video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1554
|
videos/HRA_part2/1554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed man, wearing a navy suit with a light blue shirt and a dark blue tie, stands against a neutral gray background. He points to an unseen object or idea with a confident smile, engaging the viewer with his clear, green eyes. His neatly combed brown hair and clean-shaven face add to his professional appearance. The focus is solely on him, with no additional elements in the frame, as he points with his right index finger, inviting the audience to follow his gesture.]"
},
{
"from": "gpt",
"value": "Normal. The character's fingers are twisted."
}
] |
seed46_1761
|
videos/HRA_part2/1761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling train station filled with travelers, a diligent janitor wearing a yellow high-visibility vest is wiping down a large window, revealing the vibrant cityscape outside. The scene is set during the daytime, with bright sunlight illuminating the interior of the station. Among the crowd, a person dressed in a panda costume stands out, adding a whimsical touch to the busy environment. The janitor continues to clean the window, ensuring a clear view of the passing trains and the urban landscape beyond.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1894
|
videos/HRA_part1/1894.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a navy suit, white shirt, and striped tie, races through a lush green forest, holding a koala in one arm. The koala, clinging tightly, wears a tiny barrister's wig and round spectacles, adding a whimsical touch to the scene. They run past tall trees, ferns, and flowers, with the lawyer's facial expressions alternating between determination and a smile, highlighting the unusual yet playful nature of the chase. The vibrant forest setting, complete with sunlight filtering through the leaves, enhances the dynamic and surreal atmosphere of the scenario.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2022
|
videos/HRA_part1/2022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a brown plaid shirt and blue jeans, stands in the shallow end of a clear blue swimming pool, looking curiously at a squirrel perched on the edge. The squirrel, standing upright on its hind legs, holds a nut in its paws and peers intently into the water. Sunlight filters through the leaves of nearby trees, casting dappled shadows on the pool's surface and the green grass surrounding it. The farmer, with a straw hat tilted back on his head, seems to share a moment of mutual interest with the bushy-tailed creature, both pausing in their day's activities.]"
},
{
"from": "gpt",
"value": "Bad. The man is not standing in the shallow water area, which does not match the text description."
}
] |
seed44_253
|
videos/HRA_part1/253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent peacock, resplendent in its vivid blue and green plumage, struts regally across a lush, verdant garden, the sunlight dappling its feathers in a mesmerizing play of light and shadow. Its proud head, adorned with a striking crest, swivels gracefully as it surveys its domain. Suddenly, the peacock spreads its spectacular tail, revealing an eye-popping display of iridescent ocelli that seem to shimmer with an otherworldly glow. The air is filled with the rich, earthy scents of the foliage surrounding the bird, adding depth to this enchanting scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1989
|
videos/HRA_part0/1989.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned in a futuristic, silver metallic suit with a high collar and form-fitting design, rides a majestic, reddish-brown Martian horse across a vast, rocky terrain under a dusky, pinkish-orange sky. The horse gallops gracefully, its hooves kicking up red dust from the planet's surface, as the woman leans forward with determination. Suddenly, she dismounts and begins to dance, her movements fluid and expressive, set against the barren, alien landscape dotted with distant, rugged mountains. As she dances, her silver suit catches the dim light, creating shimmering reflections that contrast with the rough, rusty-red environment of Mars.]"
},
{
"from": "gpt",
"value": "Normal. The woman's arm is missing parts, fingers are not fully generated, the face is distorted, and the horse's legs are missing parts."
}
] |
seed46_1882
|
videos/HRA_part2/1882.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated female nurse, clad in a white uniform and wearing her hair in a bun, attentively checks a smoke detector mounted on the ceiling in a modern hospital hallway. The space is pristine and well-lit, with pale green walls and white trim, exuding a sense of cleanliness and professionalism. The nurse, displaying her commitment to safety, uses a long, red-handled tool to test the device, ensuring it functions properly in the healthcare environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1840
|
videos/HRA_part0/1840.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow safety vest over a gray shirt and black pants, experiences time dilation as he leaps into the air in a high school gymnasium. The scene is captured from four different angles: first, he is seen standing still, looking at the camera. Then, he jumps into the air, the motion slowed down to emphasize the effect of time dilation, his posture mid-leap. In the next frame, he is frozen mid-air, with a basketball hoop and a volleyball net visible in the background. Lastly, he is shown in slow motion again, this time with a look of determination on his face, highlighting the unique experience of time distortion during his jump.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video is distorted, with a twisted face, twisted arms, twisted legs, and twisted hands."
}
] |
seed42_1212
|
videos/HRA_part0/1212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wild salmon, exhibiting vibrant hues of silver, red, and green, swims gracefully in a crystal-clear river, its scales shimmering under the natural sunlight filtering through the water. The salmon's powerful body and forked tail are showcased as it propels itself upstream against the current, highlighting its determination and strength in nature's challenging environment.]"
},
{
"from": "gpt",
"value": "Bad. The salmon's swimming motion in the video is not smooth and coordinated."
}
] |
seed44_1601
|
videos/HRA_part1/1601.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single sand dollar lies on a bed of pristine white sand, its intricate pattern clearly visible against the stark background. Sunlight filters through crystal-clear water, casting a warm glow on the delicate creature. The sand dollar, positioned at a slight angle, reveals its stunning symmetry and fine details. Surrounding it, the sandy bottom is undisturbed, save for a few tiny grains caught in the gentle current, highlighting the serenity of the underwater scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3098
|
videos/HRA_part2/3098.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green 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": "Bad. The facial generation of the person and the chimpanzee in the video is blurry, and the limbs are distorted."
}
] |
seed42_2727
|
videos/HRA_part0/2727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin leaps from the crystal-clear ocean waters, its streamlined body glistening in the sunlight. The vibrant blue and silver hues of its scales contrast beautifully against the turquoise backdrop. In another scene, the marlin swims gracefully beneath the surface, its elongated bill leading the way as it navigates the underwater world. Surrounded by schools of smaller fish and the lush marine environment, the marlin embodies the power and elegance of life beneath the waves.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1945
|
videos/HRA_part1/1945.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a brown tweed jacket, sits at a wooden desk adorned with books and a typewriter, gently caressing a small, docile cheetah resting its head on the desk. The writer, with a neatly trimmed beard, looks intently at the camera, while the cheetah, with a collar and a bell, remains calm and attentive. The scene captures the unlikely companionship between the intellectual and the wild animal, set against a backdrop of a study filled with bookshelves and framed pictures.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2085
|
videos/HRA_part2/2085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sprightly beaver, donning a brown coat, scurries across a lush, green meadow under a partly cloudy sky. It dashes over the grass with its front paws lifted, revealing a clear view of its full body. Moments later, it continues its run, tail held high, near a wooden fence. The scene shifts to the beaver running alongside a tranquil stream, with trees in the background, showcasing its natural habitat. Lastly, it sprints with determination, its distinctive flat tail visible as it moves through its verdant environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2438
|
videos/HRA_part2/2438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, dressed in a futuristic silver spacesuit, is depicted in zero gravity within a space station habitat, performing a series of jumps against a backdrop of LED-lit panels. He executes a powerful jump, legs spread wide, arms extended, and face obscured by his helmet's visor, capturing the essence of weightlessness. In another frame, he appears to push off from a handrail, propelling himself through the air with a sense of effortlessness. Throughout the sequence, the space station's cylindrical structure, complete with porthole windows and complex machinery, provides a vivid setting for his graceful movements.]"
},
{
"from": "gpt",
"value": "Bad. The man's jumping in the video is very unsmooth, and his movements are uncoordinated."
}
] |
seed44_3071
|
videos/HRA_part1/3071.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut, clad in a spacesuit adorned with patches and equipped with a jetpack, orbits the Earth while holding a moose, its antlers visible. Below, on a pristine planet, a worker in a blue uniform tends to a pool, where a moose swims leisurely, its large frame gliding through the crystal-clear water. The worker, wearing a blue cap, looks up at the space-suited figure and the orbiting moose, a sense of wonder in their eyes. This juxtaposition of scenes captures the surreal and unexpected elements of life in space and on Earth.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut's hand and the reindeer in the hand are deformed in the video."
}
] |
seed44_2068
|
videos/HRA_part1/2068.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, middle-aged with a neatly trimmed beard and glasses, prepares coffee in a break room. He measures coffee grounds into a filter with precision, ensuring the perfect cup. Wearing a gray shirt under a black vest and black pants, he pours water from a clear pitcher into the coffee maker with care. As the machine brews, he waits patiently, the steam rising from the freshly brewed coffee creating a warm, inviting atmosphere in the small space. He then pours the coffee into a white mug, the steam gently billowing upward, ready to enjoy a well-deserved break.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2578
|
videos/HRA_part1/2578.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dreamlike scenario, a distinguished doctor, wearing a full lab coat and stethoscope, races alongside a nimble ibex on a vibrant green meadow. The doctor, maintaining a focused gaze, keeps pace with the ibex, which bounds gracefully across the landscape, showcasing the unlikely companionship between human and wild animal. The scene is set against a backdrop of rolling hills and clear blue skies, creating a vivid and unexpected visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the antelope in the video are missing, the face is distorted, the horns are deformed, the doctor's hands are deformed, and the body is not generated."
}
] |
seed42_2039
|
videos/HRA_part0/2039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal cosmic setting, a majestic cheetah, adorned with a golden collar and walking on zero-gravity platforms, traverses through an infinite space library. Surrounded by floating bookshelves filled with ancient tomes, the cheetah moves gracefully, its gaze focused on a distant celestial body. The library, illuminated by ethereal starlight, showcases an array of knowledge from across the universe, with the cheetah embodying wisdom and power as it explores this otherworldly domain.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's movements in the video are uncoordinated."
}
] |
seed44_2897
|
videos/HRA_part1/2897.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique close-up of a baby kangaroo, or joey, wearing a red pouch, crawls on its front limbs across a wooden surface, demonstrating its early stages of mobility. The joey, with its distinctive marsupial features, including large ears and a small snout, is captured in high definition, revealing the intricate details of its fur and movements. Against a simple wooden background, the joey's red pouch stands out, adding a pop of color to the frame. The focus remains solely on the joey throughout, as it diligently crawls forward, showcasing its determination and innocence.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2660
|
videos/HRA_part2/2660.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee dressed in a miniature waiter's outfit, complete with a crisp white shirt, black vest, and bow tie, walks on its hind legs through a lush, green forest. It carries a small silver tray balanced on its right hand, adding to the whimsical scene. The chimp's expressive face, with furrowed brows and a slight smile, conveys a sense of playfulness and determination as it navigates the natural environment, surrounded by tall trees and dappled sunlight filtering through the leaves.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1347
|
videos/HRA_part0/1347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged doctor with short, neatly styled brown hair, wearing a white lab coat over a blue button-up shirt and khaki pants, is comforting a crying young patient. The child, dressed in a yellow T-shirt and blue shorts, sits on a medical examination table, clutching a stuffed animal, while the doctor gently places a reassuring hand on the child's shoulder. The scene takes place in a brightly lit clinic room, with medical posters on the walls and a computer screen visible in the background. The doctor's empathetic expression and the child's teary face convey a moment of vulnerability and care in a clinical setting.]"
},
{
"from": "gpt",
"value": "Bad. Both the doctor's and the child's hands appear deformed."
}
] |
seed46_1993
|
videos/HRA_part2/1993.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Caspian tern, the largest species, soars over a coastal landscape, its gray and white plumage gleaming under the sun. It has a bright orange-red bill with a black tip, and its wingspan stretches wide as it glides over the water. Perched on a sandy shore, the bird preens its feathers, revealing its distinctive black crest and elegant posture. In flight again, the tern's powerful wings propel it forward, and it banks sharply, showcasing its agility against a backdrop of rolling clouds and shimmering sea. Finally, diving gracefully into the water, it emerges triumphant with a small fish in its beak, demonstrating its hunting prowess in stunning detail.]"
},
{
"from": "gpt",
"value": "Bad. The Caspian tern's flight in the video is not smooth, and the movements are uncoordinated."
}
] |
seed44_1407
|
videos/HRA_part1/1407.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer clad in a blue shirt and gray pants is seen interacting with a chimpanzee in a laboratory setting. The chimpanzee, sitting upright on a chair, holds a wipe in its hand and begins wiping a surface, demonstrating tool use under the watchful guidance of the engineer. The scene captures the unique bond between human and primate in a research context, highlighting the chimpanzee's ability to mimic and perform tasks typically associated with human dexterity and intelligence.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's movements in the video are not smooth."
}
] |
seed42_1969
|
videos/HRA_part0/1969.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow Labrador dog, wearing a red collar and tags, happily swims in a natural hot spring pool, surrounded by lush green vegetation and a wooden dock. The water, clear and inviting, gently laps at the dog's fur as it paddles with ease. The dog's joyful expression and the serene environment of the hot springs create a peaceful and picturesque scene, enhanced by the vibrant greenery and the warm, bubbling water.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1477
|
videos/HRA_part2/1477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating scene, a distinguished film director, clad in a black jacket, blue jeans, and brown boots, stands on a rocky outcropping, passionately directing the action. Nearby, an agile ibex leaps over a boulder with remarkable grace, its brown fur and curved horns vivid against the craggy landscape. The camera focuses on the ibex mid-jump, capturing the animal's strength and agility, while the director observes intently, his silhouette framed against the dramatic mountain scenery.]"
},
{
"from": "gpt",
"value": "Bad. The sheep's body is twisted, the face is distorted, and the legs are twisted."
}
] |
seed46_296
|
videos/HRA_part2/296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lawyer, dressed in a dark suit, white shirt, and blue tie, finds himself inexplicably transported to a different era, reminiscent of the TV show 'Quantum Leap.' Crawling through a dimly lit, gritty tunnel, he struggles to understand his time-bending predicament. The tunnel walls are adorned with graffiti and debris, adding to the disorienting atmosphere. Suddenly, the lawyer emerges into a bustling courtroom from the past, where he must now navigate unfamiliar legal challenges. His bewildered expression and the stark contrast between his modern attire and the vintage courtroom setting underscore the surreal nature of his quantum leap experience.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2635
|
videos/HRA_part0/2635.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform with a name tag, unloads a commercial-grade stainless steel dishwasher in a busy restaurant kitchen. He is surrounded by various kitchen tools and appliances, including a large stand mixer, a high-performance stove, and multiple pots and pans. The chef efficiently removes clean dishes, stacking plates and placing utensils in their designated areas. Throughout the process, the bustling environment of the kitchen is evident, with other chefs and staff working diligently in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1217
|
videos/HRA_part1/1217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, embodying a rugged yet sensitive character, is depicted in a subtropical desert landscape, where sparse vegetation clings to life among sand dunes and rocky outcrops. The scene opens with a close-up of the actor's hand gently caressing the weathered bark of a mesquite tree, conveying a sense of connection with nature. Moments later, he is shown standing still, eyes closed, face uplifted, feeling the warm desert breeze on his skin, wearing a simple linen shirt and trousers that blend with the earthy tones of the surroundings. The camera then captures him walking barefoot across the sandy terrain, leaving faint footprints that quickly disappear under the shifting sands, highlighting the transient beauty of the desert. Finally, he sits cross-legged, hands resting on his knees, in a meditative pose, his face reflecting inner peace, as the sun begins to set, casting long shadows and painting the sky in hues of orange and pink.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are distorted, face is contorted, and legs are twisted."
}
] |
seed42_1931
|
videos/HRA_part0/1931.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [On a sandy beach under clear blue skies, three young children, two boys and a girl, wearing colorful swimsuits and sunglasses, jump gleefully into the air in slow motion. Their silhouettes are highlighted by the sun, casting playful shadows on the sand. They leap again, this time with the vast ocean as their backdrop, their laughter echoing in the warm coastal breeze. Their final jump is captured mid-air, faces full of joy and wonder, the sea gently lapping at the shore behind them, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Bad. The character's jumping in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed42_2928
|
videos/HRA_part0/2928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, typically known for its sturdy build and earthy tones, is depicted in an unexpected scenario, engaging in a joyful dance within its natural habitat. The badger, adorned with a red bow tie and a small top hat, moves energetically to an unseen beat, surrounded by lush greenery and under the shade of towering trees. Its dance is characterized by playful twirls and energetic hops, a stark contrast to its usual demeanor, all captured in a whimsical and vibrant scene that highlights the unexpected delight of a dancing badger in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The badger's body and limbs have developed mutant deformities."
}
] |
seed44_1097
|
videos/HRA_part1/1097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 great horned owl perches regally on a rugged branch, its piercing yellow eyes gazing intently into the distance. It's nestled among lush greenery, with sunlight filtering through the leaves, casting a warm glow on the owl's mottled brown and grey feathers. The owl's large, expressive eyes stand out against its feathered face, framed by tufts resembling horns. Its beak, curved and sharp, complements the fierce yet serene demeanor of this nocturnal hunter, set against a backdrop of dense forest vegetation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1765
|
videos/HRA_part1/1765.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and sporting sunglasses, stands with his arms crossed, observing the scene at a busy dock. Suddenly, a majestic deer emerges from the background, filled with lush greenery, and leaps gracefully over a small obstacle, drawing the attention of the officer and dock workers alike. The officer watches intently as the deer bounds across the wooden planks, its movements fluid and effortless, before disappearing into the foliage beyond the docks. Throughout the scene, the officer remains poised and watchful, his presence a testament to the unexpected encounters that can occur even in the midst of urban landscapes.]"
},
{
"from": "gpt",
"value": "Bad. The deer's legs became deformed, and its body eventually twisted and distorted."
}
] |
seed46_2287
|
videos/HRA_part2/2287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, complete with helmet and heavy-duty gear, takes a break from the norm as he meticulously vacuums a cozy living room, adorned with a plush sofa, rustic wooden coffee table, and vibrant houseplants. The scene opens with a close-up of the vacuum cleaner, a stark contrast to the typical firefighting tools, before panning to reveal the dedicated firefighter, hose in hand, methodically cleaning the carpet. The camera then captures the firefighter's gloved hands guiding the vacuum, followed by a shot of him standing upright, holding the vacuum hose, and looking content amidst a tidy room, where a tidy bookshelf and comfortable armchair complete the domestic setting.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm, hand, face, and leg are distorted in the video, as well as the item they are holding."
}
] |
seed42_3117
|
videos/HRA_part0/3117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man in a tan vest and brown pants walks purposefully through a dense forest, his muscular build and focused gaze conveying strength and determination. Beside him, a large, colorful lizard with vibrant green and orange scales scurries along, keeping pace effortlessly. The lush vegetation of the jungle surrounds them, with tall trees overhead filtering the sunlight into dappled patches on the forest floor. The man and the lizard continue their journey together, navigating the complex terrain as they move deeper into the wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The lizard in the video was generated abnormally, the man's face was generated unclearly, and his fingers were deformed."
}
] |
seed44_2019
|
videos/HRA_part1/2019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, dressed in a straw hat, blue shirt, and khaki shorts, playfully swims in a clear, freshwater pond, holding a rabbit securely above the waterline. The farmer, now wearing a wide-brimmed hat, blue button-down shirt, and khaki shorts, gently cradles the rabbit, which sits comfortably in his hands, as they both float on the surface of the water. The idyllic scene is set against a backdrop of lush greenery and clear blue skies, capturing the essence of a peaceful rural life.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, the arms are twisted, the hands are deformed, and the rabbit's face is distorted."
}
] |
seed46_2397
|
videos/HRA_part2/2397.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Turkish market, vibrant stalls brim with colorful spices, fresh fruits, and artisan goods, while traditional music fills the air. A vendor proudly displays a variety of flatbreads, including lahmacun topped with minced meat and vegetables, and pide with cheese and herbs. Patrons haggle over prices, their animated gestures and lively chatter adding to the energetic atmosphere. Amidst the crowd, a man in a fez hat enjoys a cup of strong Turkish coffee, seated at a small table under a canopy of hanging lanterns, encapsulating the rich culture and daily life of Turkey.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_303
|
videos/HRA_part0/303.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 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 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": "Bad. The manta ray's fins are deformed, and the eyes have not been generated."
}
] |
seed44_1100
|
videos/HRA_part1/1100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 parallel universe setting, a firefighter, identifiable by his black helmet with a shiny badge, black uniform, and red suspenders, crawls on all fours through a desolate urban landscape. The cityscape features a large, gray building with broken windows and a dark, cloudy sky. The firefighter's movements are slow and deliberate, as if navigating through a hazardous environment. His gear includes a heavy-duty jacket, sturdy gloves, and a breathing apparatus strapped to his back, alluding to the dangerous conditions he faces. Despite the bleak surroundings, the firefighter's determination is evident in his focused gaze and resolute posture.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand was not fully generated, and the legs deformed during crawling."
}
] |
seed42_236
|
videos/HRA_part0/236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical dry forest, an empathetic nurse, clad in a white uniform, gently caresses the cheek of an elderly patient sitting on a wooden bench, offering comfort and care amidst the lush, arid surroundings. Nearby, a stethoscope rests on a picnic table, hinting at a medical check-up. The nurse, wearing a white blouse, khaki pants, and a name badge, tenderly touches the patient's arm, conveying compassion and attentiveness. Surrounded by the unique flora of the subtropical dry forest, including cacti and succulents, the scene captures a moment of human connection and medical care in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1533
|
videos/HRA_part0/1533.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a red shirt and dark pants, stands at the edge of a vast highway interchange, bathed in the golden glow of twilight. With city lights twinkling in the distance, he begins to dance, his movements expressive and free, contrasting with the concrete jungle around him. Cars whiz by on multiple levels of the highway, their headlights and taillights creating streaks of color against the dusky sky. The man continues to dance, his silhouette framed by the urban landscape, embodying a sense of liberation amidst the urban sprawl.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs in the video have issues, and his face is blurry."
}
] |
seed46_1376
|
videos/HRA_part2/1376.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark uniform with a badge and a radio attached to his belt, stands with a serious expression in the middle of an urban street, partially illuminated by the glow of a streetlight. In the background, a large, gray wolf leaps over a chain-link fence in a single, powerful bound, its eyes locked onto something unseen beyond the frame. The scene captures the juxtaposition of law enforcement and untamed nature, with the officer's authoritative presence contrasted by the wolf's wild, instinctive leap.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1105
|
videos/HRA_part0/1105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a badge clearly visible, traverses a vast wetland landscape, the lush greenery contrasting sharply with his authoritative attire. He is seen wading through shallow water, his boots partially submerged, indicating a purposeful journey through this natural terrain. Moments later, he is fully immersed in swimming, his uniform now soaked, navigating the intricate network of waterways under a cloudy sky. This scene captures the unexpected sight of a law enforcement figure engaging with the wild, uncharted environment of the wetlands.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1142
|
videos/HRA_part0/1142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 gaunt writer, clad in a brown leather jacket, gray t-shirt, and dark jeans, crawls through a desert landscape, reminiscent of a jackal, with a vintage typewriter strapped to his back. The scene opens with him crawling on sandy terrain, his face reflecting determination and resolve. Next, he continues his arduous journey, his clothes and skin stained with dirt, showcasing his unwavering commitment to his craft. The camera then captures him from above, emphasizing his small figure against the vast, barren environment. Lastly, he pauses to rest, the camera focusing on his weathered hands as they gently touch the typewriter, symbolizing his dedication and the intimate connection between the writer and his instrument.]"
},
{
"from": "gpt",
"value": "Bad. The crawling motion can be seen, but the character's limbs are not coordinated, and the movements are discontinuous and abrupt."
}
] |
seed46_2414
|
videos/HRA_part2/2414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant orchard filled with apple trees heavy with ripe fruit, a large brown bear stands on its hind legs, its shaggy fur glistening in the dappled sunlight. It reaches up with a massive paw, gently swiping at the low-hanging branches laden with apples. The bear then lowers itself to all fours, picking up an apple it has dislodged, and wipes it carefully on its thick fur before taking a hearty bite, savoring the sweet, juicy flavor amidst the peaceful surroundings of the orchard.]"
},
{
"from": "gpt",
"value": "Normal. The brown bear's movements are not smooth."
}
] |
seed44_1253
|
videos/HRA_part1/1253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant scene set within lush wetlands, several figures clad in elaborate costumes dance energetically, their movements synchronized in a captivating performance. The dancers wear colorful outfits adorned with feathers and intricate patterns, their faces painted in festive designs. The backdrop showcases the beauty of the wetlands, with tall reeds swaying gently in the breeze and waterfowl flying overhead. Sunlight filters through the clouds, casting a warm glow on the dancers as they leap and twirl, embodying the spirit of nature in their lively dance.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is severely distorted, the arms are severely twisted, and the legs are severely distorted."
}
] |
seed42_1135
|
videos/HRA_part0/1135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a utility belt, leaps into the air against a backdrop of cosmic dust swirling in the night sky, creating a surreal and dramatic scene. The officer's silhouette is highlighted by the celestial phenomenon, with the dust storm's ethereal glow illuminating the surroundings. The jump, captured mid-air, adds a dynamic element to the composition, juxtaposing the grounded authority figure with the otherworldly cosmic event.]"
},
{
"from": "gpt",
"value": "Bad. A third hand appears on the person, and one leg is amputated. The face is not blurry but the facial features are not fully generated."
}
] |
seed44_3196
|
videos/HRA_part1/3196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, wearing a black tank top, dark jeans, and a silver necklace, stands against a backdrop of a sandy beach and clear blue skies. He jumps into the air, guitar in hand, against the stunning landscape of palm trees and a pristine shoreline. His silhouette is highlighted by the golden hour sunlight, casting a warm glow over the scene. The camera captures the moment of mid-air suspension, emphasizing the dynamic energy of the performance, with the tranquil beach serving as a picturesque contrast to the vibrant action.]"
},
{
"from": "gpt",
"value": "Bad. The musician's face in the video is distorted, hands and feet are deformed, and the limbs of the musician in the middle frames are severely twisted and flying around randomly."
}
] |
seed46_2055
|
videos/HRA_part2/2055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 train station, a middle-aged doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, carries a brown leather bag. He walks purposefully past a massive, lifelike mammoth skeleton displayed as a scientific exhibit, the structure towering above the busy commuters. The scene captures the juxtaposition of the prehistoric and the modern, with the well-lit, contemporary train station bustling with people going about their day, while the imposing mammoth skeleton looms as a reminder of Earth's ancient past.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's face and hands, the passenger's head, and the mammoth skeleton generation have issues."
}
] |
seed44_2168
|
videos/HRA_part1/2168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly rendered subtropical moist forest, a peculiar scene unfolds: a doctor, clad in a crisp white lab coat over khaki shorts and a blue polo shirt, kneels beside a serene pool. Nearby, a badger, unusually sporting a tiny red swim cap, paddles leisurely in the clear waters, its eyes closed in blissful enjoyment. The lush vegetation surrounds them, with sunlight filtering through the dense canopy, casting dappled shadows on the ground. This unexpected encounter between a human doctor and a swimming badger in the heart of a lush forest creates a captivating and surreal moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1767
|
videos/HRA_part1/1767.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."
}
] |
seed44_2726
|
videos/HRA_part1/2726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cod fish is presented on a bed of ice, its body a pristine silver with a distinctive dark spot pattern. The fish's eyes are bright and clear, indicating freshness, while the gills are a vivid red. The scene is set in a bustling fish market, with other varieties of seafood visible in the background, adding to the atmosphere of a vibrant marketplace. The focus remains on the cod, emphasizing its quality and size, perfect for a gourmet meal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1394
|
videos/HRA_part2/1394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, donning a classic black vest, crisp white shirt, and black tie, diligently cleans the expansive windows of a charming bistro. The scene is set against a vibrant city backdrop, with the golden hour casting a warm glow. He meticulously wipes the glass, revealing the bustling café interior, filled with patrons enjoying their meals. The waiter's attention to detail is evident as he ensures every corner of the window is spotless, enhancing the inviting atmosphere of the establishment.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, and the face is slightly deformed."
}
] |
seed46_1435
|
videos/HRA_part2/1435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate musician, donning a dark green shirt and a brown fedora, is captured in a close-up shot, staring intensely into the distance with a pensive look. His rugged appearance, complete with a well-groomed beard, conveys a sense of depth and artistic contemplation. The focus is on his expressive eyes, which seem to hold stories of experiences and inspiration, hinting at the creative energy simmering beneath the surface. Behind him, a dimly lit stage with musical instruments hints at his profession, while the overall atmosphere exudes a mood of anticipation and reflection.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3091
|
videos/HRA_part2/3091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man sits at a desk, bathed in the warm glow of a table lamp, surrounded by books and papers. He is wearing a gray t-shirt and dark glasses, and has a full beard. He yawns widely, stretching his arms above his head, showing signs of fatigue. His computer screen reflects the light, partially obscuring his face, as he leans back in his chair, the room's atmosphere conveying a sense of late-night writing and contemplation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3091
|
videos/HRA_part0/3091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man sits at a desk, bathed in the warm glow of a table lamp, surrounded by books and papers. He is wearing a gray t-shirt and dark glasses, and has a full beard. He yawns widely, stretching his arms above his head, showing signs of fatigue. His computer screen reflects the light, partially obscuring his face, as he leans back in his chair, the room's atmosphere conveying a sense of late-night writing and contemplation.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video can be clearly seen yawning and stretching his arms high over his head, the movements are basically normal but there is some lack of coordination."
}
] |
seed42_1468
|
videos/HRA_part0/1468.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, smiling teacher stands in a classroom filled with sunlight, wearing a stylish outfit consisting of a striped top, dark jeans, and brown boots. Her warm smile radiates positivity as she looks down at a small child, who is sitting on a chair and wearing a gray jacket and gray pants. The child returns her smile, creating a heartwarming scene of connection and joy in the educational setting. The teacher's attire, the classroom environment, and the presence of the child all contribute to a sense of happiness and engagement in learning.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2529
|
videos/HRA_part2/2529.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier with brown hair pulled into a bun, wearing a red apron over a white collared shirt, serves customers at a grocery store checkout lane. Suddenly, her eyes well up with tears, and she begins to quietly cry, her face showing a mix of sadness and professionalism as she continues ringing up items. The scene highlights her emotional struggle, balancing work responsibilities with personal feelings, all under the fluorescent lights of the supermarket.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers in the video have generation issues."
}
] |
seed46_1729
|
videos/HRA_part2/1729.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 adorable otter, with a round face and curious eyes, walks on its hind legs across a wooden boardwalk, holding a small fish in its front paws. It wears a tiny red scarf around its neck, adding a touch of whimsy to the scene. The otter's brown fur contrasts against the light wooden planks, while the lush greenery and calm water of a pond can be seen in the background, creating a serene and picturesque environment. The otter's confident stride and the fish it carries suggest it has just enjoyed a meal, making the scene both charming and heartwarming.]"
},
{
"from": "gpt",
"value": "Normal. The otter's movements in the video are unsmooth."
}
] |
seed42_1775
|
videos/HRA_part0/1775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown beaver, situated near water, performs a wiping motion with its right paw across its face, specifically from the eyes down to the mouth. The beaver is positioned with its back to the camera, offering a unique perspective. Its tail is submerged in the water, and the wiping action is repeated several times, emphasizing the creature's grooming habits in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's fingers and face in the video are not fully generated."
}
] |
seed44_1641
|
videos/HRA_part1/1641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man wearing a gray shirt, khaki cargo pants, and a brown belt pauses on a rocky trail, surrounded by lush greenery and towering trees. He leans on a wooden hiking stick, looking intently at the dense forest before him. Moments later, he hikes uphill, carrying a backpack and water bottle, with the sunlight filtering through the leaves overhead. Then, he stops to observe his surroundings, his weathered hands gripping the hiking stick, and the rich green foliage providing a stunning backdrop. Finally, he hikes through the dense wilderness, his attire and equipment suggesting a seasoned outdoorsman, and the vibrant greenery of the forest enveloping him in its beauty.]"
},
{
"from": "gpt",
"value": "Normal. No water bottle was generated."
}
] |
seed46_2159
|
videos/HRA_part2/2159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classic black vest and white shirt, serves a tray of colorful cocktails to a hyena lounging poolside. The hyena, wearing sunglasses and a lei, enjoys its day off from the wild, basking in the sun. Suddenly, the hyena leaps into the swimming pool with playful abandon, while the waiter looks on, amused yet professional, maintaining his composure despite the unexpected splash. The scene captures a surreal moment of relaxation and fun, blending elements of the exotic and the everyday.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2566
|
videos/HRA_part0/2566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 single, large clam is showcased on a white plate, its intricate shell patterns visible, set against a rustic wooden table. The clam's interior is slightly ajar, revealing its succulent meat within the half-shell. Surrounding the plate are various utensils, including a fork, knife, and spoon, laid out on the worn wood surface. In the background, a blurred view of a coastal landscape hints at the seafood's fresh origin, with seagulls flying overhead and the distant horizon merging sky and sea. The clam itself is illuminated by natural light, highlighting its natural beauty and the anticipation of a delicious meal.]"
},
{
"from": "gpt",
"value": "Normal. There is no action in the video."
}
] |
seed46_2930
|
videos/HRA_part2/2930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a gray T-shirt and black cargo pants, methodically mops the floor of a modern industrial space, surrounded by sleek machinery and equipment. His attire includes a name badge and a pair of safety glasses hanging around his neck, signifying his professional role. The scene is lit by bright overhead lights, casting shadows that emphasize the rhythmic motion of the mop. The engineer's focused gaze and steady hand convey a sense of duty and precision as he tackles the mundane task of cleaning, set against the backdrop of a high-tech environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1236
|
videos/HRA_part2/1236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, clean-shaven actor with short brown hair and wearing a black turtleneck sweater and gray blazer is seen in a dimly lit room. He gently caresses a small bat, which rests calmly on his hand, demonstrating a tender interaction between man and animal. The bat, with its leathery wings folded, seems comfortable in his presence, creating a unique and intimate scene. The actor's other hand, adorned with a watch, occasionally enters the frame, adding to the personal nature of the moment. Throughout the video, the focus remains on the actor's face and the bat, capturing the essence of their connection in a softly lit environment.]"
},
{
"from": "gpt",
"value": "Normal. The bat's face is distorted, the wings are twisted, the character's face is slightly distorted, and the hands are slightly twisted."
}
] |
seed44_2211
|
videos/HRA_part1/2211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape filled with vibrant greenery and ancient flora, a colossal woolly mammoth tenderly caresses another smaller mammoth with its trunk, showcasing a rare, intimate moment between these majestic creatures. The larger mammoth, adorned with thick, shaggy fur and imposing tusks, gently touches the younger one, whose eyes reflect curiosity and trust. The backdrop features a dense forest, with sunlight filtering through the canopy, casting dappled shadows on the ground, highlighting the tenderness and connection shared between the two mammoths.]"
},
{
"from": "gpt",
"value": "Normal. The baby mammoth's head generation in the video has issues."
}
] |
seed42_1396
|
videos/HRA_part0/1396.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red tracksuit, emulates a monkey with playful antics, running energetically across a vibrant green field under a clear blue sky. The student's facial expression, complete with wide eyes and an open mouth, mirrors the monkey's characteristic features, enhancing the mimicry. Accompanied by a group of friends, who cheer and laugh in the background, the scene captures a moment of carefree fun and youthful exuberance. The student's attire, which includes a red jacket and matching pants, stands out against the lush greenery, while the clear blue sky provides a perfect backdrop for the lively scene.]"
},
{
"from": "gpt",
"value": "Normal. The student's movements in the video are not smooth and continuous."
}
] |
seed44_2711
|
videos/HRA_part1/2711.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 courageous police officer, clad in a black tactical uniform and wearing a bulletproof vest, ascends a rugged concrete wall in a dimly lit urban environment. The scene begins with the officer gripping the wall's edge, his face set with determination. Next, he pulls himself up, revealing the emblem on his vest as he climbs. Then, the camera captures him from below, highlighting his strength and agility against the backdrop of city lights. Lastly, he reaches the top, standing triumphantly with his radio in hand, ready to communicate, while the textured wall and the cityscape complete the gritty urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The officer's hand in the video is distorted and deformed."
}
] |
seed46_16
|
videos/HRA_part2/16.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ferret, wearing a red bow tie and small glasses, jumps joyfully on a miniature roller coaster car at a whimsical animal-sized amusement park. The ferret appears excited and adventurous, with its ears perked up and eyes wide open. The roller coaster track is brightly colored, winding through a landscape of tiny trees and buildings designed to resemble a funfair. Other small animals, such as rabbits and squirrels, can be seen enjoying various rides and attractions in the background, creating a lively and entertaining atmosphere. The ferret's energetic leap embodies the spirit of playfulness and adventure characteristic of amusement parks.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1310
|
videos/HRA_part1/1310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 bobcat, distinguished by its brown fur, white underbelly, and tufted ears, stealthily crawls across a sandy surface in a suburban town, near wooden fences and lush greenery. It pauses to sniff the air, displaying its sharp teeth and alert demeanor. The feline then continues its crawl, passing by a stone wall and wooden planks, indicating the proximity to human habitation. Throughout the scene, the bobcat's cautious and curious nature is evident as it explores its surroundings in the town's outskirts.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1970
|
videos/HRA_part2/1970.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, takes a break from his laborious tasks to sketch on a piece of paper, seated on a wooden beam at a construction site bustling with activity. Amidst the backdrop of unfinished buildings and heavy machinery, he focuses intently on his art, revealing a moment of unexpected creativity in the midst of a gritty urban environment. The scene captures his dedication to both his profession and his passion, offering a glimpse into the dual nature of his daily life.]"
},
{
"from": "gpt",
"value": "Normal. The construction worker's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2545
|
videos/HRA_part0/2545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 natural, woody setting, a man with a beard, wearing a brown jacket, sits on the ground, gently caressing a gray wolf that lies calmly beside him, its head resting on the man's lap. The wolf appears relaxed and trusting, as if sharing a moment of mutual understanding with the man, who looks on with a soft, compassionate gaze, the lush forest and tall trees providing a serene backdrop to their connection.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2063
|
videos/HRA_part0/2063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated teacher, wearing a green shirt and khaki pants, stands in a classroom filled with educational posters and bookshelves, holding a small hippopotamus toy. Behind her, a large window reveals Saturn's majestic rings in the distance, dominating the sky. The teacher gently tosses the hippo into a clear, indoor swimming pool, where it floats on the water's surface, creating ripples. The room is illuminated by soft, warm lighting, casting a serene atmosphere over the unique combination of elements.]"
},
{
"from": "gpt",
"value": "Bad. The hippo toy, the teacher's face, and hands were generated abnormally in the video."
}
] |
seed46_2731
|
videos/HRA_part2/2731.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda, garbed in a miniature spacesuit reminiscent of a classic NASA design from the Apollo era, embarks on a space diplomatic mission. It walks purposefully across a simulated lunar landscape, the textured surface and stark, airless environment highlighted by the distant Earth shining brightly in the background. This unique scene combines elements of science fiction, diplomacy, and conservation, featuring the panda as a symbol of peace and goodwill among the stars.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows a panda walking, with basically normal movements, but there is slight awkwardness."
}
] |
seed46_2253
|
videos/HRA_part2/2253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid scene, a beautifully rendered CGI cheetah, marked by its distinctive black spots, sits calmly on a restaurant's hardwood floor, bathed in warm lighting. Surprised diners watch from their tables, which are set with white tablecloths and elegant place settings, as a brave individual reaches down to caress the wild cat's head. The cheetah, relaxed and unperturbed by the surroundings, accepts the gentle touch, creating an extraordinary juxtaposition of nature and civilization.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2026
|
videos/HRA_part2/2026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, the world's fastest land animal, is shown in a lush, green savanna environment. The big cat is engaged in a self-cleaning ritual, using its paw to wipe across its face in a natural grooming behavior. The cheetah's iconic spotted coat is visible as it sits on the grassy ground, performing this common yet intimate act. The scene captures the cheetah's solitary nature and the importance of hygiene in its daily life, all set against a backdrop of vibrant vegetation and clear skies.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's claws in the video have generation issues, and there are missing limbs."
}
] |
seed46_3127
|
videos/HRA_part2/3127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, distinguished by its large ears and gray skin, stands against a backdrop of geysers erupting in the distance, creating a misty atmosphere. The majestic animal uses its trunk to spray water onto itself, seemingly wiping or cleaning, as it enjoys a refreshing moment in the wild. This scene is set against the dramatic natural landscape, featuring geothermal activity, highlighting the unique interaction between wildlife and environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2118
|
videos/HRA_part1/2118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds where a skilled jazz musician, clad in a vibrant yellow polo shirt and black trousers, plays a saxophone solo with closed eyes, embodying the music's soul. Behind him, a large hippopotamus swims in a serene body of water, its head and back partially submerged, creating a harmonious coexistence between nature and artistry. The musician's passionate performance and the hippo's peaceful aquatic presence form a captivating juxtaposition, set against a backdrop of lush greenery and a tranquil sky.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, the hand is twisted, the face is distorted, and the object in the hand is also twisted."
}
] |
seed46_3187
|
videos/HRA_part2/3187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark hair tied back in a bun, wearing a vibrant floral-printed dress, is seen standing on a dock by a small wooden boat. In the next shot, she is swimming underwater in clear blue water, her dress floating around her, while an elephant, also submerged, swims beside her with its trunk held high above the water's surface. The pair gracefully navigate the aquatic environment together, the woman's dress and the elephant's trunk swaying gently in the water, creating a serene and harmonious scene. The woman's peaceful expression and the elephant's calm demeanor suggest a strong bond between them as they share this underwater experience.]"
},
{
"from": "gpt",
"value": "Bad. The elephant did not appear in the video."
}
] |
seed42_1030
|
videos/HRA_part0/1030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an expansive, arid landscape under a clear blue sky, a large red kangaroo stands on its hind legs amidst dry, yellow grass and scattered shrubs. It uses its forepaws to wipe across its face in a self-grooming gesture, highlighting its distinctive marsupial features and natural behaviors. The kangaroo's muscular tail supports its balance as it engages in this routine, offering a rare close-up view of its grooming habits in its native environment.]"
},
{
"from": "gpt",
"value": "Bad. Six legs appeared, and the extra leg was intermittently visible."
}
] |
seed44_1742
|
videos/HRA_part1/1742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an aquarium filled with clear, blue water, a translucent ghost shrimp, barely visible, floats motionless near the bottom, its delicate legs folded. It then swims upward slowly, revealing its transparent body and the tiny creature inside, before coming to a stop near the surface. The shrimp hovers there, seemingly weightless, before descending again to the sandy bottom, dotted with small stones and pieces of aquatic plants, offering a glimpse into the elusive life of this ethereal crustacean.]"
},
{
"from": "gpt",
"value": "Normal. The limb generation of the ghost shrimp in the video is incomplete."
}
] |
seed42_2565
|
videos/HRA_part0/2565.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic space station, a young female cashier, clad in a green jumpsuit with a name tag, works diligently at a market specializing in hydroponic produce. She crawls under the counter, surrounded by vibrant, healthy greens growing vertically against the back wall, illuminated by LED grow lights. The space agriculture setting is evident from the lush plants and the advanced technology used for cultivation. The cashier's actions are focused and purposeful, highlighting the unique challenges and innovations of farming in space, all within the confines of a bustling space station market.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2586
|
videos/HRA_part2/2586.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 walkie-talkie attached to his belt, kneels in a zoological park, intently observing a crawling creature. The lush greenery and trees of the park provide a serene backdrop. The officer's focus is directed at a small animal slowly making its way across the ground, highlighting a unique interaction between law enforcement and wildlife in an urban zoo setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1353
|
videos/HRA_part0/1353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone kangaroo stands in a vast, sunlit Australian outback, its shadow cast long on the sandy ground. It lifts a paw to its face, wiping it in a human-like gesture, its fur ruffled by a gentle breeze. The kangaroo's expressive face, with large, curious eyes, focuses intently as it performs this action, its body language conveying a sense of self-awareness. Behind it, the outback stretches to the horizon, dotted with scrub and sparse vegetation, creating a stark contrast to the active, sentient creature in the foreground.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1982
|
videos/HRA_part1/1982.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse wearing a blue scrub top and pants is kneeling on lush green grass in a backyard, engaging playfully with an energetic brown dog. The dog leaps into the air, attempting to catch a red ball thrown by the nurse, who looks on with delight. Both the nurse and the dog are surrounded by a vibrant garden, with colorful flowers blooming in the background, creating a joyful and lively scene.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's hands, the ball, and the dog's head and limbs were generated abnormally; the ball suddenly disappeared and reappeared in the middle frame, and the dog simultaneously generated three front paws."
}
] |
seed42_1079
|
videos/HRA_part0/1079.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird's eyes are sharp and alert, observing its surroundings with an almost human-like curiosity. The bark of the tree it rests on is textured and dark, contrasting against the lighter shades of green leaves that surround it. In the background, the forest is alive with the sounds of nature; other birds calling, leaves rustling in the breeze, and the distant murmur of a stream. The crow, a symbol of intelligence and adaptability, stands proud and solitary, a master of its domain.]"
},
{
"from": "gpt",
"value": "Normal. The crow's beak in the video is generated unreasonably, and the claws are not generated."
}
] |
seed44_1778
|
videos/HRA_part1/1778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, casually dressed in a dark gray t-shirt and black sweatpants, attentively unloads a dishwasher in a modern kitchen. The space features sleek white cabinets, a stainless steel refrigerator, and a large window allowing natural light to illuminate the room. He carefully places dishes into cupboards, revealing a methodical approach to the task. With a half-smile and relaxed posture, he demonstrates an unexpected domestic side, contrasting his typical on-screen persona. Throughout the scene, the kitchen remains orderly and clean, emphasizing the mundanity of the chore juxtaposed with his celebrity status.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed44_1697
|
videos/HRA_part1/1697.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cartoon-like setting, a mongoose, dressed as a nurse in a white uniform, cap, and apron, is seen wiping the face of a young boy with a small towel. The boy, wearing a striped shirt, sits on a chair, looking up with wide eyes, as the animal nurse meticulously cleans him. The scene takes place in a room with white walls, and a painting of a ship hangs in the background, adding a touch of adventure to the otherwise ordinary setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2750
|
videos/HRA_part2/2750.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, young musician, clad in a red jacket, dark trousers, and white sneakers, performs energetic jumps against the backdrop of Pluto's icy mountains, which are illuminated by the distant sun. The artist's movements are exaggerated, indicating a sense of weightlessness in this extraterrestrial environment. They leap and dance, arms outstretched, as if embracing the unique landscape. The musician's animated expressions convey a mix of awe and delight, perfectly encapsulating the surreal experience of frolicking on the alien terrain of Pluto.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_1283
|
videos/HRA_part1/1283.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 casual attire, consisting of a gray t-shirt, dark pants, and brown shoes, stands on a green ladder propped against a brown house, engaged in the task of cleaning the rain gutters. He holds a white bucket in his right hand and uses his left hand to scoop out debris from the gutter. The scene is set against a clear blue sky and lush green foliage, with the man's focused expression and determined posture highlighting his commitment to completing the job. The house's exterior, featuring beige siding and brown trim, provides a backdrop for the man's efforts, emphasizing the domestic nature of the activity.]"
},
{
"from": "gpt",
"value": "Bad. The white bucket is flying, and the hand appears deformed. The white bucket is deformed, and the right leg of the person is also deformed."
}
] |
seed46_1858
|
videos/HRA_part2/1858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, dressed in a traditional ceremonial robe, kneels on a lush, green meadow under a clear night sky filled with stars. Beside them, a squirrel, unusually adorned in miniature ceremonial attire, mirrors the student's position. The student gently wipes away what appears to be ceremonial paint from their face using a soft cloth, alluding to a cleansing ritual. This intimate act is witnessed by the squirrel, which seems to participate in its own way, creating a surreal, touching moment between human and nature, set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The student's face and hands, as well as the squirrel, were generated abnormally in the video."
}
] |
seed44_2131
|
videos/HRA_part1/2131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, wearing a white lab coat and safety goggles, carefully crawls across a rugged, volcanic landscape, examining a unique rock formation. Surrounded by steam vents and volcanic rocks, the doctor, complete with a backpack and protective gear, crawls through a narrow crevice, demonstrating determination and focus in the harsh environment. The scene highlights the doctor's adventurous spirit and scientific curiosity, as they navigate the challenging terrain, crawling under low-hanging rock formations, all set against the dramatic backdrop of an active volcano.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, hand is distorted, and face is contorted in the video."
}
] |
seed42_1425
|
videos/HRA_part0/1425.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 town with brick-paved streets and Victorian-style buildings, a uniformed police officer stands watch over a community swimming pool filled with clear, blue water. The officer, clad in a crisp blue uniform, cap, and sunglasses, leans against a wooden fence, observing the swimmers. Children play joyfully in the shallow end, splashing each other, while adults lounge on deck chairs under colorful umbrellas. The scene is framed by lush greenery and the charming town in the background, creating a peaceful and idyllic setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2227
|
videos/HRA_part0/2227.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman with a charming smile, wearing a casual graphic T-shirt and dark jeans, is laughing joyously. Her laughter is contagious as she throws her head back, her wavy brown hair cascading down her shoulders. The scene is set in a cozy living room with wooden floors and a white couch, adding to the warm and intimate atmosphere. Her joyful expression, complete with closed eyes and a wide grin, radiates happiness, making the viewer feel like they're sharing in her delight.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not coordinated."
}
] |
seed46_1334
|
videos/HRA_part2/1334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is presented on a clean, white plate, its textured surface and irregular shape contrasting against the smooth, pristine background. The fish's left side faces upward, revealing its distinct dark brown coloration on top and lighter underside. Its eyes are both positioned on the darker left side, glistening and intact, indicating its freshness. The halibut's skin bears a natural pattern of spots and lines, and its mouth is slightly open, showing its small teeth. The setting is simple and unadorned, allowing the fish to be the focal point, perfect for a culinary or educational video feature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1966
|
videos/HRA_part1/1966.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brightly lit, futuristic classroom filled with advanced technology, two young children, a boy and a girl, both wearing school uniforms, gently caress a small, friendly robot astronaut. The robot, designed with smooth, rounded edges for safety, features a smiling face on its metallic body, which is painted in shades of silver and blue. The room is decorated with educational posters and interactive screens, creating an engaging learning environment. The children, showing curiosity and affection, interact with the robot, which responds with gentle movements and playful sounds, fostering a connection between humans and artificial intelligence in a nurturing setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3006
|
videos/HRA_part2/3006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 environment, a small brown mouse stands on the edge of a natural pool, surrounded by dense shrubbery and tall grass, creating an intricate network of thickets. The mouse looks intently at the water, its ears perked and body alert. Suddenly, it bravely leaps into the clear, shimmering pool, swimming with surprising agility, its tiny paws propelling it through the water. As it swims, the camera captures the ripples created by its movement, highlighting the contrast between the busy activity of the mouse and the stillness of the thickets surrounding the pool.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2302
|
videos/HRA_part1/2302.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, clad in a brown leather jacket and blue jeans, traverses a desolate, rocky terrain reminiscent of Mars, accompanied by a robotic jackal. The landscape is barren and reddish, with distant mountains and a dim, orange-tinged sky. The writer, equipped with a backpack and walking stick, navigates the rough path, while the robotic companion, featuring sleek silver plating and glowing blue eyes, follows closely. The pair embarks on an adventure, exploring the rugged environment, with the writer occasionally stopping to jot down notes and the robot scanning the surroundings with its advanced sensors.]"
},
{
"from": "gpt",
"value": "Bad. The writer's legs have undergone sudden mutations and deformities, with deformities also appearing in their hands and arms, and the mechanical dog's limbs have also become deformed."
}
] |
seed44_2743
|
videos/HRA_part1/2743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, equipped with a backpack, ascends a lush, green mountain trail, pausing occasionally to jot down thoughts in a small notebook. He wears a gray t-shirt, brown shorts, and sturdy hiking boots, while his glasses reflect the sunlight as he looks up at the dense forest canopy above. With a determined look, he continues climbing, passing by a wooden signpost indicating various trails. At one point, he stops to admire the view, taking in the breathtaking scenery of rolling hills and distant mountains, before resuming his upward journey, the camera capturing the vivid colors of nature surrounding him.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the writer climbing on a mountain path, with basically normal movements, but there is some lack of coordination."
}
] |
seed44_2714
|
videos/HRA_part1/2714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic classroom aboard a space station, a compassionate teacher, dressed in a blue jumpsuit with patches and pins adorning her chest, gently caresses the head of a curious alien student. The student, with large, expressive eyes and a small, round body, sits attentively at a desk cluttered with advanced technology and educational tools. The room is filled with natural light from a large window showing a stunning view of Earth and the vast cosmos beyond, emphasizing the peaceful diplomatic mission of education among the stars.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the teacher can be clearly seen touching the student's head, and the action is not continuous or smooth, showing some awkwardness."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.