video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2968
|
videos/HRA_part1/2968.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic grouse, distinguished by its brown plumage speckled with white and black, struts proudly across a lush, green meadow under a bright, sunlit sky. The bird's robust body, complete with a red wattle above its beak, is prominently displayed as it moves with regal confidence. Moments later, it's seen in profile, its intricate feather patterns and textured wings highlighted against the vibrant vegetation. Then, it turns its head, revealing piercing eyes and a sharp beak, set against the backdrop of a dense forest and clear blue sky. Lastly, the grouse is captured mid-stride, its legs moving swiftly, demonstrating the strength and agility of this woodland creature, all set against a serene natural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The capercaillie's head and claws in the video were generated abnormally."
}
] |
seed44_2352
|
videos/HRA_part1/2352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, lush green savanna under a bright, sunny sky, a majestic Bengal tiger runs swiftly across the open grassland, its powerful muscles rippling beneath its vibrant orange coat, marked with distinctive black stripes. The tiger's piercing yellow eyes are focused ahead, conveying determination and grace in motion. The scene is framed by distant gallery-like structures, housing various wildlife exhibits, which add a unique architectural element to the natural setting. The tiger's fluid movements and the contrast between the untamed wilderness and the man-made galleries create a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The Bengal tiger's claws were not fully generated, and the face was generated blurry."
}
] |
seed46_1514
|
videos/HRA_part2/1514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, windswept grassland under a partly cloudy sky, a janitor wearing a yellow vest, blue jeans, and a white shirt is seen wiping a transparent, rectangular window that floats in front of him. The serene landscape stretches to the horizon, dotted with distant trees, while the janitor diligently cleans the window with a cloth, revealing the pristine clarity of the glass. The peaceful scene is punctuated by the gentle sway of the tall grass and the solitude of the janitor's task, emphasizing the unexpected context of maintenance in the midst of nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1616
|
videos/HRA_part0/1616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a lone cuttlefish hovers above a sandy seabed dotted with rocks, showcasing its dynamic color-changing abilities as it blends with the surroundings. The cephalopod displays a mesmerizing array of brown and white patterns on its skin, a demonstration of its remarkable camouflage technique. Its eight arms and two tentacles extend gracefully from its mantle, each adorned with small suckers, as it maneuvers through the aquatic environment with agility. The water is clear, allowing sunlight to filter through, illuminating the cuttlefish and the sandy bottom beneath it, creating a stunning visual display of nature's wonders.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1699
|
videos/HRA_part1/1699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blue button-down shirt and khaki pants, rearranges furniture in a cozy room with wooden floors and a fireplace, aiming to find inspiration. He thoughtfully adjusts a brown leather sofa, placing it at an angle near the hearth, with a glass coffee table in front. Next, he moves a wooden chair with a green cushion to the right side of the sofa, creating a conversational space. Then, he positions a tall bookshelf behind the chair, filled with books and trinkets, adding character to the room. Lastly, he places a small wooden desk with a typewriter next to the window, basking in natural light, perfect for writing, all while maintaining the warm, inviting atmosphere of the space.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, twisted legs, twisted arms, and a distorted face."
}
] |
seed46_2272
|
videos/HRA_part2/2272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, rakes leaves in a community garden, his gold nametag gleaming under the sunlight. He pauses to smile warmly at the camera, his friendly demeanor evident. Wearing a dark blue police uniform complete with a name badge and a cap, he continues raking, surrounded by piles of autumn leaves in various shades of orange, red, and brown. The video closes with him raking diligently, highlighting the unexpected sight of a law enforcement officer engaging in a domestic chore, fostering a sense of community and service.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2320
|
videos/HRA_part1/2320.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow high-visibility vest and khaki pants walks purposefully down a dimly lit tunnel, holding a flashlight that illuminates the way ahead. The tunnel walls, painted a dull gray, are lined with pipes and electrical conduits, providing a gritty industrial backdrop. Shadows cast by the janitor's flashlight dance on the walls, adding a sense of depth and mystery to the scene. The janitor's steps echo in the confined space, punctuating the otherwise silent atmosphere of the tunnel system.]"
},
{
"from": "gpt",
"value": "Normal. The legs are slightly twisted, and the hands are twisted."
}
] |
seed46_2939
|
videos/HRA_part2/2939.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a 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": "Bad. The mountain cat in the video is generally malformed."
}
] |
seed46_2309
|
videos/HRA_part2/2309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, balding with glasses and a neatly trimmed beard, wearing a dark green collared shirt, focuses intently on fixing a leaky faucet in a public restroom. The faucet is positioned above a stainless steel sink with a mirror in the background. The janitor kneels on a yellow floor mat, using a wrench from his well-stocked tool belt to tighten the faucet's handle. The scene is illuminated by overhead fluorescent lights, casting a warm glow on the janitor's determined face as he works diligently to stop the dripping water.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1733
|
videos/HRA_part0/1733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah, known for its prowess on land, surprisingly takes to water, swimming in a large, lush, natural pool surrounded by verdant vegetation. The big cat, identifiable by its distinctive spots, demonstrates its adaptability as it navigates the water, its muscular body moving gracefully beneath the surface. The setting sun casts a warm glow over the scene, highlighting the cheetah's wet fur and the droplets of water displaced by its powerful strokes. This rare sight captures the animal's unexpected aquatic abilities in a serene, wild environment.]"
},
{
"from": "gpt",
"value": "Normal. The cheetah's face is distorted in the video."
}
] |
seed46_2344
|
videos/HRA_part2/2344.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a gray suit, white shirt, and patterned tie, stands in a dark room illuminated by a single spotlight, giving a speech about the concept of traveling at light speed. He passionately caresses an abstract sculpture representing the fabric of spacetime, emphasizing his points about the theoretical possibilities of superluminal travel. His gestures are expressive, conveying the emotional weight of discussing such a groundbreaking topic, all while maintaining eye contact with his unseen audience, inviting them to share in the wonder and complexity of his subject matter.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2250
|
videos/HRA_part0/2250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male farmhand, clad in a white shirt and brown apron, gently caresses a small, fluffy yellow chick with a tender smile on his face, showcasing a moment of care and connection in a rural setting. The scene is set against a backdrop of wooden crates and greenery, highlighting the peaceful atmosphere of the farm. His hands, rough from labor yet gentle in touch, cradle the delicate creature, emphasizing the bond between man and nature.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's fingers are generated incorrectly, and there are issues with the generation of the chick's nose and body."
}
] |
seed46_224
|
videos/HRA_part2/224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint, rustic market, a young female cashier, wearing a green apron with a name tag reading \"Ibex,\" diligently wipes down the countertop with a cloth. The wooden cash register stand is adorned with a small flower pot and a framed picture, adding a personal touch to the space. Ibex works efficiently, her movements confident and practiced, as she cleans the area where customers place their items for purchase. The background features shelves stocked with various goods, giving a glimpse into the variety of products available in the store.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2465
|
videos/HRA_part2/2465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious brown monkey, with its fur ruffled by the breeze, is seen playfully paddling in a tranquil body of water, surrounded by lush green foliage. It uses its arms to splash about, moving gracefully through the clear blue water, with trees and plants in the background framing the scene. The monkey's expressive face shows delight as it swims, its limbs working rhythmically beneath the surface, and droplets of water scatter around it, capturing the joy of this unexpected aquatic adventure.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_106
|
videos/HRA_part2/106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a doctor, wearing a white lab coat and stethoscope, stands in a lush green forest. A small mongoose, known for its agility, leaps playfully from the doctor's right shoulder to a branch above, capturing the essence of unexpected interactions in nature. The doctor looks on with a mix of surprise and delight, highlighting the unique connection between humans and wildlife. The vibrant green foliage and dappled sunlight create a serene atmosphere, emphasizing the peaceful coexistence between the medical professional and the nimble creature.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's jumping motion in the video is not smooth and continuous; the actions are uncoordinated."
}
] |
seed42_1763
|
videos/HRA_part0/1763.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a spacious living room, a cashier, wearing a red shirt and khaki pants, is seen assembling a wooden table. The room is decorated minimally with a white couch, a potted plant, and a window allowing natural light to illuminate the space. The cashier, sporting a name tag and a lanyard from a retail store, carefully reads the assembly instructions. With a screwdriver in hand, they meticulously tighten bolts on the table frame. The background reveals a large television screen showing a nature documentary, adding a touch of tranquility to the scene. Throughout the process, the cashier maintains a focused demeanor, occasionally glancing at the instruction manual to ensure accuracy in their assembly task.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's hand and screwdriver in the video were generated abnormally."
}
] |
seed44_293
|
videos/HRA_part1/293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lion, defying expectations, swims powerfully through a tranquil body of water, its golden coat glistening as it propels itself forward with muscular strokes. Its piercing gaze is fixed ahead, conveying determination and grace in this unusual aquatic setting. The lion's head remains above the waterline, mane billowing softly, while its body undulates beneath the surface, showcasing an unexpected display of strength and agility in the liquid environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1612
|
videos/HRA_part2/1612.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a stethoscope around his neck and a colorful tie, is laughing heartily with his head thrown back, his eyes closed, and his mouth wide open, showing his amusement in a candid moment. The laughter is contagious, spreading joy and positivity in a medical setting, with the doctor's facial features animated and expressive, capturing the essence of happiness and camaraderie in a professional environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor in the video has uncoordinated movements."
}
] |
seed46_2981
|
videos/HRA_part2/2981.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cheerful cashier, donning a green apron and a nametag, is playfully dancing with a friendly horse inside a vibrant, cartoonish grocery store. The cashier, with short brown hair and a wide smile, leads the horse in a lively jig down the aisles, filled with brightly colored products. The horse, adorned with a polka-dotted bowtie and a pair of oversized sunglasses, happily trots alongside, its hooves gently tapping the checkered floor. Shoppers look on in amused surprise, some pausing to capture the unexpected spectacle on their phones, while others continue browsing the shelves, seemingly unfazed by the unusual dance party unfolding before them.]"
},
{
"from": "gpt",
"value": "Bad. The cashier and the horse's faces in the video are abnormally blurry, and their limbs are distorted."
}
] |
seed44_1760
|
videos/HRA_part1/1760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by soft purple lights and adorned with cosmic artwork, a young, bald writer wearing a black turtleneck and jeans sits pensively at a sleek, metallic desk. He wipes away a smudge on the pristine, reflective surface, revealing a holographic interface beneath. Around him, floating canvases display vibrant, otherworldly landscapes, while the artist himself seems lost in thought, perhaps contemplating his next masterpiece among the stars.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand appears deformed."
}
] |
seed46_3165
|
videos/HRA_part2/3165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative woman, clad in a yellow top and denim jeans, stands before a large canvas in an airy studio filled with natural light. She holds a paintbrush in her right hand, dabbing it into a vivid palette of colors, while her left hand rests on her hip. Her wavy brown hair cascades down her back as she intently focuses on her artwork, surrounded by a scattering of completed paintings and art supplies. The atmosphere is one of tranquility and inspiration, with the unfinished painting on the easel capturing the essence of her artistic process.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1329
|
videos/HRA_part0/1329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A skilled musician, dressed in a dark green shirt and brown trousers, sits on a wooden stool under the shade of a tree, engrossed in playing a portable keyboard. Nearby, a majestic elephant, adorned with intricate patterns on its body, stands calmly, its trunk reaching down to touch the musician's head in a tender gesture. The scene takes place in a lush, grassy environment, with the elephant's legs slightly bent, as if it were gently swaying to the music. The musician's fingers dance across the keys, creating a harmonious melody that seems to captivate both the human and the elephant alike.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2190
|
videos/HRA_part2/2190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a brown beret and glasses, sits in a dimly lit studio filled with art supplies and paintings, engrossed in reading a book about art history. The camera captures the artist's hands turning the pages, revealing colorful illustrations of famous artworks. In another shot, the artist is seen from behind, sitting in front of a large canvas with paintbrushes in hand, contemplating the next stroke while a book on art techniques lies open nearby. Throughout the video, the artist's passion for both creating and studying art is evident in the careful attention given to both the book and the canvas.]"
},
{
"from": "gpt",
"value": "Bad. The action of turning the pages can be seen, but the actions are not continuous and there are sudden changes."
}
] |
seed44_261
|
videos/HRA_part1/261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, wearing a gray t-shirt and jeans, attentively waters lush green plants arranged in a neat row against a plain studio wall. He begins by pouring water from a green watering can onto the first plant, a potted ficus. Next, he moves to the second plant, a healthy monstera, continuing his task with care. Then, he focuses on the third plant, a vibrant snake plant, ensuring each receives adequate hydration. Lastly, he tends to the fourth plant, a thriving peace lily, completing the sequence with dedication, all within the simple yet functional confines of the studio space.]"
},
{
"from": "gpt",
"value": "Bad. The director's facial expressions and hand generation in the video have issues."
}
] |
seed46_1456
|
videos/HRA_part2/1456.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, recognizable by his distinct facial hair and dressed in hiking gear which includes a gray jacket, backpack, and cap, pauses on a rocky trail. The scenic mountain landscape behind him, featuring lush greenery and distant peaks, provides a stunning contrast to his utilitarian appearance. Initially, he looks down at his feet, seemingly contemplating his next step. Then, he turns his head slightly, his gaze following the path ahead. Next, he stops to observe the breathtaking view, his expression reflecting a sense of peace and appreciation for nature. Finally, he smiles widely, perhaps recalling a fond memory, before continuing his journey, embodying the unexpected image of a janitor enjoying a hike in the great outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video walks very unsmoothly, and his movements are uncoordinated."
}
] |
seed44_2808
|
videos/HRA_part1/2808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a black jacket and blue jeans, is seen caressing a kangaroo at a busy bus stop in the heart of a city. The scene opens with the actor standing next to the marsupial, both seemingly waiting for a bus amidst the urban landscape filled with pedestrians and traffic. As the camera focuses, the actor gently strokes the kangaroo's back, showing a tender connection between them. The kangaroo, unperturbed by the surroundings, leans into the touch, its eyes closed in apparent comfort. Behind them, the bustling city life continues, with cars passing by and people going about their day, creating a contrast to the intimate moment shared between the actor and the kangaroo.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted in the video, and the kangaroo's face is also distorted."
}
] |
seed44_1596
|
videos/HRA_part1/1596.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic stag strides purposefully across an ancient stone bridge, its antlers framing the scene like natural architecture against a backdrop of lush greenery and a misty morning sky. The deer's confident gait and the bridge's weathered texture tell a story of time and resilience in nature. As it walks, the stag's hooves make soft sounds on the moss-covered stones, creating a harmonious melody echoing through the serene woodland setting. The bridge, arching gracefully over a tranquil stream, becomes a pathway connecting two verdant forests, with the deer serving as a symbol of grace and wildness moving between these spaces.]"
},
{
"from": "gpt",
"value": "Normal. The Bucks character's face is distorted, and the feet are twisted."
}
] |
seed42_1023
|
videos/HRA_part0/1023.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 otter strolls leisurely across ancient cobblestones, exploring the historical ruins of a stone fortress, its textured walls and arched doorways framing the scene. The curious creature, with its brown fur and small, pointed face, ambles through the site, seemingly undisturbed by the historic ambiance surrounding it. Its path leads it past weathered statues and through narrow passageways, the muted colors of the stone providing a stark contrast to the lush greenery that has reclaimed parts of the ancient structure. Throughout its journey, the otter maintains a peaceful pace, offering a unique perspective on the intersection of nature and history.]"
},
{
"from": "gpt",
"value": "Bad. The otter's body is twisted, its paws are twisted, its face is twisted, and its legs are twisted."
}
] |
seed42_1859
|
videos/HRA_part0/1859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer kneels on a grassy park area, attentively watching a squirrel. The squirrel, emboldened, leaps from the ground onto the officer's outstretched arm, seeking a nut held in the officer's other hand. The cop wears a standard police uniform, including a navy blue shirt, black tactical pants, and a badge, while the greenery and trees in the background set a peaceful outdoor scene. The squirrel's acrobatic leap and the officer's gentle interaction create a heartwarming moment in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's hand and the squirrel in the video are generated abnormally; during the middle frames of the squirrel's jump, the squirrel's limbs are distorted."
}
] |
seed42_1037
|
videos/HRA_part0/1037.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, complete with a stethoscope around his neck, dons a brown jacket, dark trousers, and black boots as he shovels snow from a walkway. Snowflakes gently fall from a gray sky, settling on the green pine tree in the background. The doctor, wearing glasses and a wedding ring, pauses to wipe his brow, revealing his determination. He continues to clear the snow, demonstrating his commitment to his duties despite the weather. Throughout the scene, the doctor's attire remains unchanged, emphasizing his professional identity even in this domestic task.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated and too mechanical."
}
] |
seed46_1418
|
videos/HRA_part2/1418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a yellow reflective vest, blue latex gloves, and a badge, runs with purpose toward a cluster of factories in the background. The factories feature large smokestacks, metal siding, and concrete exteriors, set against a cloudy gray sky. The officer's intense gaze and focused posture convey urgency as they sprint across a desolate industrial landscape, the factories' imposing structures looming ominously behind.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's hand appears deformed."
}
] |
seed42_150
|
videos/HRA_part0/150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit room, two young children sit cross-legged on a vibrant multi-colored rug, surrounded by an array of plush toys and colorful books. The older child, wearing a yellow shirt, leans over a book, animatedly pointing at the pages as they read aloud with enthusiasm. The younger child, dressed in a blue sweater, listens intently, eyes wide with wonder and hands resting on their knees. The walls of the room are painted a calming light blue, adorned with playful artwork and educational posters, creating a nurturing environment that fosters a love for reading and learning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_258
|
videos/HRA_part1/258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate female veterinarian, wearing a white lab coat and blue scrubs, gently feeds a small dog from a spoon, her caring nature evident in her warm smile. The clinic room is clean and modern, with stainless steel equipment and a large window providing natural light. Behind her, a poster about pet nutrition hangs on the pale green wall. On a nearby table, various pet food samples are neatly arranged, emphasizing the importance of proper animal care. Throughout the scene, the vet's loving interaction with the dog highlights her dedication to animal welfare.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1512
|
videos/HRA_part1/1512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dynamic montage begins with a charismatic musician wearing a space-themed outfit, strumming an electric guitar under the glow of neon lights, surrounded by cosmic visuals. The scene shifts to a historic moon landing, featuring a space-suited astronaut planting a flag on the lunar surface, with the Earth visible in the distance. Lastly, we see a determined athlete sprinting across a track, the focus on their powerful legs and the intensity in their eyes, pushing towards the finish line against a backdrop of cheering spectators. Each scene is seamlessly connected through a thematic thread of human achievement and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The musician's hands appear deformed, and human legs appear deformed."
}
] |
seed46_2157
|
videos/HRA_part2/2157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vole, brown with white underparts, scurries along a paved path between two large apartment complexes, their exteriors a mix of brick and siding, under a partly cloudy sky. The rodent navigates the concrete walkway, dotted with cracks and weeds, passing by the base of the buildings where potted plants and bicycles are stored. It continues its journey undisturbed, weaving between the structures that tower above it, set against the backdrop of a suburban neighborhood with cars parked along the street and other apartment buildings visible in the distance.]"
},
{
"from": "gpt",
"value": "Bad. The hamster in the video was generated abnormally, with its limbs distorted and deformed in the middle frames, and its tail and head suddenly swapped positions."
}
] |
seed42_2873
|
videos/HRA_part0/2873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet futuristic scene, a giant panda, wearing a spacesuit and helmet adorned with antennas, sits against a backdrop of stars and galaxies, symbolizing deep space communication. The panda is seen wiping its paw across the visor of its helmet, perhaps to clear condensation, while floating in zero gravity, surrounded by the vastness of space. This unique juxtaposition of elements - the panda representing Earthly innocence, the spacesuit and helmet signifying human exploration, and the cosmic background evoking a sense of wonder - creates a captivating and surreal visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the panda wiping the helmet visor with its paw; the action is basically normal but there is some lack of coordination."
}
] |
seed44_3185
|
videos/HRA_part1/3185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 set within a dense boreal forest, a janitor, dressed in a brown jacket, khaki pants, and a gray cap, diligently wipes a transparent pane that seemingly divides the wilderness. Behind this glass, a majestic leopard prowls within its enclosure, observing the man with curiosity. The forest's lush greenery and tall coniferous trees envelop the surroundings, creating a vivid contrast against the man-made structure. The janitor, focused on his task, occasionally glances at the leopard, acknowledging the unusual juxtaposition of his cleaning duties amidst the wild environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1017
|
videos/HRA_part2/1017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, upscale restaurant filled with the clinking of glasses and chatter, a waiter in a crisp, black uniform expertly navigates the lively dining room. He deftly pushes a polished, stainless steel service cart laden with fine china and gleaming silverware, carefully avoiding any contact with the patrons enjoying their meals. The elegant space, adorned with hanging lights casting a warm glow and walls decorated with framed artwork, provides a sophisticated setting for this scene of seamless service execution.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's arm is twisted, and the guest's face is distorted."
}
] |
seed44_326
|
videos/HRA_part1/326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and black tactical gear, leaps over a row of lush green vineyards under a bright blue sky, suggesting an urgent pursuit. The officer, equipped with a utility belt and a radio, lands on the other side of the vines, continuing the chase with determination. The scene captures the contrast between the peaceful landscape of the vineyard and the high-stakes action of the law enforcement pursuit.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_303
|
videos/HRA_part1/303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, open ocean scene where sunlight filters through the water's surface, illuminating a majestic manta ray as it glides effortlessly through the clear blue depths. The manta ray, with its impressive wingspan, showcases its graceful movements, framed against the vibrant coral reef below. Its dark dorsal side contrasts sharply with the lighter underbelly, creating a stunning visual as it maneuvers with fluidity. Nearby, smaller fish swim alongside the manta ray, highlighting the peaceful coexistence in the underwater ecosystem. The scene is serene and captivating, offering a rare glimpse into the beauty of marine life.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2390
|
videos/HRA_part1/2390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and unexpected scene, a waiter wearing a traditional French uniform, complete with a black vest, white shirt, black bow tie, and black pants, is shown running alongside a full-grown rhinoceros. Both are moving at a steady pace across a lush, green grassland, under a bright blue sky dotted with white clouds. The waiter maintains a focused expression, while the rhinoceros runs with its head held high, creating a surreal and comical juxtaposition of elegance and wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the person and the rhinoceros in the video are not smooth."
}
] |
seed46_1767
|
videos/HRA_part2/1767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary buzzard perches majestically on a barren branch, its piercing eyes scanning the vast, sunlit savannah below for any signs of movement. The bird, with its distinct brown and white plumage, contrasts starkly against the muted tones of the landscape. Suddenly, it spreads its impressive wingspan and takes flight, gliding effortlessly over the terrain. Its sharp talons are clearly visible as it descends with laser-like precision towards a potential meal, showcasing the raw power and agility of this apex predator. The scene is set against a backdrop of rolling hills and scattered trees, bathed in the warm glow of the afternoon sun.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2953
|
videos/HRA_part0/2953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blue t-shirt and khaki shorts, runs across a vast desert landscape under a clear blue sky, with distant mountains providing a dramatic backdrop. The student, wearing a backpack and a cap, navigates the sandy terrain with determination, the camera capturing the texture of the dunes and the play of light and shadow. As the scene progresses, the focus remains on the runner, highlighting their stamina and resilience against the stark beauty of the desert environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1441
|
videos/HRA_part0/1441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, nestled in the fork of a lush eucalyptus tree, gently caresses its companion with a fuzzy paw, both enveloped in the verdant embrace of their arboreal home. The koala, with its round face and endearing expression, tenderly touches another koala, showcasing a heartwarming display of affection. Their interaction is set against the vibrant green foliage, highlighting the tenderness of their connection. As they engage in this intimate gesture, their soft fur and the intricate details of the eucalyptus leaves create a visually captivating scene. Throughout, the two koalas remain in this loving embrace, emphasizing the emotional bond between them.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2841
|
videos/HRA_part2/2841.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a red flannel shirt and denim overalls, dances joyously in a lush green field, while a curious deer watches from a distance, its ears perked up, intrigued by the unusual sight. The farmer's movements are lively and free, embodying a sense of unbridled happiness, as the deer remains frozen in place, observing the dance with wide, expressive eyes. The scene is set against a backdrop of rolling hills and a clear blue sky, creating a picturesque rural landscape that complements the harmonious interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1428
|
videos/HRA_part0/1428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 handsome male waiter, wearing a crisp white shirt, black vest, and necktie, serves a couple at an elegant indoor restaurant. Suddenly, he breaks into song, passionately singing an operatic aria while continuing to serve. The camera captures his animated face as he sings, highlighting his emotional performance. Throughout, the well-lit dining area with its ornate chandelier and patrons at other tables remains visible, creating a lively atmosphere. The waiter's confident singing and the restaurant's upscale ambiance provide a memorable contrast to his regular duties.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted."
}
] |
seed46_2261
|
videos/HRA_part2/2261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an array of colorful fish. The grouper, with its distinctive spotted pattern and wide, flat head, explores its surroundings with a slow, methodical motion. Its eyes, fixed on the camera, seem to convey intelligence and awareness. The water is crystal clear, allowing every detail of the grouper's body and the intricate ecosystem it inhabits to be visible. The scene is illuminated by natural sunlight filtering through the surface, casting dappled light on the sandy seabed and the marine life above.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3209
|
videos/HRA_part0/3209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a red t-shirt and black shorts is depicted running alongside a kangaroo on a dusty trail surrounded by lush vegetation, both appearing energetic and engaged in the activity. They run together on a dirt path amidst dense greenery, the kangaroo bounding effortlessly beside the man, who maintains a steady pace. The scene captures the unique companionship between the man, dressed casually in a red top and dark shorts, and the kangaroo, as they traverse the natural environment together. The duo continues their run through the vibrant landscape, the kangaroo's powerful legs propelling it forward in sync with the man's strides, highlighting their shared rhythm and connection amidst the verdant scenery.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, legs, the kangaroo's body, head, and legs are distorted in the video."
}
] |
seed46_1660
|
videos/HRA_part2/1660.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a white shirt and black pants, carefully balances a tray of refreshments on his hands, offering it to a friendly mammoth. The mammoth, depicted with brown fur and large tusks, swims leisurely in a serene lake, its body half-submerged in the clear water. The waiter stands at the edge of the lake, extending the tray towards the mammoth, who reaches out with its trunk to gently take a drink. The sky is a vivid orange, suggesting either sunrise or sunset, adding a touch of magic to this extraordinary encounter between two unlikely companions.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2313
|
videos/HRA_part0/2313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden jackal leaps gracefully over a log in the middle of a grassy savanna, its body stretched mid-air, showing agility and strength. The jackal, with its keen eyes and alert posture, exhibits a powerful jump, clearing the obstacle effortlessly. The scene captures the animal's dynamic movement against a backdrop of tall grasses swaying in the breeze, highlighting the beauty and resilience of this wild canine in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3051
|
videos/HRA_part0/3051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a white T-shirt and blue jeans, encounters a hare in the midst of vast farmlands, where the land stretches out under a wide, open sky. The scene then shifts to the student swimming in a serene, crystal-clear lake, surrounded by lush greenery, as the hare watches from the shore, curious and alert. The student's relaxed demeanor and the hare's attentive stance create a harmonious moment between nature and humanity, all set against the backdrop of expansive farmlands and a peaceful body of water.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_136
|
videos/HRA_part0/136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a white martial arts uniform with a red stripe, executes a high kick against a blue sky, showcasing agility and precision. Surrounded by lush greenery, including palm trees and bushes, the scene highlights the contrast between nature and human skill. The artist's ponytail swings during the kick, emphasizing the dynamic motion. Nearby, a wooden fence and a building with a thatched roof add to the tropical setting. Throughout the sequence, the artist maintains a focused gaze, highlighting determination and control.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1106
|
videos/HRA_part2/1106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red deer leaps over a wooden fence in a lush, green field, its powerful legs and large frame displayed against a backdrop of trees and rolling hills. The deer, with an impressive set of antlers, is captured mid-jump, showing its agility and grace as it clears the barrier. The scene is set in a natural, countryside environment, with the deer's movement frozen in time, highlighting the beauty and strength of this wild animal.]"
},
{
"from": "gpt",
"value": "Bad. The red deer's legs are barely visible, showing deformities and mutations. And it did not cross the wooden barrier."
}
] |
seed44_1194
|
videos/HRA_part1/1194.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, distinguished by his uniform consisting of a navy blue shirt with badges, dark pants, and black shoes, vacuums the carpet in a modest living room. The room features a small brown couch, a glass coffee table, and a beige recliner, with sunlight streaming through the window, highlighting dust particles in the air. The officer, displaying a serious demeanor, methodically maneuvers the vacuum cleaner across the carpeted floor, revealing his commitment to household chores despite his profession. The domestic scene contrasts sharply with his authoritative attire, emphasizing the duality of his role as both protector and provider.]"
},
{
"from": "gpt",
"value": "Normal. The vacuum cleaner is deformed, and the person's hand is also deformed."
}
] |
seed42_192
|
videos/HRA_part0/192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, wearing a yellow helmet, a white tank top, blue jeans, and brown work boots, pauses from his labor to stand on a sandy beach, the serene ocean stretching behind him. He takes a moment to enjoy the view before energetically diving into the clear blue water, his clothes still on, embracing the refreshing swim. Underwater, he opens his eyes, revealing his blue goggles, as he swims with purpose, surrounded by the vivid marine life and the bright sunlight filtering through the surface. Afterward, he emerges from the sea, dripping wet, and walks back to his work site, leaving wet footprints on the sand, embodying a break well taken.]"
},
{
"from": "gpt",
"value": "Bad. No brown work boots were generated."
}
] |
seed44_2576
|
videos/HRA_part1/2576.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, dressed in a casual outfit of a gray hoodie and blue jeans, diligently cleans a large window in a modern building, surrounded by other windows. The natural light from outside illuminates the space, casting a warm glow on the young cleaner. The scene is set in a minimalist room with white walls and hardwood floors, adding to the clean aesthetic. The student, with a focused look on their face, uses a squeegee and a bucket of soapy water to ensure every inch of the glass is spotless, reflecting their commitment to the task at hand.]"
},
{
"from": "gpt",
"value": "Normal. The man's face in the video is blurry, and there are missing parts in the fingers."
}
] |
seed44_3098
|
videos/HRA_part1/3098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush, green forest environment, two individuals wearing khaki safari outfits are seen running alongside a chimpanzee, engaged in playful interaction. The scene is vibrant and full of life, with the humans and the chimpanzee moving together in harmony. They dash across a dirt path, surrounded by dense vegetation, as the chimpanzee exhibits its natural agility and strength. The trio's energetic run is captured in high detail, highlighting the dynamic movement and the unique bond between humans and this primate in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2820
|
videos/HRA_part1/2820.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a white collared shirt, points with her right hand to something outside the frame, her left hand resting on the counter. Behind her, a row of colorful candy bars lines the shelf, while above her head, a sign displays various services offered, such as check cashing and lottery tickets. The scene takes place inside a busy convenience store, with customers visible in the background, creating a snapshot of daily life in a bustling urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's left hand, mentioned in the caption, is not shown to be lightly placed on the counter in the video."
}
] |
seed44_2520
|
videos/HRA_part1/2520.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A tiny vole, brown in color, scurries through a miniature world set against the backdrop of towering skyscrapers, their glass facades reflecting sunlight. The vole runs across a small wooden bridge, navigating its way through a lush green park nestled within the urban jungle. It then darts under a miniature Eiffel Tower, a playful nod to global landmarks, before disappearing into the safety of a hollow log, all while the cityscape looms large and impressive in the background.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the hamster in the video are not smooth."
}
] |
seed42_2357
|
videos/HRA_part0/2357.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hare, donning a red apron and a name tag, works diligently as a cashier in a charming store nestled deep within a lush rainforest. The store's wooden shelves are stocked with unique items, including exotic fruits, colorful fabrics, and handmade crafts. Outside, the vibrant rainforest comes alive with the sounds of wildlife and the gentle patter of rain. Suddenly, the hare takes a break and ventures outside, where it encounters a serene natural pool, its clear waters inviting for a refreshing swim amidst the emerald greenery. The hare, now in swimming attire, joyfully splashes in the pool, surrounded by the lush foliage and the calming atmosphere of the rainforest.]"
},
{
"from": "gpt",
"value": "Bad. The scene of the wild rabbit working as a salesperson was not generated."
}
] |
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 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 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. Basically correct."
}
] |
seed46_1173
|
videos/HRA_part2/1173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman clad in a futuristic, form-fitting, metallic blue bodysuit sprints down the pristine, white corridor of a space-age medical facility, illuminated by soft, ambient lighting. Her athletic build and focused gaze convey urgency and determination. In the next scene, she continues her run, passing by high-tech medical equipment and digital screens displaying complex data. The sleek design of the facility, featuring curved walls and glowing lines, adds a sense of advanced technology. Finally, she reaches a critical area, marked by a large, illuminated circle on the floor, where she stops abruptly, ready to face whatever emergency awaits her.]"
},
{
"from": "gpt",
"value": "Bad. The video shows missing limbs and head of the female character."
}
] |
seed42_1010
|
videos/HRA_part0/1010.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a dark gray jacket and light gray shirt, sits at a desk in a space hotel room, the Earth visible through the window behind him. He wipes the screen of his laptop with a cloth, revealing the reflection of the planet. The room is illuminated by soft, ambient light, giving it a futuristic yet cozy feel. The writer's focused expression and the clean, high-tech environment convey a sense of dedication and precision in his work, all set against the backdrop of the majestic Earth, which fills the large window behind him.]"
},
{
"from": "gpt",
"value": "Bad. The wiping motion is not continuous, and it is done in the air in front of the computer screen."
}
] |
seed42_2045
|
videos/HRA_part0/2045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its distinctive black and white fur, walks through a bustling cityscape filled with towering skyscrapers, neon signs, and busy streets. It navigates the urban environment with a curious yet calm demeanor, passing by modern architecture and city life, creating a surreal juxtaposition between nature and metropolis. The panda's presence among the high-rise buildings and urban hustle highlights an unexpected encounter between wildlife and the human-built world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1897
|
videos/HRA_part1/1897.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 depiction, a gray and white cat, wearing a miniature spacesuit complete with a gold badge, is seen floating weightlessly in a spaceship, its paws gently touching a control panel. The cat, named Ambassador Fluff, is on a diplomatic mission among the stars, representing Earth's feline population. As zero-gravity music plays, the cat begins to dance, its movements fluid and graceful in the microgravity environment, embodying the spirit of intergalactic diplomacy through the universal language of dance. Behind Ambassador Fluff, a view of distant galaxies and nebulae can be seen through the spaceship's windows, adding to the surreal and majestic atmosphere of this cosmic dance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1938
|
videos/HRA_part1/1938.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a clean, white uniform and a green apron, is diligently scrubbing the bathroom floor in a hospital setting, her focused gaze and determined posture highlighting her commitment to hygiene. She uses a green scrub brush and a bucket of soapy water, her actions methodical and thorough. The bathroom is modern and well-lit, featuring stainless steel fixtures and a clean, white toilet, sink, and shower stall. The nurse's attention to detail and her professional demeanor underscore the importance of maintaining a sterile environment in the healthcare facility.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's hand and the cleaning brush in her hand are generated abnormally, with distortion and deformation in the middle frames."
}
] |
seed46_2104
|
videos/HRA_part2/2104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, donning a crisp white shirt and black vest, stands in a spacious living room with hardwood floors and a large window, engaging in an unusual task. He is diligently assembling a wooden table using various tools, demonstrating unexpected handyman skills. As the scene progresses, the fully assembled table is revealed, complete with a tablecloth and set for a meal, blending elements of his professional service role with a domestic setting. The waiter then proceeds to polish the silverware, juxtaposing his traditional duties with the earlier DIY activity, all within the same elegant residential space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_216
|
videos/HRA_part0/216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male lawyer, wearing a dark suit and a white shirt, attentively listens in a courtroom setting, his face expressing concern and focus. Seated at a wooden desk adorned with legal documents, he leans forward intently, his right hand resting on his chin in a gesture of deep consideration. The background features a traditional court setting with wood-paneled walls and a high ceiling, emphasizing the seriousness and formality of the legal proceedings. The judge and other participants are partially visible, adding context to the scene without detracting from the central figure of the engaged lawyer.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, and the hands are severely twisted."
}
] |
seed44_2937
|
videos/HRA_part1/2937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling fire station, a seasoned firefighter, clad in a navy blue uniform and a yellow reflective vest, expertly operates a coffee machine. The walls are adorned with firefighting equipment and memorabilia, adding to the authenticity of the setting. The firefighter, with a rugged beard and a focused gaze, pours the freshly brewed coffee into a white mug with the fire department's emblem. The room is illuminated by natural light streaming in from a large window, casting a warm glow on the firefighter as he adds a touch of cream to his coffee, embodying a moment of calm amidst the high-stakes environment of emergency response.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2288
|
videos/HRA_part0/2288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 black jacket and khaki pants, is seen in a close-up shot, wiping his brow with a white handkerchief. Behind him, a herd of antelopes can be observed grazing in a vast, grassy savanna, creating a juxtaposition between the director's world and the natural habitat of the antelopes. The director's weathered face and focused gaze suggest a moment of intense concentration during a film shoot, while the antelopes continue their serene existence in the background, unaware of the human drama unfolding nearby.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1725
|
videos/HRA_part0/1725.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a crisp white shirt and black pants, serves a dingo seated at a table set amidst dense green thickets. The dingo, wearing a red bandana, looks expectantly at the waiter, who holds a platter of food. Nearby, a swimming pool glistens under the sun, its clear blue water contrasting with the lush vegetation surrounding it. The waiter, with a friendly smile, places the dish before the dingo, who eagerly leans forward, creating a surreal yet charming tableau.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2737
|
videos/HRA_part2/2737.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a tranquil, shallow pond surrounded by lush vegetation, a large moose with a wide, flat antler rack stands with its head submerged underwater. As it lifts its head, water droplets cascade down its face. The animal then proceeds to shake its head vigorously from side to side, flinging water off its fur and antlers. Its ears flap dynamically during the shaking motion, and its tongue can be seen hanging out playfully. Throughout the scene, the moose's eyes remain closed, indicating its enjoyment of the refreshing activity.]"
},
{
"from": "gpt",
"value": "Bad. The moose's ears flapping and tongue hanging out mentioned in the caption do not appear in the video."
}
] |
seed42_2551
|
videos/HRA_part0/2551.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, dressed in a flowing white robe with gold trim, stands in a vast, dimly lit space chamber, holding a fluffy rabbit gently against her chest. The chamber is filled with rows of benches, each occupied by similarly dressed figures, all facing an altar adorned with candles and space-themed decorations. The student caresses the rabbit lovingly, her face expressing deep reverence and peace, as the soft light from the candles illuminates the scene, casting a warm glow on everyone present. The rabbit, seemingly aware of its significant role, remains calm and still, adding a sense of serenity to the unique religious ceremony taking place among the stars.]"
},
{
"from": "gpt",
"value": "Bad. The person's face is distorted, hands are twisted, the rabbit's body is distorted, and the head is twisted."
}
] |
seed42_1516
|
videos/HRA_part0/1516.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious male engineer, wearing a blue button-down shirt and glasses, meticulously irons his clothes in a modestly furnished room with a wooden floor and cream walls. He stands at an ironing board covered with a white cloth, carefully smoothing out wrinkles in a garment. The room is illuminated by natural light from a window behind him, casting a warm glow over the scene. On the wall to his right, a large painting in shades of green adds a splash of color to the otherwise simple space. Beside the window, a desk with a laptop and engineering blueprints hints at his professional life, while a shelf filled with books and a houseplant brings a personal touch to the environment.]"
},
{
"from": "gpt",
"value": "Bad. The head and hands of the person in the video, as well as the iron, were poorly generated."
}
] |
seed42_1443
|
videos/HRA_part0/1443.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and surreal scene, a large, gray rhinoceros leaps into the air, defying expectations, with its powerful legs extended and body arched. This incredible moment is captured against a backdrop of a vast savanna landscape, dotted with trees and stretching to a distant horizon under a bright blue sky. The rhino, known for its heavy, armored skin and imposing horn, is shown mid-jump, creating a unique and unforgettable image that highlights the animal's unexpected agility and strength.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1927
|
videos/HRA_part0/1927.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a casual green shirt and khaki pants, finds inspiration while leaping energetically onto a large rock in a lush forest setting, as if escaping the ordinary to explore the unknown. Nearby, an awe-inspiring mammoth, seemingly from another time, stands majestically under a canopy of ancient trees, its massive frame and textured skin adding an element of prehistoric wonder to the scene. The juxtaposition of the writer's leap and the mammoth's presence creates a surreal and captivating narrative, blending human creativity with the grandeur of nature's past.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2549
|
videos/HRA_part1/2549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, wearing a beige jacket and dark trousers, sits on a wooden dock by the water's edge. He gently caresses a small, curious otter that has climbed onto his lap, looking into its eyes with a warm smile. The otter, with its sleek brown fur and bright, inquisitive gaze, seems comfortable and at ease in the actor's presence. The scene is set against a serene backdrop of gently lapping waves and lush greenery, capturing a tender moment between human and animal in a peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The person's face in the video is slightly distorted, the hands are distorted, and the otter's head is distorted."
}
] |
seed46_1738
|
videos/HRA_part2/1738.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 forest clearing illuminated by dappled sunlight, a man with short brown hair, wearing a blue shirt, khaki shorts, and brown shoes, stands facing a deer. The deer, with its head lowered, is a majestic eight-point stag. The man gently wipes something from the deer's face using a soft cloth, revealing a tender moment of human-animal interaction. The scene is peaceful, with the man's caring gesture toward the wild creature highlighting the connection between humans and nature.]"
},
{
"from": "gpt",
"value": "Normal. The action of the deer lowering its head can be seen, but the action of the man wiping the deer's face with a soft cloth is not continuous and has a sudden change."
}
] |
seed44_2626
|
videos/HRA_part1/2626.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating underwater scene, a cluster of jellyfish, predominantly moon jellyfish, gracefully floats in a harmonious formation. Their translucent bell-shaped bodies, illuminated by a soft blue light, reveal intricate patterns and textures. Surrounding them are various marine creatures, including small fish and other jellyfish species, adding to the vibrant ecosystem. The jellyfish pulsate rhythmically, propelling themselves through the water, while their trailing tentacles gently undulate, creating a mesmerizing visual display in this serene aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2041
|
videos/HRA_part2/2041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is showcased on a wooden cutting board, its right side facing upward, displaying a clean, unblemished surface. The fish, with a length exceeding two feet, is set against a background of green herbs, lemon wedges, and a chef's knife, evoking a culinary preparation scene. The halibut's left eye is positioned prominently on the top side, indicating the fish's freshness, while its gills are slightly open, revealing the vibrant red color within. The overall setup, with the halibut as the central focus, is meticulously arranged to highlight the quality and size of the fish, perfect for a gourmet seafood dish.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1423
|
videos/HRA_part1/1423.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a gray sweater and glasses, sits at a rustic wooden desk in a cozy room filled with books, typing away on a vintage typewriter. Beside her, a curious ferret emerges from a cage, its bright eyes scanning the environment. The animal then embarks on a playful walk across the desk, exploring various objects like a small potted plant and a glass jar. Throughout the scene, the writer continues to type, occasionally glancing at the ferret with a smile, capturing the essence of a peaceful day in her life, surrounded by literary works and a charming pet.]"
},
{
"from": "gpt",
"value": "Bad. The actions of playing and exploring are very unsmooth and uncoordinated."
}
] |
seed46_2790
|
videos/HRA_part2/2790.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and a helmet, walks alongside a majestic jaguar in a surreal scene. Both stride purposefully on a dirt path, the wild cat's spots contrasting with the firefighter's bright orange suit. The setting sun casts a golden glow, highlighting the unusual pair as they move together, the jaguar's powerful form and the firefighter's protective stance forming an unforgettable image. The firefighter's heavy boots and the jaguar's confident gait are in sync, creating a unique bond between human and beast in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the person in the video are distorted, the face is distorted, the jaguar's claws are distorted, and the legs are distorted."
}
] |
seed46_1639
|
videos/HRA_part2/1639.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with curly brown hair pulled into a bun, wearing a gray T-shirt and jeans, sits on a wooden chair in a spacious studio filled with natural light. She is engrossed in painting a large canvas with vibrant colors using a palette knife, surrounded by various art supplies like brushes, paints, and rags. The room is decorated with other colorful paintings, potted plants, and a large window letting in ample sunlight, creating a warm and inspiring atmosphere. The woman's focused expression and the splashes of paint on her clothes and hands highlight her passion and dedication to her craft.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_251
|
videos/HRA_part2/251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a spacesuit decorated with patches and emblems swims effortlessly in zero gravity within a space station habitat. The habitat, illuminated by soft, ambient lighting, features curved walls and large windows offering breathtaking views of the cosmos. A pet lizard, also weightless, floats nearby, its scales reflecting the light in iridescent patterns. The engineer gently propels themselves through the water-filled enclosure, designed to simulate Earth's aquatic environments, while the lizard seems to hover curiously beside them, both adapted to life in the microgravity of the space station.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1017
|
videos/HRA_part0/1017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, upscale restaurant filled with the clinking of glasses and chatter, a waiter in a crisp, black uniform expertly navigates the lively dining room. He deftly pushes a polished, stainless steel service cart laden with fine china and gleaming silverware, carefully avoiding any contact with the patrons enjoying their meals. The elegant space, adorned with hanging lights casting a warm glow and walls decorated with framed artwork, provides a sophisticated setting for this scene of seamless service execution.]"
},
{
"from": "gpt",
"value": "Normal. The server's fingers in the video are not fully generated."
}
] |
seed44_1615
|
videos/HRA_part1/1615.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, dressed in a sky-blue scrubs top and matching cap, tends to a patient in an expansive, sunlit grassland. She gently wipes the patient's face with a soft cloth, her caring demeanor evident in her focused eyes and gentle smile. The serene landscape of tall, swaying grass and distant, rolling hills provides a peaceful backdrop to the intimate moment of care. The nurse's attire, emblematic of her profession, contrasts beautifully with the lush greenery, highlighting her role as a caregiver in this unexpected outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1490
|
videos/HRA_part1/1490.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a helmet, leaps over debris inside a burning apartment complex, the intense flames and smoke creating a dramatic backdrop. The scene highlights the heroism and physical demands faced by firefighters in rescue operations. The exterior of the complex shows multiple stories engulfed in fire, emphasizing the scale of the emergency. The firefighter's decisive action, jumping over obstacles, symbolizes the urgent and dangerous nature of their mission to save lives and contain the blaze.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1208
|
videos/HRA_part0/1208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meticulously crafted aquarium filled with vibrant green aquatic plants, a ghost shrimp, nearly transparent with faint blue-gray veins, clings to a piece of driftwood. Its delicate antennae wave gently in the water current, and its legs grip the wood securely. Nearby, a stone arch adds to the scenery, while the shrimp's see-through body allows a glimpse of its internal organs. The shrimp's translucent exoskeleton and the lush underwater environment create a captivating scene, enhanced by the play of light and shadow in the tank.]"
},
{
"from": "gpt",
"value": "Bad. The ghost shrimp's body is twisted."
}
] |
seed44_1046
|
videos/HRA_part1/1046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 diligent worker, clad in a high-visibility yellow vest, blue jeans, and a brown jacket, methodically rakes a large pile of autumn leaves into a meticulously organized heap. The scene is set in a spacious backyard, bordered by a wooden fence, with additional piles of leaves scattered throughout the yard, indicating a day of hard work. The worker's focus is intense, his movements efficient, as he tackles the task with determination, the vibrant colors of the fallen foliage contrasting beautifully against the green grass.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2770
|
videos/HRA_part0/2770.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 legs and tail of the ibex in the video are not fully generated, the horns are deformed, and there are issues with the ears."
}
] |
seed44_2345
|
videos/HRA_part1/2345.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a doctor, clad in a crisp white lab coat, stands in a vibrant jungle setting, complete with lush green foliage and exotic flowers. Accompanied by a dingo, the duo begins to dance gracefully, the doctor's stethoscope swinging rhythmically as they move. The dingo, surprisingly elegant, prances alongside, its fur glistening under the golden sunlight filtering through the canopy above. The two continue their dance, the doctor's glasses catching the light and the dingo's tail swishing in time, creating a surreal and joyful spectacle in the heart of the jungle.]"
},
{
"from": "gpt",
"value": "Bad. The doctor and the dog's movements in the video are very unsmooth and uncoordinated."
}
] |
seed44_3036
|
videos/HRA_part1/3036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A teenage boy wearing a red jacket and khaki pants is sprinting across a grassy field, his gaze fixed ahead with determination. As he runs, a small rabbit enters the frame from the bottom right corner, bounding alongside him. The student acknowledges the rabbit with a brief glance, but both continue their run, the student maintaining his focus and the rabbit keeping pace, against the backdrop of a clear blue sky and distant green hills.]"
},
{
"from": "gpt",
"value": "Bad. The boy's running in the video is very unsmooth, and his movements are uncoordinated."
}
] |
seed46_102
|
videos/HRA_part2/102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum-like setting filled with art galleries, a sleek and powerful jaguar, adorned with a golden collar, walks gracefully among the exhibits. The feline's presence captivates the attention, as it moves elegantly through the spacious hall, surrounded by classical sculptures and Renaissance paintings. Its confident stride and majestic demeanor contrast beautifully with the artistic masterpieces displayed on the walls, creating a unique juxtaposition between nature and culture. The golden collar it wears adds a touch of sophistication, making the jaguar appear almost like a living exhibit within the gallery space.]"
},
{
"from": "gpt",
"value": "Bad. The jaguar in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed44_2305
|
videos/HRA_part1/2305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student wearing a gray jacket walks through a vast, sunny temperate shrubland, with a yellow signpost and a lush green landscape stretching into the distance. The young man, carrying a backpack, strolls along a sandy path bordered by dense shrubbery, under a clear blue sky. He pauses to observe his surroundings, revealing a serene environment with distant mountains and a rich array of vegetation, including shrubs and small trees, all set against a backdrop of bright sunlight. Continuing his journey, he moves through the shrubland, which is characterized by its temperate climate and diverse plant life, offering a peaceful scene of nature and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the student in the video are missing, and the face is deformed."
}
] |
seed44_2048
|
videos/HRA_part1/2048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, with a brown body and lighter underbelly, playfully wipes its face with a paw, sitting upright against a backdrop of lush greenery. Nearby, a highway stretches into the horizon, lined with guardrails and dotted with cars moving in the distance, offering a contrast between nature and urban development. The otter, seemingly unperturbed by the nearby traffic, continues its grooming ritual, highlighting the coexistence of wildlife and human infrastructure.]"
},
{
"from": "gpt",
"value": "Normal. The otter in the video uses its paws to wipe its face almost normally, with only slightly uncoordinated movements."
}
] |
seed44_1356
|
videos/HRA_part1/1356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, vibrant green and iridescent, hovers in a close-up shot against a blurred background of lush vegetation. Its wings, a blur of motion, propel it as it feeds from a red salvia flower, the curved beak piercing the bloom. The bird's small size, quick movements, and the detailed feathers are highlighted, set against the rich greenery and soft, natural lighting. The scene captures the hummingbird's agility and the delicate interaction between the bird and the flower, encapsulating the beauty of nature in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The hummingbird's movements are not smooth."
}
] |
seed42_1072
|
videos/HRA_part0/1072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 director, donning a casual gray shirt and black cap, is shown engaged in an unexpected task: unclogging a drain. In the first scene, he is kneeling on a hardwood floor, attentively examining a drain with a serious look on his face. Next, he is seen plunging the clogged drain with a red plunger, demonstrating his hands-on approach to problem-solving. Following this, the director is depicted using a drain snake to clear the blockage, his expression one of determination. Lastly, he inspects the drain once more, now clean, with a look of satisfaction, his casual attire contrasting with his professional role.]"
},
{
"from": "gpt",
"value": "Normal. The red plunger is not very realistic, and the human hand appears deformed."
}
] |
seed44_1865
|
videos/HRA_part1/1865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two adult buffalo, with shaggy brown fur and impressive horns, engage in a tender moment. One buffalo affectionately caresses the other's face with its muzzle, displaying a rare display of gentleness and connection between these typically rugged creatures. The scene is set against a backdrop of lush grasslands and distant, rolling hills, capturing the essence of their wild habitat while highlighting the intimate bond shared by these majestic animals.]"
},
{
"from": "gpt",
"value": "Normal. The horns of the water buffalo on the left and the face of the adjacent water buffalo are missing when they overlap."
}
] |
seed44_1349
|
videos/HRA_part1/1349.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed figure, dressed in a full-body brown bear suit, performs a lively jig atop a lush, green heathland blanketed with purple heather flowers. The dancer's movements are energetic and joyful, their bear-clad form spinning and leaping against the vibrant landscape. The heathland stretches out behind them, dotted with patches of colorful blooms and tall grasses swaying in the breeze. The sky above is a brilliant blue, with wispy clouds adding texture to the horizon. Throughout the scene, the dancing bear remains the central focus, their animated presence captivating against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_3122
|
videos/HRA_part2/3122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brave firefighter, clad in full gear and a helmet, stands against the backdrop of a firetruck under a cloudy sky, waving confidently with his right hand. He wears a yellow reflective jacket over his equipment, adding a pop of color to the scene. In the next frame, he is seen from behind, still waving, with the red fire engine and a suburban neighborhood visible in the background. The firefighter then pauses his wave, looking intently at something off-camera, before continuing to wave amicably, his actions conveying reassurance and professionalism in the face of potential danger.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's arm-waving action is slightly unsmooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.