform and cap, stands beside a large, friendly dog. The officer gently caresses the animal's head with a smile, forming a contrast against the urban backdrop of towering skyscrapers and busy streets. This tender moment between the law enforcer and the canine companion is captured against the steel and glass skyline, offering a glimpse of compassion amidst the city's concrete jungle.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1028
|
videos/HRA_part0/1028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 astronaut, clad in a white spacesuit adorned with the American flag, embarks on a spacewalk to repair a satellite. Holding a specialized tool in one hand and a cleaning wipe in the other, they meticulously clean a solar panel against the backdrop of Earth, visible in the distance. The astronaut's gloved hands carefully grip the cleaning wipe as they perform maintenance tasks, ensuring the satellite's functionality. Throughout the spacewalk, the vastness of space surrounds the astronaut, highlighting the isolation and importance of their mission to repair critical equipment orbiting the planet.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut's movements in the video are not smooth and coordinated."
}
] |
seed42_2237
|
videos/HRA_part0/2237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, majestic tuna fish glides through the crystal-clear waters of the ocean, its sleek silver body cutting through the water with grace and power. The sunlight filters down from the surface above, casting shimmering patterns across the tuna's scales. Schools of smaller fish scatter in its path, the tuna's presence commanding respect in the underwater realm. In the distance, the silhouette of a reef can be seen, adding depth and context to the tuna's aquatic habitat. The video captures the tuna from various angles, showcasing its size and strength as it navigates its natural environment with ease.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2212
|
videos/HRA_part2/2212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a silver spacesuit, reminiscent of a high-tech astronaut, walks across a vast, barren landscape under a twilight sky, reminiscent of a distant planet. A cobra, its scales shimmering with iridescent colors, slithers along the ground beside him, seemingly unphased by the alien environment. In the background, a massive deep space communication array rises into the sky, its dishes facing the cosmos, ready to transmit messages across the universe. The man stops, looking up at the stars, while the cobra rears up, mirroring his stance, both figures framed by the imposing silhouette of the communication array.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2547
|
videos/HRA_part0/2547.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a yellow safety vest and holding a mop, stands near a large window overlooking a kangaroo casually hopping through the grounds of a power plant complex, set against a backdrop of industrial cooling towers. The scene transitions to show the janitor, now in swimming trunks, diving into a clear, blue pool, while a kangaroo watches from the edge, all under the watchful gaze of the towering power plant structures in the distance. The final shot captures the unexpected duo, the janitor and the kangaroo, enjoying a peaceful moment together by the poolside, with the power plant's silhouette framing the serene scene.]"
},
{
"from": "gpt",
"value": "Bad. In scene one, the kangaroo was generated abnormally, and in the swimming pool scene, there were issues with the generation of the cleaner's head and hands."
}
] |
seed44_2806
|
videos/HRA_part1/2806.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, wearing a dark blue jacket, beige pants, and carrying a brown backpack, runs along the docks on a misty day, passing by large ships and industrial buildings. He stops momentarily to gaze at the water, his reflection visible in the wet pavement. Continuing his run, he passes wooden benches and green spaces, with the city skyline in the distance. Throughout his journey, he remains engrossed in his thoughts, occasionally glancing down at a notebook tucked into his backpack, the colors of the docks' wood and metal contrasting against the muted tones of the surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The notebook in the video was generated abnormally, the writer's facial features were generated blurry, and the hands and feet were deformed."
}
] |
seed44_2728
|
videos/HRA_part1/2728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artistic individual, donning a black beret and a red and black striped shirt, dances whimsically in a studio filled with vibrant paintings and art supplies. In their right hand, they hold a ferret that matches their playful energy, engaging in a synchronized dance that reflects their unique bond. The ferret, wrapped around their wrist like a furry bracelet, seems to enjoy the movement, adding a touch of eccentricity to the scene. The artist's left hand gestures expressively, complementing their dance moves, while the chaotic yet colorful environment around them enhances the creative atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The facial features of the artist in the video are generated blurry, and the hands and the ferret on the hands are generated deformed."
}
] |
seed46_1078
|
videos/HRA_part2/1078.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 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 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": "Good. Basically correct."
}
] |
seed44_1609
|
videos/HRA_part1/1609.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student with a messy bun, wearing a white t-shirt and grey sweatpants, stands in a small dorm kitchen. She measures coffee grounds into a filter, her movements practiced and efficient. Next, she pours water from a bottle into the coffee maker, the light catching the droplets as they fall. Then, she pushes the start button on the machine, her face lighting up with anticipation. Lastly, she adds a splash of milk to her mug, stirring it slowly as steam rises, ready to enjoy her well-deserved break amidst the stacks of books and papers on her desk.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1446
|
videos/HRA_part0/1446.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches regally on a branch, its vibrant plumage a stunning mix of green, blue, and brown feathers, set against a backdrop of lush foliage and clear blue sky. Its long, curved beak points upward, ready to snatch prey from the air. In the next frame, it takes flight, wings outstretched, revealing the striking contrast of its underbelly and the iridescent sheen of its back feathers. It swoops gracefully, capturing an unsuspecting insect in mid-air, before returning to its perch, triumphant, the captured prey visible in its beak, all set against the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's beak and wings in the video have issues."
}
] |
seed42_2221
|
videos/HRA_part0/2221.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a medium-large raptor with a brown back and contrasting white underparts, soars gracefully over a serene lake at sunset. Its piercing yellow eyes are fixed on the water below, searching for prey. The bird's distinctive head, marked with a dark eye-stripe and a white throat, contrasts strikingly with its dark cap. Its underwings show a mix of white and brown streaks, while its legs dangle beneath it, ready to grasp a fish. The osprey's silhouette is framed by the warm glow of the setting sun, casting a golden hue over the tranquil waters.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1547
|
videos/HRA_part0/1547.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, young Asian nurse wearing a white uniform and a name tag takes a break from her hospital duties to clean the large, rectangular window in the patient's room. Holding a squeegee in her right hand and a spray bottle in her left, she sprays the glass with a cleaning solution, creating a fine mist. She then wipes it down with the squeegee, leaving a clear, streak-free surface. The natural light from outside illuminates the room, casting a warm glow on the nurse as she works diligently, ensuring the window is spotless.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's movements in the video are uncoordinated."
}
] |
seed42_1119
|
videos/HRA_part0/1119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful Asian cashier, wearing a red apron over a white collared shirt, black pants, and black shoes, is seen mid-air, jumping with both feet off the ground, her ponytail bouncing behind her. The camera captures her from various angles, showing her enthusiasm and energy as she performs this unexpected action within the confines of her workplace, a modern convenience store with neatly arranged shelves and bright lighting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2666
|
videos/HRA_part0/2666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant forest setting, a mother beaver gently caresses her kits with her large, flat tail, while they sit cozily together on the riverbank. The kits, with their soft, brown fur, look up at her with adoration, as the mother's nurturing touch conveys love and protection. Surrounded by the vibrant greenery and tranquility of nature, this heartwarming scene captures the tender bond between a beaver mother and her offspring.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed44_2231
|
videos/HRA_part1/2231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a fantastical depiction, a janitor, dressed in a reflective silver suit, gently caresses the ethereal auroras of Uranus. The celestial event unfolds with vibrant green and purple hues swirling across the planet's atmosphere, creating an otherworldly spectacle. The janitor, equipped with a futuristic cleaning tool, appears to interact with the auroral lights, as if nurturing the beauty of the cosmic phenomenon. This surreal scene merges the mundane profession of a janitor with the majestic wonder of space, set against the backdrop of Uranus's mesmerizing auroras.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's fingers were not generated in the video."
}
] |
seed44_2288
|
videos/HRA_part1/2288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a black jacket and khaki pants, is seen in a close-up shot, wiping his brow with a white handkerchief. Behind him, a herd of antelopes can be observed grazing in a vast, grassy savanna, creating a juxtaposition between the director's world and the natural habitat of the antelopes. The director's weathered face and focused gaze suggest a moment of intense concentration during a film shoot, while the antelopes continue their serene existence in the background, unaware of the human drama unfolding nearby.]"
},
{
"from": "gpt",
"value": "Bad. The director's fingers are generated incorrectly, and the antelope is malformed."
}
] |
seed44_1480
|
videos/HRA_part1/1480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a large hippopotamus walks along a riverbank, its massive body glistening under the sun, with industrial factories looming in the background. The scene opens with a wide shot of the river, where the hippo emerges from the water, its wet skin reflecting the sunlight. It then proceeds to walk along the riverbank, its powerful legs propelling it forward, as it passes by the factories, which emit plumes of smoke into the sky. The camera focuses on the hippo's movements, capturing its every step as it traverses this unusual landscape, the factories serving as a stark contrast to the natural beauty of the animal.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1453
|
videos/HRA_part1/1453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning common pheasant, characterized by its vibrant plumage, is captured in a natural habitat, surrounded by lush green foliage. The male bird, with its distinctive red face, prominent white neck collar, and golden crest, struts confidently on the forest floor. Its iridescent green head and long, brownish-green tail feathers are highlighted as it moves through the underbrush. The setting showcases the pheasant's environment, featuring tall grasses and leafy plants, providing a rich, textured backdrop for this captivating display of avian beauty.]"
},
{
"from": "gpt",
"value": "Bad. The bird's legs in the video are not fully generated, and the chicken's beak disappears halfway through."
}
] |
seed46_1419
|
videos/HRA_part2/1419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a helmet, is sprinting with intense focus through a lush, green park. He's gripping a fire hose as he runs beside a serene lake, where ducks are seen swimming in the background. The scene conveys a sense of urgency and determination, with the firefighter's muscular physique straining against his equipment. The park is filled with vibrant greenery and tall trees, providing a stark contrast to the firefighter's urgent mission. As he races past a wooden bench and a playground, the peaceful setting underscores the potential danger lurking nearby.]"
},
{
"from": "gpt",
"value": "Bad. The character does not have a fire hose in their hands."
}
] |
seed42_3131
|
videos/HRA_part0/3131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 police officer, wearing a navy uniform with badge and name tag, meticulously cleans a large aquarium filled with colorful fish and aquatic plants, set against a backdrop of a modern, minimalist interior. The officer, displaying a gentle side, carefully tends to the tank, ensuring the well-being of the marine life within. The aquarium, illuminated by overhead lights, showcases various species of fish swimming calmly, oblivious to the officer's presence. The room's clean lines and neutral tones contrast with the vibrant colors of the fish, creating a visually striking scene.]"
},
{
"from": "gpt",
"value": "Bad. The fish in the video was generated abnormally, and the police officer's hand was deformed."
}
] |
seed42_2745
|
videos/HRA_part0/2745.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform with a black necktie and a tall toque blanche hat, stands on a small wooden stool. He is in the process of changing a light bulb in a restaurant kitchen, surrounded by stainless steel appliances and shelves stocked with cooking utensils. The kitchen is brightly lit, except for the area where the burnt-out bulb needs replacement. The chef, with a slight smile, carefully unscrews the old light bulb, demonstrating a lighthearted moment in his daily routine amidst the professional culinary environment.]"
},
{
"from": "gpt",
"value": "Normal. The chef's action of unscrewing the light bulb in the video is not smooth and coordinated."
}
] |
seed46_3171
|
videos/HRA_part2/3171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman sits serenely in a sunlit room, her eyes closed, focusing deeply on her breath. She wears a simple white blouse, the fabric gently moving with each inhale and exhale, highlighting the tranquility of the moment. Sunbeams filter through sheer curtains, casting a warm glow on her face, emphasizing her peaceful expression. Her hands rest calmly in her lap, fingers slightly curled, embodying a state of deep relaxation and mindfulness. The room is sparsely decorated, with a potted plant in the corner adding a touch of nature to the serene atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. Almost no action."
}
] |
seed44_1000
|
videos/HRA_part1/1000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged cashier, donning a red apron over a casual outfit, is shown unclogging a drain in a break room, revealing a moment of unexpected duty. The scene opens with the cashier looking into the drain with a concerned expression, followed by her using a plunger to clear the clog, showcasing determination. Next, she inspects the plunger with a look of resolve, indicating her commitment to resolving the issue. The scene then shows her pouring a cleaning solution down the drain, wearing rubber gloves for protection, and finally, she tests the faucet, ensuring the water flows freely, a sign of success, all while maintaining her red apron emblematic of her primary role.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm in the video suddenly distorts and elongates in the middle frame, which is not coordinated."
}
] |
seed42_2507
|
videos/HRA_part0/2507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated bill resembling a sword, swims gracefully through the clear blue waters of the ocean. Its body, a sleek silver hue with a dark blue back, glides effortlessly as it navigates the aquatic environment. Sunlight filters through the water, casting shimmering highlights on the fish's streamlined form. The surrounding marine life, including schools of smaller fish scattering in its presence, underscores the swordfish's dominance in its habitat. Against the vast, open sea, the swordfish embodies power and agility, its unique appearance and behavior captivating the viewer in this underwater scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1584
|
videos/HRA_part1/1584.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a yellow high-visibility vest, blue jeans, and a gray shirt, dances with uninhibited joy in the vastness of a desert canyon. The landscape features towering red rock formations, lush greenery, and a distant mountain range under a clear blue sky. The janitor, holding a broom as if it were a dance partner, spins and twirls with abandon, embodying a spirit of freedom and happiness amidst the stark beauty of nature. As the camera pans out, the scale of the canyons becomes apparent, contrasting the figure of the dancing janitor against the immense natural surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video dances very poorly, with uncoordinated movements."
}
] |
seed44_1852
|
videos/HRA_part1/1852.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 female cashier, with a casual hairstyle and wearing a dark green jacket over a gray t-shirt, leans against a white wall with a wooden panel. She holds a book titled \"The Great Gatsby\" by F. Scott Fitzgerald, reading it intently during a break. The scene is set in a grocery store aisle, with shelves stocked with products like canned goods and boxes of cereal visible in the background. The cashier's relaxed posture and focused gaze on the classic novel convey a sense of peace and personal time amidst her work environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2970
|
videos/HRA_part1/2970.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 young female cashier, wearing a red apron over her gray sweater and black jeans, stands at a register, looking surprised. Behind her, a full-sized moose runs across the store, its antlers adorned with Christmas lights, adding a surreal touch to the supermarket setting. The moose dashes between the aisles filled with groceries, creating a chaotic yet amusing atmosphere. The cashier watches the unexpected visitor with a mix of shock and amusement, as customers look on in disbelief, capturing the bizarre event on their smartphones. The moose's presence disrupts the mundane routine of the store, turning it into an unforgettable experience for everyone present.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows a moose crossing through the store, with movements that are not continuous and smooth, appearing uncoordinated; customers can be seen using their smartphones to record, but their movements are also not smooth and appear uncoordinated."
}
] |
seed44_1730
|
videos/HRA_part1/1730.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown shirt and glasses, is seen in a unique scenario, engaging with a hyena at a public swimming pool. The director, standing at the edge of the pool, interacts with the wild animal, which is swimming in the water, creating an extraordinary juxtaposition of human and beast in an unexpected urban setting. The director's attire, complete with brown shirt and glasses, contrasts with the untamed presence of the swimming hyena, capturing a surreal and captivating moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1788
|
videos/HRA_part0/1788.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gerbil, adorned with a miniature top hat and tiny suspenders, stands on its hind legs on a wooden stage. The rodent energetically moves to an unseen beat, its forepaws mimicking a dancer's gestures against a backdrop of a red velvet curtain. The scene is whimsical, with the gerbil's lively expressions and animated body language capturing the essence of joyful dancing under the warm glow of spotlight, all set against a rich, textured red background that adds depth and drama to the performance.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's limbs in the video have issues with generation, the paws are not fully formed, and the face is generated blurry."
}
] |
seed42_2675
|
videos/HRA_part0/2675.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, resembling Chris Hemsworth, waters plants in a lush, green backyard garden filled with various potted plants and trees. He wears a simple white tank top, brown cargo shorts, and brown flip-flops, giving off a casual, laid-back vibe. The scene is set during the day, with bright sunlight illuminating the vibrant greenery and highlighting the actor's chiseled physique. As he tends to the plants, he occasionally pauses to smile at the camera, showcasing his charming personality and the peaceful atmosphere of the garden.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2091
|
videos/HRA_part2/2091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student wearing a gray sweater and black jeans sits in a classroom, wiping the surface of a large, advanced telescope with a cloth, as if preparing it for use. The room is dimly lit, with a projector screen displaying images of deep space in the background. The student's focus is intense, their actions deliberate, as they handle the telescope with care, its size and complexity suggesting it is used for serious astronomical research or communication. The overall scene conveys a sense of dedication and curiosity about the mysteries of the universe.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1575
|
videos/HRA_part1/1575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a lab coat walks purposefully across a large, open laboratory space filled with complex machinery and high-tech equipment, the setting for a quantum entanglement experiment. The room is illuminated by bright overhead lights, casting a sterile glow over everything. In the background, scientists can be seen observing data on computer screens and discussing theories, their faces serious and focused. The worker carries a clipboard, pausing occasionally to check notes or adjust settings on various machines, all while surrounded by the hum of active scientific inquiry into the mysteries of quantum mechanics.]"
},
{
"from": "gpt",
"value": "Bad. The character's walking in the video is not smooth, with uncoordinated movements."
}
] |
seed42_1959
|
videos/HRA_part0/1959.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, wearing a gray t-shirt and black tactical pants, stands in a modern, open-plan kitchen with white cabinets and stainless steel appliances. He confidently flips a crepe on a large, round griddle, showcasing his culinary skills. The kitchen is part of a fire station, with a red fire truck visible through an arched doorway behind him. The firefighter, now donning an apron over his attire, carefully adds ingredients to the crepe, demonstrating his ability to balance the demands of firefighting with the precision required in cooking. The scene captures the unexpected yet harmonious blend of a firefighter's life-saving duties and his passion for creating delicious meals.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_111
|
videos/HRA_part0/111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with gold accents and a peaked cap, runs purposefully across a grand hall within a futuristic space station. The hall is lined with flags from various nations and interspersed with abstract art pieces, all illuminated by the soft glow of recessed lighting. In the distance, a large, circular window reveals the vastness of space and the distant twinkle of stars. The officer's run suggests urgency, possibly related to security matters at the ongoing political summit, where delegates from Earth and various space colonies gather to discuss interstellar policy. The polished floor reflects the officer's movement, emphasizing the gravity of the situation in this otherwise serene and majestic setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2930
|
videos/HRA_part1/2930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, clad in a gray T-shirt and black cargo pants, methodically mops the floor of a modern industrial space, surrounded by sleek machinery and equipment. His attire includes a name badge and a pair of safety glasses hanging around his neck, signifying his professional role. The scene is lit by bright overhead lights, casting shadows that emphasize the rhythmic motion of the mop. The engineer's focused gaze and steady hand convey a sense of duty and precision as he tackles the mundane task of cleaning, set against the backdrop of a high-tech environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2417
|
videos/HRA_part2/2417.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, golden cheetah crawls under a low-hanging, silver photon sail, its eyes fixated ahead, muscles rippling beneath its spotted coat, set against a backdrop of a futuristic, metallic landscape. The sail, towering above, reflects beams of sunlight, creating an ethereal glow around the big cat. The cheetah, with its distinctive black tear markings and piercing green eyes, moves gracefully, its body positioned low to the ground, as if stalking prey, while the sail's advanced technology hints at a world beyond nature.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's movements in the video are not smooth."
}
] |
seed46_147
|
videos/HRA_part2/147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dense rainforest underbrush, a tiny vole emerges, its soft, brown fur glistening with moisture. It pauses, nose twitching, against the textured bark of a towering tree, as if caressing the ancient, moss-covered surface. Sunlight filters through the lush canopy overhead, casting dappled shadows on the rich soil below. The vole, sensing safety, continues its gentle exploration, its small paws leaving faint impressions on the damp earth, all set against the vibrant backdrop of the rainforest's greenery.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1035
|
videos/HRA_part1/1035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a standard uniform complete with badge, gun holster, and radio, is engaged in an unexpected task. He is seen from behind, bending over a small hole in the ground, which is surrounded by a ring of yellow tape. His right hand is plunged into the hole, indicating he is unclogging a drain. The location appears to be a public park, with green grass and trees in the background, and a group of people watching the unusual scene from a distance, their expressions a mix of amusement and curiosity. A yellow sign with the words \"Caution, Wet Floor\" leans against a nearby tree, adding to the surreal atmosphere of the situation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2831
|
videos/HRA_part0/2831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 whimsical scene unfolds where a costumed musician, dressed in a vibrant green hippopotamus outfit, gracefully crawls across a dimly lit stage. The stage is adorned with a red velvet curtain, adding a touch of drama. The musician's movements are slow and deliberate, almost balletic, as they crawl with an air of performance art. The costume is complete with oversized hippo ears and a large, friendly smile, creating a surreal and captivating visual display.]"
},
{
"from": "gpt",
"value": "Bad. The musicians in the video are generally generated distorted and deformed."
}
] |
seed46_1764
|
videos/HRA_part2/1764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a sleek silver spacesuit adorned with patches, performs an energetic dance against the backdrop of a vast, star-filled universe. The scene opens with the actor floating gracefully in zero gravity, spinning and twirling with the joy of someone experiencing the wonder of space tourism. Their movements are fluid and expressive, conveying a sense of freedom and exhilaration. As the dance continues, the actor executes a series of dynamic leaps and poses, each one highlighting the unique challenges and opportunities of dancing in microgravity. The stars shimmer and galaxies glow in the distance, providing a breathtaking canvas for this cosmic performance. Throughout the video, the actor's face, visible through the clear visor of their helmet, radiates with delight, sharing the magic of space travel through the universal language of dance.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the actors in the video are deformed and missing, fingers are not fully generated, the body is twisted, and the face is not generated."
}
] |
seed44_1550
|
videos/HRA_part1/1550.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged teacher, wearing a gray crew neck shirt, khaki pants, and black shoes, is seen from above, loading a stainless steel dishwasher in a well-lit kitchen. The kitchen features white cabinets, a white refrigerator, and a gray countertop. The teacher, with short brown hair and glasses, carefully places dishes into the lower rack of the dishwasher. In another angle, the teacher, now wearing a gray shirt and dark pants, continues loading the dishwasher, placing a cup in the upper rack. The room is brightly lit, with white walls and ceiling, and the teacher's focused expression conveys a sense of routine and responsibility.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_3178
|
videos/HRA_part0/3178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red beret and carrying a large canvas, walks purposefully down a bustling city street lined with vintage cinemas. Each theater features marquee signs advertising classic films from the golden age of cinema. The artist's attire includes a striped shirt, dark trousers, and a pair of worn-out sneakers, giving a sense of his creative and casual lifestyle. As he strides, passersby glance curiously at his oversized artwork, which is draped in a protective cloth, hinting at the mystery and anticipation of his latest creation. The vibrant atmosphere of the old movie houses and the artist's journey through the urban landscape evoke a sense of nostalgia and artistic inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The artist's feet are distorted in the video, as well as the faces of passersby and hands."
}
] |
seed44_2639
|
videos/HRA_part1/2639.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical scene, a costumed individual, dressed as a rhinoceros, leaps dynamically across a vast, cosmic landscape, dotted with floating celestial orbs. Simultaneously, in a corner of this otherworldly setting, a solemn, space-themed funeral procession takes place, with attendees dressed in futuristic attire, paying their respects. Amidst this surreal backdrop, a figure, dressed as a stereotypical grocery store cashier, complete with a checkered shirt and name tag, stands at an unconventional checkout counter, processing transactions for the peculiar gathering, adding an element of mundanity to the extraordinary event.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1404
|
videos/HRA_part0/1404.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 captivating scene unfolds on a moonlit beach, where a diverse group of people, dressed in vibrant, patterned shirts and shorts, gather around a bonfire. The atmosphere is festive, with a bat flying gracefully across the night sky, its silhouette visible against the glowing embers. The crowd dances energetically to lively music, their movements fluid and joyful, while others look on, clapping and cheering. Nearby, the calm sea reflects the firelight, creating a mesmerizing, shimmering effect on the water's surface. The sandy beach, dotted with palm trees, provides a picturesque setting for this nocturnal celebration.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are distorted, face is distorted, and legs are deformed."
}
] |
seed46_1997
|
videos/HRA_part2/1997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged worker, clad in a tan vest, dark pants, and brown gloves, interacts with a realistic monkey puppet, crawling on all fours across a lush green landscape. The detailed puppet, featuring lifelike fur and expressive eyes, follows the worker's movements closely. The worker, with a serious yet focused demeanor, guides the monkey puppet through various natural terrains, including dense foliage and rocky terrain, highlighting the puppet's agility and realism. Throughout the scene, the worker's connection with the monkey puppet conveys a sense of companionship and shared purpose in their outdoor adventure.]"
},
{
"from": "gpt",
"value": "Normal. The monkey's movements in the video are not smooth."
}
] |
seed42_1789
|
videos/HRA_part0/1789.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 agile antelope leaps majestically across the sun-drenched savanna, its powerful legs propelling it high above the golden grasses. The animal, distinguished by its brown fur and impressive horns, is captured mid-jump, with all four feet off the ground, highlighting its remarkable athleticism. In the background, a vast landscape stretches out under a clear blue sky, dotted with distant trees, emphasizing the vastness of the environment. The scene is one of raw nature, with the antelope's leap frozen in time, showcasing the beauty and grace of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the antelope in the video are missing, there are too many horns generated, and there are issues with the eyes."
}
] |
seed44_2496
|
videos/HRA_part1/2496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, green-brown jungle cobra crawls across a lush, moss-covered log in the dense rainforest undergrowth. The snake's hood is slightly raised, revealing its distinctive markings as it navigates the textured surface. Sunlight filters through the canopy, casting dappled light on the cobra, emphasizing its muscular body and smooth scales as it moves with purpose and grace in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The cobra's head is not raised in the video."
}
] |
seed42_2501
|
videos/HRA_part0/2501.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cave, a police officer, wearing a uniform with a badge and a utility belt equipped with various tools, including a flashlight, gently caresses the rough stone wall, seemingly searching for hidden clues or evidence. The cave's textured walls, illuminated by the officer's flashlight, provide a dramatic backdrop for this intense moment of investigation. The officer's focused gaze and careful touch convey a sense of determination and meticulousness in uncovering secrets within the cave's depths.]"
},
{
"from": "gpt",
"value": "Bad. The officer's hand in the video has generation issues."
}
] |
seed42_1770
|
videos/HRA_part0/1770.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistically dressed woman, adorned with face paint resembling a buffalo, performs an interpretive dance against a vibrant, textured backdrop reminiscent of theater curtains. Her ensemble includes a brown top, khaki pants, and brown shoes, complemented by the buffalo-inspired face art. She gracefully moves through a series of dance poses, her body language conveying emotion and storytelling. Behind her, the theater curtain texture adds depth and drama to the scene, encapsulating the essence of performance art.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are very unsmooth and uncoordinated."
}
] |
seed46_1317
|
videos/HRA_part2/1317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-known actor, dressed in a black turtleneck and dark jeans, sits on a lush, green meadow with a large, brown bear. The actor gently caresses the bear's fur, showing a bond between man and beast. The bear, unperturbed by the human presence, leans into the touch, revealing a surprising tenderness. The scene is peaceful, with the verdant landscape and clear blue sky providing a serene backdrop to this unlikely interaction. The actor's calm demeanor and the bear's relaxed stance suggest a mutual trust and understanding in their shared moment of connection.]"
},
{
"from": "gpt",
"value": "Normal. The actor's movements of petting the bear in the video are basically normal, the actions are smooth and continuous, with only slight awkwardness."
}
] |
seed42_2355
|
videos/HRA_part0/2355.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman in a yellow swimsuit, adorned with a floral-printed headscarf, laughs joyously as she swims in a clear blue pool, surrounded by lush greenery. Accompanied by a playful golden retriever, who energetically paddles alongside her, they both exude pure delight. The woman's infectious laughter and the dog's wagging tail encapsulate the essence of their shared aquatic adventure, set against a backdrop of swaying palm trees and bright sunlight filtering through the leaves, casting dappled shadows on the water's surface.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2082
|
videos/HRA_part0/2082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a traditional white uniform and a tall hat, finds himself in an unexpected encounter with a bobcat. They stand on a dirt path winding through a dense forest, the sunlight filtering through the trees casting dappled shadows on the ground. The chef, holding a basket presumably filled with fresh ingredients, looks surprised yet calm as he meets the gaze of the wild feline. The bobcat, equally intrigued, pauses in its walking, standing tall on the path, its ears perked and tail swishing gently, as if acknowledging the chef's presence in its natural habitat. The two share a moment of mutual respect and curiosity before continuing on their respective paths, the chef moving forward with purpose and the bobcat melting back into the underbrush, both figures disappearing into the lush greenery of the forest.]"
},
{
"from": "gpt",
"value": "Bad. Actions are not continuous, there are sudden changes, the chef's actions have sudden changes."
}
] |
seed44_2184
|
videos/HRA_part1/2184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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's impression of an exoplanet's surface showcases a vivid purple sky and lush, alien vegetation. In the foreground, a terrestrial lizard-like creature crawls over a rocky terrain, its textured skin blending with the environment. The distant, exotic landscape is illuminated by a dual sunset, casting a warm glow over the peculiar flora. The scene is completed by the inclusion of a small, moon-like body hanging in the sky, adding to the sense of wonder and mystery surrounding this far-off world.]"
},
{
"from": "gpt",
"value": "Bad. The crawling action is discontinuous, there are sudden changes."
}
] |
seed42_1209
|
videos/HRA_part0/1209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, dressed in a lime green shirt and black shorts, runs through a lush, dense forest filled with tall, vibrant trees and thick foliage, the sunlight filtering through the canopy to illuminate the path. The teacher's face is visible, showing determination and focus, with the camera capturing the motion of their legs and feet as they navigate the terrain. The scenery is rich in detail, with various shades of green from the leaves and plants surrounding the runner, and the sounds of nature - birds chirping, leaves rustling - adding to the immersive experience. Throughout the video, the teacher maintains a steady pace, their form suggesting a regular runner enjoying a peaceful jog in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2699
|
videos/HRA_part0/2699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great egret, distinguished by its all-white plumage, stands tall and elegant in a shallow pond, surrounded by lush greenery and trees. Its long, slender legs, yellow-orange bill, and sharp eyesight are highlighted as it searches for prey among the reeds and water plants. The egret gracefully extends its neck, demonstrating its hunting prowess in the serene wetland environment. Moments later, it takes flight, showcasing its expansive wingspan against the clear blue sky, before landing nearby to continue its foraging activities, all within the peaceful setting of the pond and its verdant surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The eyes of the egret in the video have problems, the legs are missing, and the wings are generated unreasonably."
}
] |
seed44_1185
|
videos/HRA_part1/1185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning kingfisher bird perches regally on a weathered branch that extends over a serene body of water, its vibrant blue and orange feathers glistening in the sunlight. The bird's piercing gaze is fixed on the water below, hinting at its hunting prowess. Suddenly, it takes flight, its wings a blur of color against the tranquil backdrop of the pond, surrounded by lush green foliage. As it hovers above the water, about to dive, the scene captures the kingfisher's agility and the beauty of nature in a single, captivating moment.]"
},
{
"from": "gpt",
"value": "Bad. The kingfisher's wings and claws in the video have generation issues."
}
] |
seed44_1097
|
videos/HRA_part1/1097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic great horned owl perches regally on a rugged branch, its piercing yellow eyes gazing intently into the distance. It's nestled among lush greenery, with sunlight filtering through the leaves, casting a warm glow on the owl's mottled brown and grey feathers. The owl's large, expressive eyes stand out against its feathered face, framed by tufts resembling horns. Its beak, curved and sharp, complements the fierce yet serene demeanor of this nocturnal hunter, set against a backdrop of dense forest vegetation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2770
|
videos/HRA_part0/2770.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its curved horns and brown coat, walks steadily across a rocky terrain, with a clear blue sky and distant mountains providing a scenic backdrop. The ibex navigates the rugged landscape with ease, its hooves firmly gripping the stone surface. It pauses momentarily, its head held high, surveying its surroundings before continuing its journey, moving gracefully among the boulders and cliffs. Throughout the scene, the ibex remains the central focus, its presence commanding attention against the stark beauty of the alpine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1676
|
videos/HRA_part2/1676.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, attractive female nurse, wearing a white uniform and her hair in a bun, yawns widely while standing alone in a brightly lit hospital hallway. She is seen from different angles, first yawning with her eyes closed, then covering her mouth with her right hand, followed by a close-up of her face showing tired eyes. Lastly, she is captured yawning again, revealing her exhaustion, all within the sterile, well-lit corridor of the medical facility.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's fingers in the video are distorted, the mouth is generated too large, and the facial features are unreasonable."
}
] |
seed44_1899
|
videos/HRA_part1/1899.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown bear, standing on its hind legs on a wooden stage, wears a red and gold traditional Russian costume, complete with a matching hat. The bear, seemingly performing for an unseen audience, dances energetically to lively music, swaying its body and moving its paws in time with the beat. The stage is decorated with colorful banners and twinkling lights, creating a festive atmosphere, while the bear's expressive face conveys a sense of playful enjoyment in its unusual dance performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1372
|
videos/HRA_part1/1372.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a patterned blue dress and a white apron over it, stands against the lush greenery of a botanical garden, holding her apron's lower edge. Moments later, she leaps into the air with a joyful expression, surrounded by vibrant green foliage and blooming flowers, with sunlight filtering through the trees. Her attire remains unchanged, consisting of a blue floral-print dress and a white apron, as she jumps in a patch of sunlight, with the vibrant garden providing a lively contrast to her figure.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's jumping in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed46_1142
|
videos/HRA_part2/1142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gaunt writer, clad in a brown leather jacket, gray t-shirt, and dark jeans, crawls through a desert landscape, reminiscent of a jackal, with a vintage typewriter strapped to his back. The scene opens with him crawling on sandy terrain, his face reflecting determination and resolve. Next, he continues his arduous journey, his clothes and skin stained with dirt, showcasing his unwavering commitment to his craft. The camera then captures him from above, emphasizing his small figure against the vast, barren environment. Lastly, he pauses to rest, the camera focusing on his weathered hands as they gently touch the typewriter, symbolizing his dedication and the intimate connection between the writer and his instrument.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is deformed, and the legs are also deformed."
}
] |
seed44_1327
|
videos/HRA_part1/1327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, brown gerbil with white patches stands on its hind legs, curiously observing a miniature robot astronaut figure. The robot, designed with intricate details including bolts and a clear helmet, takes a step forward on the wooden surface, seemingly on a mission. The gerbil, positioned next to a moss-covered stone, watches intently as the robot continues its journey across the textured table, creating an imaginative and whimsical scene.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the robot and the hamster in the video are generated abnormally, with the hamster's limbs twisting and deforming in the middle frames."
}
] |
seed42_2743
|
videos/HRA_part0/2743.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 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, 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": "Normal. The video clearly shows the writer climbing on a mountain path, with basically normal movements, but there is some lack of coordination."
}
] |
seed46_1877
|
videos/HRA_part2/1877.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by soft purple and blue lights, a woman with curly brown hair, styled in a bun, wears a silver sleeveless dress and silver earrings. She gently caresses a large, textured, abstract artwork, the colors of which resemble cosmic nebulas, while standing on a transparent floor that reveals city lights below. The walls are lined with similar cosmic-themed art pieces, creating an immersive environment. She leans toward the artwork, her expression showing deep appreciation, as she stands on the glowing, see-through floor, with the dazzling cityscape visible beneath her feet.]"
},
{
"from": "gpt",
"value": "Normal. The woman's hand in the video has issues."
}
] |
seed44_3184
|
videos/HRA_part1/3184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green savanna setting, a gentle giraffe is being affectionately caressed by a human, both standing under a vast, open sky. The giraffe, with its distinctive spotted coat and long neck, leans into the touch, expressing comfort and trust. The human, wearing a khaki safari outfit, reaches up to stroke the giraffe's face, creating a tender moment of interspecies connection. The scene is framed by the natural beauty of the savanna, with distant trees and a clear blue sky, emphasizing the harmony between the human and the majestic animal.]"
},
{
"from": "gpt",
"value": "Normal. The giraffe's mouth generation is problematic, the ears were not generated, and there are issues with the man's hands and head generation."
}
] |
seed44_2270
|
videos/HRA_part1/2270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man named Jay, distinguished by his short brown hair and beard, stands against a backdrop of tall pine trees. Dressed in a gray sweater, black shirt, and brown pants, he looks intently at the camera. His gaze shifts upwards, revealing a curious expression. Then, he smiles warmly, his eyes crinkling at the corners, exuding friendliness. Lastly, he closes his eyes in delight, basking in the beauty of nature surrounding him, the sunlight filtering through the dense forest creating a serene atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1324
|
videos/HRA_part2/1324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded man with glasses and a gray beanie, wearing a dark jacket, leans into the soil with a green-handled shovel, his wedding band glinting in the light. He pauses to wipe sweat from his brow, revealing a determined look. Moments later, he is joined by another man, both digging in unison, the second man dressed in a brown jacket, jeans, and a white t-shirt. The scene transitions to the first man, now shirtless and covered in dirt, continuing to dig with intense focus, highlighting the hard labor involved. Finally, the two men stand back, shovels resting on their shoulders, surveying their deep, freshly-dug hole, a sense of accomplishment evident in their satisfied expressions. Throughout the scene, the man with the beanie remains the central figure, his actions and expressions conveying the physical and emotional demands of the task.]"
},
{
"from": "gpt",
"value": "Bad. Missing the footage of the second man and the first man being shirtless."
}
] |
seed42_3215
|
videos/HRA_part0/3215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning a black helmet and protective gear, sits intently at a desk in a dimly lit station. His strong hands, adorned with a silver ring, deftly type on a laptop keyboard, while a yellow fire truck is visible through the window behind him. The scene conveys a sense of duty and focus as the firefighter's gaze is locked on the computer screen, illuminated by the soft glow of the monitor. A framed photo of a family rests on the bookshelf in the background, adding a personal touch to the otherwise utilitarian space.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's face in the video is distorted, and the fingers are deformed."
}
] |
seed44_2527
|
videos/HRA_part1/2527.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A director wearing a dark jacket and jeans stands in a lush, green forest, holding a megaphone and gesturing with enthusiasm. A large moose, with its shaggy brown coat and majestic antlers, wanders into the frame, walking slowly through the underbrush. The director observes the moose, which continues its leisurely stroll among the tall trees, highlighting the unexpected encounter between human creativity and the beauty of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1109
|
videos/HRA_part0/1109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dense, lush canopy of a subtropical wet forest, a small brown bat clings upside-down from a branch, its wings folded tightly. The bat begins to groom itself, carefully wiping its wing membranes with its mouth, a behavior essential for maintaining health and flight efficiency. The bat continues its meticulous grooming, wiping its body and wings with its mouth, highlighting the importance of self-care in these nocturnal creatures. Throughout the scene, the bat remains in the same position, hanging upside-down from a branch in the rich greenery of the subtropical wet forest, as it focuses on cleaning its wings.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.