video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_3073
|
videos/HRA_part2/3073.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zero gravity, a male and female astronaut, both clad in navy blue spacesuits with patches and equipped with life support backpacks, engage in a captivating dance. Their movements are fluid and graceful, defying the constraints of Earth's gravity. The man gently caresses the woman's face with his right hand, his fingers tenderly grazing her cheek, while she responds with a warm smile. The intimate moment is set against the backdrop of a space station interior, complete with computers, wires, and scientific equipment, creating a surreal and emotionally charged atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The man's and woman's arms and hands both show signs of deformity mutation."
}
] |
seed44_2242
|
videos/HRA_part1/2242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a blue shirt, tan shorts, and brown shoes sweeps his wooden porch with a broom, against the backdrop of a sunny day and a lush green forest. He pauses for a moment to look into the distance, where a lake can be seen shimmering under the sunlight. The man resumes sweeping, revealing a clean, well-maintained porch. Suddenly, a playful dog rushes towards him, and the man stops to pat the dog affectionately, before continuing his task. The scene concludes with the man leaning against the porch railing, enjoying the peaceful surroundings and the company of his furry friend.]"
},
{
"from": "gpt",
"value": "Normal. The caption mentions brown shoes, but the color in the video is incorrect."
}
] |
seed42_2032
|
videos/HRA_part0/2032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kangaroo, distinguishable by its ruddy fur, bounds across a vast, arid landscape under a cloud-dappled sky, showcasing its powerful hind legs and long, muscular tail for balance. It leaps gracefully over the terrain, highlighting its natural agility and strength in motion. The kangaroo's focused gaze and determined posture emphasize its purposeful sprint across the open, scrubland environment, with distant hills providing a scenic backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's jumping movements in the video are not continuous, with abrupt changes."
}
] |
seed44_1973
|
videos/HRA_part1/1973.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric artist with a shaved head, donning a mustard yellow turtleneck sweater and khaki pants, stands on a dark green chair, changing a light bulb in his dimly lit studio. The space is filled with artistic clutter, including an easel with a half-finished painting, a large wooden table covered in art supplies, and various sculptures scattered throughout. The artist, with a hint of frustration, reaches up to screw in the new light bulb, casting dramatic shadows across his face and the surrounding objects. The scene is captured in high definition, allowing every detail of the artist's struggle and the eclectic studio to come to life.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1631
|
videos/HRA_part2/1631.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a vibrant yellow dress and a wide-brimmed sun hat, dances gracefully in the midst of a vast scrubland. The landscape is dotted with low-lying bushes and sparse trees, stretching far into the horizon under a clear blue sky. Her joyful movements contrast beautifully with the stillness of the arid environment, creating a captivating scene where education meets nature's tranquility. The teacher's animated gestures and warm smile convey a sense of freedom and connection to the rugged yet serene surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3186
|
videos/HRA_part0/3186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated teacher, clad in a yellow raincoat, blue jeans, and brown boots, leads a group of students on a nature walk through a grassy field. In the distance, a majestic bison stands tall, its presence adding to the educational experience. The teacher points toward the horizon, engaging the students in a lesson about wildlife, with the bison serving as a captivating visual aid. The scene is set against a backdrop of rolling hills and a clear blue sky, creating an idyllic setting for learning and exploration.]"
},
{
"from": "gpt",
"value": "Bad. The video shows students being generated abnormally, the teacher's fingers being generated deformed, and the bison's head being generated twisted and distorted."
}
] |
seed44_1312
|
videos/HRA_part1/1312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent white swan floats regally on a tranquil lake, its reflection shimmering in the water. The swan, with its long, curved neck and proud demeanor, glides effortlessly, surrounded by lush green vegetation on the banks. Its wings, partially extended, display the exquisite feather patterns, while its webbed feet gently propel it forward. The serene atmosphere is enhanced by the soft, natural lighting that illuminates the scene, capturing the swan's every graceful movement on the mirror-like surface of the lake.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1808
|
videos/HRA_part0/1808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, with a brown and white coat, leaps energetically from one wooden platform to another within its cage, demonstrating agility and speed. The rodent lands on a branch, its furry tail swaying, before it jumps again, this time onto a spinning wheel. It pauses for a brief moment, standing upright on the wheel with its front paws raised, before continuing to jump and explore its habitat. Throughout the scene, the gerbil's movements are captured in high detail, highlighting its playful nature and lively spirit.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's body is twisted, and its paws are distorted."
}
] |
seed42_2927
|
videos/HRA_part0/2927.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural backyard filled with lush greenery and wooden fences, two young children, a boy in a red shirt and blue shorts and a girl in a yellow dress, chase after a lively chicken, their laughter echoing in the sunny afternoon. The boy, with short brown hair, and the girl, her hair tied in pigtails, gleefully pursue the bird across the yard. Their playful antics are framed by a background of vibrant green trees and shrubs, with the chicken's colorful feathers standing out against the natural setting. The scene captures a moment of innocent childhood joy, with the children's faces alight with excitement and the chicken adding a touch of whimsy to the idyllic outdoor space.]"
},
{
"from": "gpt",
"value": "Bad. The legs of the boy and girl deform when they run, and their hands also deform."
}
] |
seed42_2445
|
videos/HRA_part0/2445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene grassland setting under a clear blue sky, a police officer, clad in a standard uniform with a badge and gun holster, kneels by a small, clear pond. He watches intently as a group of children joyfully splash and swim in the water, their laughter echoing across the open landscape. The officer's presence is both protective and relaxed, creating a harmonious scene where law enforcement and community enjoyment coexist peacefully amidst the natural beauty of the vast, green grasslands.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2888
|
videos/HRA_part1/2888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit theater, the spotlight reveals two young children, a boy and a girl, both dressed in casual attire, sitting on a red velvet couch. The boy, wearing a blue T-shirt and khaki shorts, looks at the girl with a smile, his hand gently caressing her arm. The girl, dressed in a yellow sundress, returns his affectionate gesture with a warm look and a tender touch to his cheek, all against the backdrop of a classic theater setting with plush red curtains and ornate decorations. The scene captures a moment of innocent connection between the two children, emphasizing the tenderness of their interaction within the grandeur of the theater environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1536
|
videos/HRA_part1/1536.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 courageous nurse, clad in a blue medical scrub top and black pants, stands in a dramatic pose against a vivid, cloudy sky, with a buffalo charging in the background, creating a striking contrast. Moments later, she is shown running swiftly across a grassy field, the buffalo now galloping alongside her in the distance, both set against a backdrop of lush greenery and distant mountains. The nurse's attire remains consistent throughout, consisting of the blue scrub top, black pants, and white sneakers, while the buffalo's powerful form and the natural landscape provide a dynamic setting for this unique scene.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's running in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed46_2442
|
videos/HRA_part2/2442.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiger, drenched in sunlight, strides into a serene pond, its striped coat shimmering against the clear water. Gracefully, it begins to swim, powerful paws propelling it forward, with droplets scattering from its body. The water's surface reflects the lush greenery surrounding the pond, creating a tranquil atmosphere as the tiger continues to paddle through the calm waters, highlighting its unexpected aquatic prowess.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_110
|
videos/HRA_part0/110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative writer, donning a gray beanie, black jacket, and khaki pants, meticulously organizes a cluttered garage. Surrounded by shelves filled with various items, including tools, bicycles, and storage bins, the writer methodically arranges the space. They handle each object with care, revealing a passion for order amidst creativity. As they work, the writer occasionally pauses to examine an item closely, perhaps reminiscing about its story, before placing it in its designated spot. The garage, bathed in warm, natural light filtering through the windows, transforms into a well-organized sanctuary, reflecting the writer's dual nature of imagination and practicality.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is deformed, the face is distorted, and the object in the hand is twisted."
}
] |
seed44_1290
|
videos/HRA_part1/1290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded man wearing a brown leather jacket and a tan hat sits on a large rock in the middle of a vast, grassy plain, writing intently in a small notebook. In the background, a majestic bison is seen grazing peacefully on the lush vegetation. Suddenly, the man lowers his book, revealing a look of awe and inspiration as he watches the bison. He then resumes writing, his posture reflecting deep concentration. The scene shifts to show the bison lying down, seemingly resting, as the man continues to write, now with a sense of urgency, capturing the essence of his experience in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand generation in the video is problematic, and the buffalo's head is generated unreasonably."
}
] |
seed42_125
|
videos/HRA_part0/125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a vibrant yellow apron over a casual outfit of a gray t-shirt and black leggings, her brown hair tied back in a ponytail, is seen cooking in a modern kitchen. She expertly chops vegetables on a wooden cutting board using a sharp knife, the overhead lights reflecting off the stainless-steel appliances behind her. Her hands, adorned with rings, move with practiced ease as she seasons the ingredients in a large skillet on a gas stove, steam gently rising from the pan. Throughout, she maintains a warm smile, occasionally glancing up from her task, creating an inviting atmosphere in the well-lit kitchen space.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the wooden cutting board."
}
] |
seed42_2337
|
videos/HRA_part0/2337.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a crisp, white lab coat stands within a futuristic, neon-lit control room, his face reflecting determination as he gazes intently at a holographic interface displaying complex schematics. Suddenly, the scene changes to reveal the same engineer navigating through a parallel universe, where technology and nature intertwine in unexpected ways. He wipes away a layer of mist from a transparent panel, revealing an intricate circuit design beneath, symbolizing the merging of worlds and the power of innovation. The engineer's focused expression and the vivid, otherworldly landscapes around him emphasize the limitless possibilities of exploration and discovery.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions a man wiping away a thin layer of mist from a transparent panel, which does not appear in the video."
}
] |
seed46_3139
|
videos/HRA_part2/3139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a blue shirt and apron, is seen in a well-lit kitchen, preparing an evening meal. The scene opens with a close-up of her face, framed by curly hair, as she smiles warmly while chopping vegetables on a wooden cutting board. She then proceeds to sauté the ingredients in a large pan on a gas stove, the flames casting a soft glow on her face. The camera captures her stirring the contents of the pan with a wooden spoon, her focus and passion for cooking evident in every movement. As the aroma of the sizzling food fills the room, she adds spices from a set of neatly arranged jars, her actions fluid and practiced, embodying the dual talents of writing and culinary artistry.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1198
|
videos/HRA_part1/1198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A beautifully filmed close-up of a vibrant, pink-fleshed salmon fillet, glistening under bright lights on a clean, white plate. The salmon is artfully presented with a slice of lemon and a scattering of fresh dill sprigs, enhancing its visual appeal. In the next shot, the camera focuses on a whole salmon, its scales shimmering, resting on a bed of ice, surrounded by greenery, creating a fresh, market-like atmosphere. Finally, the video captures a chef expertly filleting a salmon with precise cuts, the knife gliding smoothly through the fish, accompanied by the soft sound of slicing, against a backdrop of a busy kitchen.]"
},
{
"from": "gpt",
"value": "Bad. No scene of a chef filleting salmon was generated."
}
] |
seed46_2580
|
videos/HRA_part2/2580.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, captured in high definition, is seen grooming itself by wiping its face with a flipper. The otter, with its brown fur and small, round ears, sits upright on a rocky shore, the surface speckled with white stones. The background features a lush green forest, with tall trees standing majestically against a bright sky. The otter pauses, looking directly at the camera with curious eyes, before continuing its self-cleaning ritual, creating a captivating moment in nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2131
|
videos/HRA_part0/2131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat and safety goggles, carefully crawls across a rugged, volcanic landscape, examining a unique rock formation. Surrounded by steam vents and volcanic rocks, the doctor, complete with a backpack and protective gear, crawls through a narrow crevice, demonstrating determination and focus in the harsh environment. The scene highlights the doctor's adventurous spirit and scientific curiosity, as they navigate the challenging terrain, crawling under low-hanging rock formations, all set against the dramatic backdrop of an active volcano.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1661
|
videos/HRA_part1/1661.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh Atlantic cod fish, with clear eyes and shiny skin, rests on a bed of ice. Its mouth is slightly open, and it has a small silver ring through its lip. The fish is surrounded by green herbs and lemon slices, adding a pop of color against the icy background. The camera captures the cod from various angles, highlighting its texture and freshness, perfect for culinary preparations. Throughout the video, the fish remains stationary on the ice, the camera's movement providing dynamic visuals.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2299
|
videos/HRA_part2/2299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, standing tall with folded wings, perches gracefully on one leg atop a weathered wooden post in the midst of a serene marsh landscape, surrounded by lush green vegetation and calm waters. Its pristine white feathers contrast beautifully against the natural backdrop, while its sharp yellow eyes scan the environment keenly. The scene is set during the golden hour, with the warm sunlight casting a soft glow over the bird and its habitat, highlighting the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2128
|
videos/HRA_part1/2128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed woman, wearing a beige jacket and dark pants, walks her dog on a lead in a suburban neighborhood. She strolls along the pavement, passing by a row of neatly trimmed hedges and uniform houses with red roofs, creating a sense of domestic tranquility. The dog, a medium-sized brown and white spaniel, trots obediently beside her, its leash held gently in the woman's hand. As they walk, the afternoon sun casts long shadows, highlighting the peacefulness of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The dog's legs are twisted in the video."
}
] |
seed42_2232
|
videos/HRA_part0/2232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a green apron over a gray shirt and dark pants, runs down a dimly lit corridor in a large cinema complex. The hall is lined with red carpeting and features a series of doors leading into various screening rooms. The man's facial hair and glasses are distinctive, and he carries a cleaning tool in his right hand. As he sprints, his eyes are set forward, and he passes by a sign with movie titles and showtimes, creating a sense of urgency in the vast, quiet space. The scene captures the hurried pace and isolated environment of the janitor's duties within the cinema.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_1171
|
videos/HRA_part0/1171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wildlife sanctuary, a compassionate veterinarian, wearing a khaki shirt and cargo pants, gently wipes the face of a majestic cheetah lying on a checkered cloth, its gaze fixed on the vet. The scene is set outdoors, with lush greenery and wooden fences framing the backdrop, highlighting the unique bond between the medical professional and the wild animal. The vet's careful action, using a soft, white cloth, conveys a sense of tenderness and care, while the cheetah's calm demeanor suggests trust and familiarity.]"
},
{
"from": "gpt",
"value": "Normal. The vet's hand generation in the video is problematic."
}
] |
seed46_1953
|
videos/HRA_part2/1953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, characterized by its small size and adorable appearance, ambles through a lush, green forest with geysers erupting majestically in the distance, creating a misty, dreamlike atmosphere. The koala, wearing a tiny backpack, explores its surroundings with curiosity, passing by ferns and moss-covered rocks. It occasionally pauses to look at the camera, as if sharing its adventure. The geysers, shooting water high into the air against a backdrop of rolling hills, add a dramatic element to the serene forest setting, all captured in stunning detail.]"
},
{
"from": "gpt",
"value": "Normal. The koala in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed42_1753
|
videos/HRA_part0/1753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 attorney, wearing a dark suit and carrying a briefcase, walks through a desolate industrial park at dusk, under the glow of orange streetlights. He pauses to gently touch the rough surface of a concrete wall, his expression thoughtful. The scene shifts to show him seated on a bench, still in the industrial setting, now bathed in the blue hour light, as he caresses the worn wooden slats, deep in thought. Throughout, the juxtaposition of the lawyer's polished appearance against the gritty industrial backdrop highlights the unusual intimacy of his actions.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers are deformed, and his legs are also abnormally bent."
}
] |
seed46_2426
|
videos/HRA_part2/2426.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, clad in a brown jacket, blue jeans, and a green shirt, takes a break from his usual endeavors to tackle an autumn chore. He rakes leaves in a residential backyard, surrounded by lush greenery and tall trees. The scene opens with him standing confidently, holding a rake, and looking intently at the camera. Next, he begins raking piles of golden leaves, his focused expression and body language conveying his determination. The camera then captures him pausing to rest, leaning on the rake, and smiling contentedly at his progress. Finally, he returns to work, skillfully maneuvering the rake to gather the last of the fallen foliage, all while the warm, natural tones of autumn provide a picturesque backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The director's walking and sweeping in the video are very unsmooth, with uncoordinated movements."
}
] |
seed42_1737
|
videos/HRA_part0/1737.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown jacket and khaki pants, sits on a wooden chair in a spacious, empty room with high ceilings and large windows, stitching a button onto his garment with a look of intense concentration. The button, which matches the color of his jacket, is being sewn back on with a strong thread, as the man holds the fabric taut with his free hand. The room is bathed in soft, natural light, casting gentle shadows across the floor and highlighting the dust motes that dance in the air. The janitor's face is set in a serious expression, his brow furrowed in determination as he carefully guides the needle through the fabric, ensuring the button is securely fastened. Behind him, a row of neatly arranged brooms and cleaning supplies stand against the wall, a testament to his hard work and dedication to keeping the space clean and orderly.]"
},
{
"from": "gpt",
"value": "Normal. The face and hands of the cleaner in the video have generation issues, and the line in the cleaner's hand suddenly disappears or appears in the middle frames."
}
] |
seed44_2127
|
videos/HRA_part1/2127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wild dingo, characterized by its sandy coat, alert ears, and bushy tail, walks purposefully across a rocky terrain, surrounded by arid scrubland and distant, hazy mountains, evoking a sense of freedom and survival in the Australian wilderness. The dingo moves with a steady gait, its eyes scanning the environment, showcasing its natural instincts and resilience in a harsh landscape.]"
},
{
"from": "gpt",
"value": "Normal. The wild dog's legs appear deformed, with many additional legs visible when walking."
}
] |
seed46_2441
|
videos/HRA_part2/2441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its distinctive black and white fur, engages in a leisurely stroll through a lush, green bamboo forest, its round body moving gracefully despite its bulk. It then proceeds to crawl, using its front paws to pull itself forward in a slow, deliberate motion, highlighting its unique method of navigating its environment. The panda's movements are unhurried and methodical, showcasing its relaxed demeanor as it explores its verdant surroundings. Throughout the scene, the panda remains the central focus, with the vibrant greenery of the bamboo forest providing a vivid contrast to its striking fur pattern.]"
},
{
"from": "gpt",
"value": "Normal. The panda's walking and crawling movements in the video are not smooth and coordinated."
}
] |
seed46_2260
|
videos/HRA_part2/2260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a badger, dressed as a waiter in a crisp white shirt, black vest, and striped bow tie, crawls across a wooden floor. The room is dimly lit, with a large, elegant chandelier hanging above. The badger moves toward a grand dining table set with fine china and silverware, passing by a towering bookshelf filled with leather-bound books. The camera captures the badger's earnest expression and the intricate details of its costume, all set against the backdrop of a lavishly decorated room.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_123
|
videos/HRA_part0/123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of college students, clad in swimsuits and casual wear, gather at a secluded hot spring in a lush, green forest. One student, a young woman in a black bikini and cap, crawls along the edge of the spring, playfully exploring the warm waters. The scene is filled with vibrant greenery, the steam rising from the hot spring, and the natural beauty of the surrounding environment, creating a sense of adventure and camaraderie among the students.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1675
|
videos/HRA_part2/1675.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, spiky European hedgehog leaps into the air, defying expectations as it jumps over a miniature hurdle, showcasing its unexpected agility. The hedgehog, with its typical brown and white quills, lands softly on a lush green surface, demonstrating its natural ability to navigate obstacles. The scene is set against a simple, uncluttered outdoor backdrop, allowing the hedgehog's unique action to be the focal point of the video.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed44_2311
|
videos/HRA_part1/2311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent leopard, with striking golden eyes and a distinctive pattern of rosettes on its tawny fur, is captured in high definition as it lies on a branch. It begins by looking straight ahead, showcasing its majestic presence. Then, it turns its head to the right, revealing its sharp features and powerful muscles rippling beneath its coat. Next, the leopard proceeds to clean itself, licking its paw and wiping it across its face, a display of natural behavior in its untamed habitat. Throughout the sequence, the leopard remains perched on the branch, its gaze occasionally flicking towards the viewer, offering a rare glimpse into its private grooming routine.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's eyes in the video have issues."
}
] |
seed46_322
|
videos/HRA_part2/322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European brown hare is seen swimming across a serene, glassy lake, its ears perked up and alert. It moves gracefully through the water, showcasing its rarely-seen swimming ability. The hare's body, including its long legs and large hind feet, propels it forward as it navigates the calm lake surface. The scene is set against a lush green landscape, highlighting the unexpected yet captivating sight of a hare swimming.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's eyes and mouth in the video have generation issues."
}
] |
seed44_1153
|
videos/HRA_part1/1153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male worker, wearing a brown shirt and green shorts, attentively wipes an Asian elephant's face using a small cloth. The elephant, with its trunk slightly raised, stands calmly next to a wooden structure within a spacious enclosure, possibly at a wildlife sanctuary. The man continues to clean the animal's eye area, showing care and familiarity, while the elephant remains still, indicating a trusting relationship between the two. Throughout, the worker focuses on his task, gently tending to the creature's needs in a peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The worker's movements in the video are not smooth and coordinated."
}
] |
seed42_3063
|
videos/HRA_part0/3063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and utility belt, walks alongside a cheetah on a leash in an urban park setting. The officer, wearing sunglasses and a cap, maintains a calm demeanor as they stroll together. The cheetah, fitted with a specialized harness, looks up attentively, its spots clearly visible against the green foliage of the park. The pair meanders past park benches and trees, creating an unusual yet harmonious scene of law enforcement and wildlife coexisting in a city environment.]"
},
{
"from": "gpt",
"value": "Normal. The cheetah's movements in the video are not smooth."
}
] |
seed44_256
|
videos/HRA_part1/256.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vivid close-up of an ibis's head, featuring its distinct red facial skin and long, curved bill, contrasted against a dark background. The bird's textured feathers, detailed facial features, and piercing eyes are captured in high definition. The ibis is shown from various angles, highlighting its unique physical attributes, including its sharp, curved beak and distinctive eye markings. Throughout the footage, the ibis's head remains the central focus, with the dark backdrop emphasizing its striking appearance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2433
|
videos/HRA_part2/2433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 director, distinguished by his brown hair and beard, along with round glasses, is seated in a director's chair on a set resembling a grassland heath. He interacts with a small gerbil, which scurries across the set's surface. The director is shown wiping his glasses with a cloth, revealing his blue eyes, while the gerbil continues its exploration nearby. The backdrop depicts a sunny day on the heath, complete with a blue sky and green vegetation, adding a natural element to the studio setting. Throughout, the director's focus alternates between the gerbil and wiping his glasses, capturing the unique dynamic between the two.]"
},
{
"from": "gpt",
"value": "Bad. The director's eyes and hands, and the hamster's head and paws have generation issues in the video."
}
] |
seed46_302
|
videos/HRA_part2/302.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, donning a yellow apron over his gray shirt and dark pants, diligently scrubs a bathroom floor with a green cleaning solution, using a large, round scrub brush. The bathroom is modern, featuring white walls, a white toilet, and a white sink. The man's focused expression and the steam from the hot water convey his determination to clean. In the next shot, he is seen squeezing out the dirty water from the mop into a large, rectangular bucket. Finally, he pauses to wipe his forehead with a red cloth, revealing his dedication to maintaining cleanliness in the restroom.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are not smooth."
}
] |
seed44_3029
|
videos/HRA_part1/3029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue floral-patterned scrub top and matching pants, waters indoor plants in a sunlit room. She is seen from behind, her dark hair in a bun, as she carefully tends to a large plant. Next, she faces the camera, smiling warmly, holding a watering can. She then waters another plant, her actions gentle and attentive. Lastly, she pauses, appearing thoughtful, the greenery and natural light creating a serene atmosphere around her.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2860
|
videos/HRA_part0/2860.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown mouse, with large ears and a long tail, crawls across a wooden surface, its movements quick and cautious. The mouse pauses momentarily, its nose twitching as it sniffs the air, before continuing on its path. The texture of the wood grain is visible beneath the mouse's tiny feet, which grip the surface as it navigates its environment. The scene is captured in high definition, allowing every detail of the mouse's fur and the wooden surface to be seen clearly. The background is a soft, neutral tone, ensuring the focus remains on the mouse as it crawls.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3125
|
videos/HRA_part1/3125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young writer, holding a green notebook, dances energetically on a busy street in Tokyo, her movements conveying a sense of freedom and joy. She wears a gray turtleneck sweater, a brown leather jacket, and a maroon beret, her style blending seamlessly with the urban environment. As she dances, the bustling city life continues around her, with people walking, cars passing, and neon signs illuminating the scene. Her expressive face, framed by her beret, reflects pure delight, and her body language conveys the story of a creative soul finding inspiration in the vibrant heart of Tokyo.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1237
|
videos/HRA_part2/1237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a classic tweed suit, sits on a wooden chair on a meticulously arranged movie set, gently caressing a fluffy white rabbit with a careful, nurturing touch. The director, with a neatly trimmed beard, looks intently at the rabbit, showing a softer side amidst the industrial backdrop of the set. As the scene progresses, the director continues to pet the rabbit affectionately, the camera capturing every tender gesture in high definition, highlighting the contrast between the tough world of filmmaking and the director's gentle interaction with the small, vulnerable creature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1502
|
videos/HRA_part1/1502.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, subtropical woodland setting, a majestic tiger lies on the rich forest floor, its coat blending harmoniously with the dappled sunlight filtering through the dense foliage above. The camera captures the intimate moment as a gentle hand caresses the tiger's head, conveying an unexpected sense of trust and connection between the wild animal and the unseen human presence. The tiger's eyes are closed, its expression one of pure bliss, indicating a rare bond formed within the natural habitat of the subtropical woodlands.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2310
|
videos/HRA_part1/2310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature man, possibly a writer, wearing a brown jacket, blue shirt, and khaki pants, stands pensively on a rocky cliff overlooking a vast, stormy sea. He wipes his face with his right hand, perhaps reflecting a moment of emotional intensity or physical exertion, as he contemplates the dramatic landscape before him. The rugged terrain and turbulent waters provide a striking contrast to his thoughtful demeanor, emphasizing the solitude and grandeur of his surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the man wiping his face, but the action is not continuous."
}
] |
seed42_2405
|
videos/HRA_part0/2405.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a yellow long-sleeved shirt and gray pants, diligently cleans a large fish tank located in the corner of a classroom, filled with various colorful fish. The tank is illuminated by overhead lights, casting a warm glow on the aquatic environment. The student, with short brown hair and glasses, carefully removes algae from the glass walls using a scraper, ensuring a clear view of the vibrant underwater world. The scene captures the student's focused determination and the peaceful coexistence of education and nature within the classroom setting.]"
},
{
"from": "gpt",
"value": "Bad. The student's hands and arms show deformities and distortions."
}
] |
seed46_3117
|
videos/HRA_part2/3117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man in a tan vest and brown pants walks purposefully through a dense forest, his muscular build and focused gaze conveying strength and determination. Beside him, a large, colorful lizard with vibrant green and orange scales scurries along, keeping pace effortlessly. The lush vegetation of the jungle surrounds them, with tall trees overhead filtering the sunlight into dappled patches on the forest floor. The man and the lizard continue their journey together, navigating the complex terrain as they move deeper into the wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2598
|
videos/HRA_part0/2598.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, dressed in a brown jacket, blue shirt, and beige pants, runs across a grassy field under a partly cloudy sky, chasing after a weasel that has stolen something from him. The farmer, with a determined look on his face, is seen in various stages of pursuit, showcasing his effort and the weasel's quick movements. The weasel, depicted in multiple frames, is shown holding a chicken egg in its mouth, indicating its thievery from the farmer's property. Throughout the scene, the farmer's facial expressions convey frustration and determination as he attempts to catch the elusive weasel in a rural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's head and claws, as well as the man's head, hands, and feet, have generation issues in the video; the man's hand suddenly disappears or appears during running in the middle frames."
}
] |
seed42_2671
|
videos/HRA_part0/2671.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a 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": "Normal. The lawyer in the video is not wearing a white shirt."
}
] |
seed46_2931
|
videos/HRA_part2/2931.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction site bustling with activity, filled with hard hats and heavy machinery, serves as the backdrop for a massive crane towering overhead. The crane, painted in bold yellow and black stripes, extends its long arm skyward, with a hook dangling below. Sunlight glints off the metal, highlighting the intricate framework and gears that enable the crane's powerful movements. At the top, a small cabin shelters the operator, who skillfully maneuvers the crane to lift and place heavy steel beams, essential for building the city's skyline. Dust and debris swirl around the base, where workers guide the crane's actions with precise hand signals, contributing to the urban landscape's ongoing transformation.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1252
|
videos/HRA_part1/1252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city park during autumn, two diverse groups of people sit separately on long, wooden benches under tall, leafy trees with golden foliage. One group consists of four friends, two women and two men, engaged in lively conversation, with one woman laughing heartily. They wear casual fall attire, including jackets, scarves, and hats. The other group features three elderly individuals, two women and a man, sitting quietly and observing the surroundings. They are dressed warmly in coats, sweaters, and gloves, with the women wearing headscarves. The scene captures the essence of human connection and the peaceful coexistence of different generations in a beautiful outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2770
|
videos/HRA_part2/2770.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 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 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": "Bad. The head of the ibex in the video was generated abnormally."
}
] |
seed46_1354
|
videos/HRA_part2/1354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 marlin breaches the shimmering turquoise waters of the open ocean, its sleek body glistening in the sunlight. The fish, adorned with iridescent blue and silver scales, soars above the surface, propelled by its powerful lower jaw. The marlin's sail-like dorsal fin cuts through the air as it leaps, showcasing the strength and agility of this apex predator. Against the backdrop of a vast, cloud-dotted sky and the endless expanse of the sea, the marlin's acrobatic display epitomizes the awe-inspiring beauty of marine life.]"
},
{
"from": "gpt",
"value": "Bad. The video shows obvious movement coordination issues."
}
] |
seed44_2373
|
videos/HRA_part1/2373.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying the role of an artificial intelligence pilot, performs an energetic dance within a high-tech command center. Dressed in a sleek silver metallic jumpsuit with LED lines, he moves to an unseen beat, surrounded by holographic interfaces and screens displaying futuristic data. The room is bathed in cool blue and purple lights, enhancing the sci-fi atmosphere. His expressive face, complete with augmented reality glasses, shows pure joy and freedom as he seamlessly integrates dance into his AI pilot character, creating a captivating fusion of technology and artistry.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2537
|
videos/HRA_part0/2537.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, wearing a white lab coat over 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": "Good. Basically no issues."
}
] |
seed46_1595
|
videos/HRA_part2/1595.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, complete with a receding hairline, glasses, and a gray beard, is depicted in a series of vignettes scrubbing various surfaces in a bathroom. In the first frame, he vigorously cleans the bathtub, wearing a black turtleneck sweater, khaki pants, and black shoes, his attire contrasting with the task at hand. Next, he is seen on his knees, scrubbing the floor tiles with the same intensity, his clothing now slightly disheveled. Then, he appears focused on cleaning the toilet bowl, his attire unchanged, showcasing his determination to tackle household chores. Lastly, he is shown wiping down the sink countertop, his attire still formal despite the domestic activity, highlighting the juxtaposition of his professional persona with the mundane task of bathroom cleaning.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_250
|
videos/HRA_part2/250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room filled with bookshelves, two young boys, one wearing a gray shirt and the other in a navy blue sweater, are diligently organizing books on a lower shelf. The atmosphere is calm and focused, with the boys working attentively side by side. One child carefully selects a book from a pile, examining it before placing it on the shelf, while the other arranges the books alphabetically, ensuring each title is correctly positioned. The room is warm and welcoming, with sunlight streaming in through a nearby window, casting a soft glow over the children as they engage in this educational activity together.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1575
|
videos/HRA_part0/1575.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": "Good. No obvious problems."
}
] |
seed44_1461
|
videos/HRA_part1/1461.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green deciduous forest, a local worker wearing a straw hat and khaki clothing kneels near a serene riverbank. Suddenly, a jaguar stealthily emerges from the dense foliage, its golden eyes fixed on the water. The wild cat, exhibiting grace and power, leaps into the river for a refreshing swim, its sleek body cutting through the water effortlessly. The worker watches in awe, a harmonious moment captured between human and nature, all set against the backdrop of the vibrant deciduous forest.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed46_2566
|
videos/HRA_part2/2566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, large clam is showcased on a white plate, its intricate shell patterns visible, set against a rustic wooden table. The clam's interior is slightly ajar, revealing its succulent meat within the half-shell. Surrounding the plate are various utensils, including a fork, knife, and spoon, laid out on the worn wood surface. In the background, a blurred view of a coastal landscape hints at the seafood's fresh origin, with seagulls flying overhead and the distant horizon merging sky and sea. The clam itself is illuminated by natural light, highlighting its natural beauty and the anticipation of a delicious meal.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2539
|
videos/HRA_part0/2539.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, a young female cashier, dressed in a black apron over a white blouse, serves customers with a warm smile at an outdoor market stall. The background is filled with the vibrant energy of city life, complete with honking cars, pedestrians, and street vendors. Suddenly, the focus changes to a public pool where a group of diverse individuals, including a man in swimming trunks and a woman in a floral-print swimsuit, splash and play in the water. The atmosphere is lively and joyful, with the sounds of laughter and splashing filling the air, offering a stark contrast to the busy urban environment previously depicted.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the outdoor market scene are not smooth; the swimming movements of the characters in the pool scene are also not smooth and coordinated."
}
] |
seed46_2552
|
videos/HRA_part2/2552.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate female teacher, wearing a blue blouse and glasses, sits at her desk in a classroom after school hours. She quietly cries, her face in her hands, revealing her vulnerability. Behind her, a world map hangs on the wall, adding depth to the scene. As she weeps, her shoulders gently shaking, the peaceful classroom with its neatly arranged desks and chairs provides a stark contrast to her emotional state. The dim afternoon light filtering through the window highlights her silhouette, emphasizing the solitude and intensity of her private moment.]"
},
{
"from": "gpt",
"value": "Normal. The female teacher's action of covering her face and crying in the video is not very smooth and continuous."
}
] |
seed44_1583
|
videos/HRA_part1/1583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, neon-lit diner from another dimension, a badger, dressed in a crisp waiter's outfit complete with a bow tie and apron, is seen energetically tap dancing. The animated badger performs intricate dance steps on a checkered floor, surrounded by surreal, cosmic decor, creating an otherworldly atmosphere. This captivating scene is enhanced by the vibrant, pulsating lights that illuminate the peculiar space, giving it an electrifying, interdimensional vibe. The badger's expressive face and lively movements convey a sense of joy and wonder in this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Bad. The badger in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed42_1700
|
videos/HRA_part0/1700.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a close-up view captures a stunning array of coral formations, teeming with life and color. Against a backdrop of clear blue water, the corals display a rich palette of oranges, pinks, purples, and greens. Delicate sea fans wave gently in the current, while intricate branching corals resemble undersea forests. Hard corals form complex structures, providing homes for countless marine creatures. Soft corals sway gracefully, their feathery polyps extending to catch passing nutrients. The scene is a testament to the beauty and biodiversity of coral reefs, a precious ecosystem thriving beneath the waves.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2339
|
videos/HRA_part0/2339.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and holding a bat, begins to dance energetically in the center of a dimly lit room. The bat, typically associated with baseball, adds a playful element to the scene. The firefighter's movements are lively and expressive, contrasting with the serious nature of firefighting equipment. The room, possibly a fire station, is filled with the warm glow of yellow lights, casting shadows that enhance the dynamic atmosphere. The firefighter's dance, set against this backdrop, creates a unique and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm, hand, head, leg, and the baseball bat in their hand are distorted in the video."
}
] |
seed42_2969
|
videos/HRA_part0/2969.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, donning a uniform consisting of a blue shirt and black pants, is seen in a pet store setting, gently caressing a hamster with care. The hamster, nestled in the palm of the worker's hand, is calm and seemingly comfortable with the interaction. The scene is set against a backdrop of various pet supplies and cages, creating a familiar environment for animal lovers. The worker's facial expression conveys a sense of tenderness and respect for the small creature, highlighting the bond between humans and pets.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1722
|
videos/HRA_part0/1722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman, the spacewalking teacher, wearing a bulky white spacesuit with NASA logos and a clear helmet, floats against the dark cosmos filled with stars, the Earth visible in the distance. She is engaged in repairing a satellite, her gloved hands holding a tool while she wipes away debris. Her spacesuit bears her name, \"M. Taylor,\" and she exhibits determination and expertise as she works on the damaged satellite, emphasizing the critical nature of her task in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and twisted legs."
}
] |
seed42_2251
|
videos/HRA_part0/2251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 modern office setting, a professional lawyer, dressed in a navy suit, white shirt, and patterned tie, sits at a large wooden desk adorned with a nameplate, laptop, and various legal documents. Against a backdrop of tall windows revealing a sunny city skyline, the lawyer attentively sketches an outline of a legal strategy on a whiteboard, using a green marker, while occasionally glancing at the papers scattered on the desk. The scene captures the lawyer's analytical skills and creative approach to solving legal challenges, blending traditional law practice with innovative problem-solving techniques.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1841
|
videos/HRA_part0/1841.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stretching into the horizon, a group of three people, two men and a woman, wearing beige safari outfits and wide-brimmed hats, walk side by side, their shadows cast long by the afternoon sun. They traverse the grassy landscape dotted with scattered acacia trees, their journey unfolding under a clear blue sky. Alongside them, a herd of gazelles grazes peacefully, the animals' lithe forms and delicate movements contrasting with the humans' steady pace. The people occasionally glance at the wildlife, their expressions a mix of wonder and respect for the natural world they explore together.]"
},
{
"from": "gpt",
"value": "Normal. The movements are somewhat uncoordinated."
}
] |
seed42_124
|
videos/HRA_part0/124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with glasses and a neat beard sits at a wooden desk, intensely pushing letters on a vintage typewriter, surrounded by piles of books and papers. The room is dimly lit by a standing lamp, casting shadows that emphasize his focused expression. Wearing a green military-style jacket, he leans forward, completely absorbed in his work, as if battling to translate his thoughts into words. The cluttered environment reflects his creative process, with the typewriter positioned center-stage, highlighting the act of writing as both a physical and mental endeavor.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1232
|
videos/HRA_part2/1232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a well-dressed doctor, wearing a suit and tie, spectacles, and a stethoscope around his neck, playfully floats on a yellow inflatable raft in a clear blue swimming pool. In the background, a mammoth, standing at the edge of the pool, looks on curiously, its massive body shaded by the trees overhead. The doctor's attire remains perfectly neat despite the water, and the mammoth's presence adds an element of surrealism to the otherwise ordinary setting of a backyard pool surrounded by lush greenery.]"
},
{
"from": "gpt",
"value": "Bad. The man's arm is twisted, the hand is twisted, the face is twisted, the man's kayak is twisted, the elephant's legs are twisted, and the head is deformed."
}
] |
seed44_2060
|
videos/HRA_part1/2060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a stunning array of coral formations takes center stage. Hard corals in various shades of brown and orange create a textured landscape, while neon green and blue soft corals sway gently in the current. Brightly colored fish, such as yellow tangs and red snappers, dart in and out of the coral structures. The water above is crystal clear, allowing sunlight to filter down and illuminate the rich colors of the coral reef. In the distance, the silhouette of a large sea turtle can be seen gliding through the water, adding to the serene atmosphere of this underwater paradise.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2992
|
videos/HRA_part0/2992.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a khaki safari outfit walks alongside a kangaroo in an Australian outback setting, both appearing relaxed and accustomed to each other's company. The kangaroo, with its distinctive marsupial pouch, hops gently beside her, while the woman, wearing a wide-brimmed hat and sunglasses, carries a walking stick and a backpack. They traverse a landscape dotted with eucalyptus trees and scrub, under a clear blue sky. The woman occasionally looks down at the kangaroo with a smile, highlighting the unusual yet harmonious companionship between human and wildlife in the vast, open wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2833
|
videos/HRA_part0/2833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, clad in a red flannel shirt and denim overalls, is seen exerting effort as he pulls on a thick rope. The scene is set on a vast, green farm, with lush fields stretching into the horizon. The farmer's weathered hands grip the rope tightly, his face contorted in determination, highlighting the physical demands of his labor. Behind him, a wooden barn with a rusty roof provides a rustic backdrop, while the clear blue sky above adds a sense of serenity to the hardworking atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted in the video."
}
] |
seed46_1783
|
videos/HRA_part2/1783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, costumed in a vibrant green shirt and brown pants, strolls alongside a life-sized, realistic hippopotamus puppet, which is operated by two puppeteers dressed in all-black attire. The trio walks across a grassy field under a clear blue sky, creating a whimsical and unexpected scene. The actor, with a bemused smile, interacts with the puppet, which responds with lifelike movements and expressions, adding to the surreal atmosphere of the outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is twisted, the arms are twisted, the legs are twisted, the hippo puppet's body is twisted, and the legs are twisted."
}
] |
seed42_2454
|
videos/HRA_part0/2454.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a black robe and cap, runs through a futuristic, space-themed cemetery, where floating gravestones and holographic epitaphs are the norm. The sky is tinted with purples and blues, hinting at twilight in this extraterrestrial setting. The student, with short brown hair and a determined look, sprints past the unique graves, which include a zero-gravity burial pod and a memorial sculpture made of interstellar dust. The landscape is dotted with alien flora and fauna, adding to the otherworldly atmosphere of this solemn yet dynamic scene.]"
},
{
"from": "gpt",
"value": "Normal. The student's cap was not generated in the video."
}
] |
seed42_1937
|
videos/HRA_part0/1937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, known for his role in a space-themed reality TV series, gently caresses the smooth, metallic surface of a spacecraft console, his face illuminated by the soft glow of the control panel lights. Dressed in a futuristic silver jumpsuit with black accents, he leans over the controls, his eyes locked onto a screen displaying complex data, conveying a sense of focused intimacy with the technology. The scene is set inside a sleek, modern spaceship cabin, with large windows showing the vastness of space beyond, stars twinkling against the dark cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2480
|
videos/HRA_part1/2480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male lion, distinguished by his thick, dark mane, powerful build, and tawny coat, sprints across a vast, arid savanna. His piercing yellow eyes and focused expression convey determination. The lion's muscular legs propel him forward in a burst of speed, stirring up clouds of dust beneath his paws. The landscape is dotted with scattered acacia trees and distant mountains, providing a rich, natural setting for this awe-inspiring display of raw power and grace.]"
},
{
"from": "gpt",
"value": "Normal. The lion's running in the video is basically normal, but there are some coordination issues."
}
] |
seed46_161
|
videos/HRA_part2/161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, cosmic library filled with floating bookshelves and galaxies in the background, a majestic lion, adorned with a golden collar and a serious expression, is seen wiping the dust off ancient books with a delicate paw. The shelves are stocked with books of all sizes, and the lion moves between them, engaged in the meticulous task of cleaning. Surrounded by the grandeur of space and knowledge, the lion continues its duty, highlighting the serene yet awe-inspiring setting.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the lion wearing a golden collar."
}
] |
seed42_328
|
videos/HRA_part0/328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 temperate deciduous forest, a professional lawyer, dressed in a gray suit and carrying a leather briefcase, wipes his brow as he pauses from his hike. The lush green forest, filled with tall trees and sunlight filtering through the leaves, provides a serene backdrop. The lawyer, wearing a gray blazer, button-down shirt, and khaki pants, is shown wiping his face with a handkerchief, revealing a moment of respite during his outdoor excursion. The peaceful atmosphere of the forest is highlighted by the dappled sunlight and the vibrant greenery surrounding the well-dressed man.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's fingers and arms are deformed in the video, the face is distorted, and the sweat towel is generated unnaturally."
}
] |
seed44_2865
|
videos/HRA_part1/2865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled teacher in a yellow polo shirt and khaki shorts kneels beside a small pool, assisting a ferret in its first swimming lesson. The ferret, wearing a tiny life jacket, paddles energetically with its feet, its nose just above the waterline. The teacher gently supports the ferret from behind, offering encouragement and ensuring safety. The scene is set in a brightly lit room with large windows, casting a warm glow over the educational and nurturing moment shared between the teacher and the adventurous ferret.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's actions of petting the ferret in the video are basically normal, with only slight awkwardness."
}
] |
seed46_2347
|
videos/HRA_part2/2347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacesuit adorned with NASA patches and a backpack, pauses his cleaning duties on a Martian landscape under a starry sky. He looks up, captivated by the celestial beauty, before engaging in a joyful dance, spinning and moving gracefully against the backdrop of Mars' red terrain and the twinkling stars above. His movements are fluid and expressive, a stark contrast to the barren, rocky surface of the planet beneath him. Despite the harsh environment, the janitor finds a moment of joy and wonder, encapsulating the spirit of exploration and the human capacity for finding beauty in unexpected places.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's limbs and body are generated twisted, and the face is deformed."
}
] |
seed42_2755
|
videos/HRA_part0/2755.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a dark green jacket, beige pants, and brown shoes, walks across a grassy field under a clear blue sky, carrying an easel and a canvas. The focus shifts to reveal a majestic antelope standing in the distance, its silhouette framed by the golden hour sunlight. The artist stops, observing the antelope intently, before setting up the easel and beginning to sketch the graceful creature against the backdrop of a serene landscape. The artist's hands move skillfully over the canvas, capturing the essence of the antelope in motion, with the rolling hills and distant mountains providing a stunning natural setting for this artistic endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The antelope in the video is distorted."
}
] |
seed44_2939
|
videos/HRA_part1/2939.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a bobcat, with distinctive ear tufts and a short tail, leaps over a checkout counter in slow motion, its muscles tensing and releasing with each bound. The cash register, with its glowing display and scattered coins, provides context to the setting. The cashier, wearing a red apron and a surprised expression, watches the wild cat jump, creating an unexpected and captivating moment. The bobcat's leap is captured in mid-air, highlighting its agility and grace, against the backdrop of a typical supermarket checkout area.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_310
|
videos/HRA_part2/310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a black jacket and khaki pants, confidently walks alongside a zebra in the middle of a desert landscape, both seemingly unfazed by the arid environment. The director holds a megaphone in one hand and a script in the other, while the zebra, a symbol of the untamed, ambles beside him, the two forming an unlikely duo in this surreal scene. The sun casts long shadows, highlighting the stark beauty of the desert, as the director and the zebra continue their journey together, a testament to the unexpected alliances that can occur in the pursuit of art.]"
},
{
"from": "gpt",
"value": "Bad. The director's face in the video is generated blurry, hands and feet are deformed, the zebra's limbs are generated disproportionately, and there is a frame where the zebra has five legs."
}
] |
seed42_1953
|
videos/HRA_part0/1953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, characterized by its small size and adorable appearance, ambles through a lush, green forest with geysers erupting majestically in the distance, creating a misty, dreamlike atmosphere. The koala, wearing a tiny backpack, explores its surroundings with curiosity, passing by ferns and moss-covered rocks. It occasionally pauses to look at the camera, as if sharing its adventure. The geysers, shooting water high into the air against a backdrop of rolling hills, add a dramatic element to the serene forest setting, all captured in stunning detail.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the koala with a small backpack as mentioned in the caption."
}
] |
seed44_3006
|
videos/HRA_part1/3006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green environment, a small brown mouse stands on the edge of a natural pool, surrounded by dense shrubbery and tall grass, creating an intricate network of thickets. The mouse looks intently at the water, its ears perked and body alert. Suddenly, it bravely leaps into the clear, shimmering pool, swimming with surprising agility, its tiny paws propelling it through the water. As it swims, the camera captures the ripples created by its movement, highlighting the contrast between the busy activity of the mouse and the stillness of the thickets surrounding the pool.]"
},
{
"from": "gpt",
"value": "Bad. The swimming of the brown mouse in the video is very unsmooth, with uncoordinated movements."
}
] |
seed42_1165
|
videos/HRA_part0/1165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jungle environment, two young boys, one wearing a yellow t-shirt and the other in a blue shirt, are seen interacting with a small monkey. The monkey, sitting on a branch at eye level with the children, reaches out to touch the hand of the boy in the yellow shirt, who gently caresses its head in return. The second child looks on with a smile, his hands resting on the branch, as they both share a tender moment with the curious primate, surrounded by the vibrant foliage of their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The boy's hand appears deformed and the monkey's face also becomes deformed."
}
] |
seed46_126
|
videos/HRA_part2/126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his uniform and badge, stands in a cozy kitchen, illuminated by warm overhead lights. He focuses intently on chopping vegetables on a wooden cutting board placed on a granite countertop. The kitchen is modern, featuring stainless steel appliances and a tile backsplash. The officer, displaying a serious yet calm demeanor, proceeds to sauté the vegetables in a large skillet on a gas stove, the flames providing a vibrant contrast to the neutral tones of the kitchen. Throughout, he maintains the disciplined bearing of a law enforcement professional, even as he prepares a home-cooked meal.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show a cutting board or vegetables."
}
] |
seed44_1281
|
videos/HRA_part1/1281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a gray jacket over his uniform, stands at the edge of a dense forest, contemplating his next move. He is holding hiking gear, including a walking stick, a backpack, and a water bottle, indicating his readiness for an outdoor adventure. The forest features tall, lush trees and a clear, sunny day, with a trail leading into the woods. The janitor begins his hike, walking confidently down the trail, his equipment in tow, as he explores the natural beauty of the forest surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1533
|
videos/HRA_part2/1533.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a red shirt and dark pants, stands at the edge of a vast highway interchange, bathed in the golden glow of twilight. With city lights twinkling in the distance, he begins to dance, his movements expressive and free, contrasting with the concrete jungle around him. Cars whiz by on multiple levels of the highway, their headlights and taillights creating streaks of color against the dusky sky. The man continues to dance, his silhouette framed by the urban landscape, embodying a sense of liberation amidst the urban sprawl.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1590
|
videos/HRA_part0/1590.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, dressed in a red shirt, black vest, and dark pants, stands on a dimly lit stage, pointing with his right hand. He wears a black beret and glasses, adding to his artistic flair. Behind him, a vibrant purple curtain complements the stage lights, which cast a warm glow on his face. His left hand rests on his hip, and he points emphatically with his right, engaging the audience in a dynamic performance. The background is blurred, emphasizing the musician's commanding presence as he points with passion and intensity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2617
|
videos/HRA_part0/2617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a dark gray jacket, white shirt, and black tie, is shown in a bathroom, intently focused on unclogging a drain. The bathroom features a white sink with chrome fixtures, a mirror above it, and a window in the background. The musician, with his graying hair and serious demeanor, uses a metal wire hanger as a makeshift tool to clear the clogged drain, demonstrating his problem-solving skills in an unexpected domestic task. The scene captures the juxtaposition of his refined appearance and the mundane chore, highlighting his versatility beyond his musical talents.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is slightly distorted, and the hands are twisted."
}
] |
seed46_2678
|
videos/HRA_part2/2678.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, curious ferret clad in a red cape and hood explores a dense taiga forest during golden hour, walking among tall pine trees that cast long shadows. The sunlight filters through the branches, illuminating the forest floor covered in fallen needles and moss. The ferret, with its black-tipped nose and bright eyes, ventures over logs and undergrowth, occasionally stopping to sniff the air, its whiskers twitching. Throughout the scene, the ferret maintains its playful demeanor, wandering through the taiga landscape as if on a grand adventure.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3029
|
videos/HRA_part2/3029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue floral-patterned scrub top and matching pants, waters indoor plants in a sunlit room. She is seen from behind, her dark hair in a bun, as she carefully tends to a large plant. Next, she faces the camera, smiling warmly, holding a watering can. She then waters another plant, her actions gentle and attentive. Lastly, she pauses, appearing thoughtful, the greenery and natural light creating a serene atmosphere around her.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's face, hands, and arms are distorted in the video."
}
] |
seed46_1753
|
videos/HRA_part2/1753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 attorney, wearing a dark suit and carrying a briefcase, walks through a desolate industrial park at dusk, under the glow of orange streetlights. He pauses to gently touch the rough surface of a concrete wall, his expression thoughtful. The scene shifts to show him seated on a bench, still in the industrial setting, now bathed in the blue hour light, as he caresses the worn wooden slats, deep in thought. Throughout, the juxtaposition of the lawyer's polished appearance against the gritty industrial backdrop highlights the unusual intimacy of his actions.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2025
|
videos/HRA_part0/2025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, donning a green jacket, blue jeans, and a gray cap, stands on a ladder propped against the side of a barn, which features a vibrant red exterior and white trim. He is engaged in cleaning the gutters, using a gloved hand to remove debris. The scene is set against a backdrop of lush greenery and a clear blue sky. Moments later, he pauses to survey his work, a pitchfork leaning against the barn wall beside him. The farmer then continues his task diligently, his attire and the pastoral setting creating a vivid image of rural life.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm appear deformed and mutated, and the object in the man's hand also becomes distorted."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.