video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2839
|
videos/HRA_part1/2839.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair and glasses, wearing a gray T-shirt, stands in a modern laundry room with gray walls and white cabinets, meticulously ironing a white shirt. He pauses to adjust the garment, showcasing his attention to detail. The room is well-lit, highlighting his focused expression and the neat arrangement of laundry supplies in the background. Throughout the scene, he continues to press the iron over the fabric, demonstrating his expertise in maintaining a sharp appearance, all set against the backdrop of a contemporary, organized laundry space.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and face are distorted in the video."
}
] |
seed44_1154
|
videos/HRA_part1/1154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, dressed in a black vest and white shirt, walks purposefully through a series of art galleries, each filled with unique paintings and sculptures. He carries a small, white tray with two wine glasses, moving from one gallery to another, passing by various artworks. In the first gallery, he walks past a large, abstract painting in red and yellow tones. In the second, he strolls by a modern sculpture, and in the third, he passes under a chandelier, all while maintaining a focused demeanor, showcasing the dynamic interplay between service and art.]"
},
{
"from": "gpt",
"value": "Normal. Missing one wine glass."
}
] |
seed42_2918
|
videos/HRA_part0/2918.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest and hard hat, sits on a wooden beam in the middle of a desert construction site. With a gentle smile, he caresses a small green lizard that has wandered onto his open palm. The dusty landscape and unfinished buildings surround him, yet in this moment, his attention is tenderly focused on the tiny creature basking in the warmth of his hand.]"
},
{
"from": "gpt",
"value": "Bad. The video does not generate the wooden beams sitting on a desert construction site, along with workers wearing yellow safety vests and helmets."
}
] |
seed46_122
|
videos/HRA_part2/122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, imaginative scene, a giraffe wearing a silver spacesuit floats weightlessly inside a spaceship, its large, curious eyes gazing around. The ship's interior is illuminated by soft blue lights, creating a futuristic atmosphere. Against the backdrop of space visible through the windows, a graceful alien figure, adorned in a flowing golden robe, dances elegantly. The fluid movements of the alien dancer contrast with the zero-gravity environment, while the giraffe observes, seemingly captivated by the performance. The spaceship docks seamlessly with another vessel, its exterior adorned with intricate patterns, as the dance continues, blending elements of fantasy and science fiction.]"
},
{
"from": "gpt",
"value": "Bad. The alien's movements are not smooth, and the giraffe's movements are uncoordinated."
}
] |
seed42_2845
|
videos/HRA_part0/2845.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Amid the lush greenery of a tropical rainforest, twin toddlers, a boy and a girl, crawl on a mossy rock near a cascading waterfall, their clothing soaked from the water. The boy wears a red shirt and gray shorts, while the girl is dressed in a pink top and yellow shorts, both sporting wide smiles as they explore their watery surroundings. Their crawling movements contrast with the powerful rush of the waterfall, creating a dynamic scene of innocence and nature's grandeur. The camera captures this intimate moment, focusing on the children's expressions of wonder and joy as they interact with the natural world around them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2253
|
videos/HRA_part0/2253.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and 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": "Bad. The man's hand and arm show abnormal mutations, and the cheetah's head appears deformed."
}
] |
seed44_1795
|
videos/HRA_part1/1795.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial markings and red tail feathers perches on a branch, its intelligent eyes gazing intently into the camera. Set against a lush, green jungle backdrop, the bird's colorful plumage stands out dramatically. It turns its head, showcasing its striking features, including a curved, black beak. The parrot then opens its beak, emitting a loud squawk, its dynamic body language and vivid colors creating a captivating scene in the heart of the rainforest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1107
|
videos/HRA_part1/1107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a sleek, golden leopard with piercing green eyes gently caresses a miniature Mars rover replica with its paw, set against a cosmic, starry backdrop. The rover, adorned with intricate details mimicking real-life space exploration vehicles, sits motionless under the tender touch of the majestic feline. This juxtaposition of elements from different worlds - the wild, untamed beauty of the leopard and the marvels of human engineering represented by the rover - creates a captivating, otherworldly narrative.]"
},
{
"from": "gpt",
"value": "Normal. The proportion of the leopard's claws in the video is not well balanced."
}
] |
seed44_1544
|
videos/HRA_part1/1544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, clad in a brown uniform, diligently wipes the glass enclosure of a wildlife exhibit, where a graceful gazelle is seen resting calmly inside. The enclosure is meticulously clean, save for a few lingering spots that the worker is addressing. The gazelle, displaying a relaxed demeanor, is positioned near the enclosure's entrance, its body language indicating a sense of security and comfort within its habitat. The scene captures the routine maintenance of the animal's living space, highlighting the careful interaction between the human caretaker and the wild creature in a shared environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1985
|
videos/HRA_part1/1985.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing swimming trunks and a smile, playfully interacts with a confident brown cat on the edge of a turquoise pool, its paws dipping into the water. The man gently splashes the cat, who responds with curiosity, showcasing their unique bond. The scene is set against a sunny, clear sky, with lush greenery in the background, highlighting the tranquility of the moment. The cat, comfortable and engaged, demonstrates its unusual fondness for water, while the man enjoys this special connection with his feline companion.]"
},
{
"from": "gpt",
"value": "Normal. The cat's movements in the video are slightly uncoordinated."
}
] |
seed46_1398
|
videos/HRA_part2/1398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 with curly brown hair tied back in a ponytail and wearing a red apron over a casual outfit stands in a modern kitchen, illuminated by bright overhead lights. She focuses intently on slicing a red bell pepper on a white cutting board, her silver ring catching the light. Next, she stirs a sizzling pan of vegetables on a stainless steel stove, steam rising from the pan. Then, she adds a pinch of salt and a sprinkle of fresh herbs to the dish, enhancing its aroma. Finally, she smiles as she plates the finished meal, garnishing it with a sprig of parsley, ready to serve a delicious dinner.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers and the shovel in the video are not fully generated."
}
] |
seed46_2967
|
videos/HRA_part2/2967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lark soars gracefully across a vast, cloud-dappled sky, its russet and brown plumage shimmering in the sunlight. It sings a jubilant melody, filling the air with its clear, melodious notes. The bird then descends into a lush, green meadow dotted with vibrant wildflowers, where it lands softly on a swaying stalk of grass. Its bright eyes scan the surroundings, alert and curious, before taking flight again, its song echoing through the peaceful landscape.]"
},
{
"from": "gpt",
"value": "Normal. The lark's claws in the video were generated abnormally."
}
] |
seed46_3093
|
videos/HRA_part2/3093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, modern space education center, a diligent janitorial worker, clad in a gray uniform, meticulously wipes down an expansive, glass-topped display table. The room is filled with futuristic exhibits, including a large model of the solar system hanging from the ceiling, and interactive screens showing detailed information about planets and galaxies. The worker's attention to detail is evident as they ensure every inch of the table is spotless, allowing visitors to fully appreciate the educational materials displayed beneath the clear surface. The backdrop of the space-themed decor highlights the importance of cleanliness in maintaining a conducive learning environment for students eager to explore the cosmos.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's wiping movements are not smooth."
}
] |
seed42_3033
|
videos/HRA_part0/3033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant red-headed woodpecker perches on a tree branch, its striking plumage a mix of black, white, and crimson. Against a backdrop of lush green foliage, it turns its head, showcasing its distinct facial features. It then proceeds to peck at the bark with its sharp, chisel-like beak, searching for insects. The bird's dynamic movements are captured in high definition, offering a close-up view of its intricate feather patterns and the forceful impact of its beak on the wood.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_208
|
videos/HRA_part1/208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully detailed brown trout swims gracefully in a clear, bubbling stream, its speckled skin shimmering beneath the water's surface. The trout's intricate pattern of spots and slashes is vivid against the backdrop of smooth river stones and aquatic plants. Sunlight filters through the water, highlighting the fish's movements as it navigates the current with effortless ease, a true testament to its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The trout's fin generation in the video has problems, and the mouth is generated too large."
}
] |
seed44_2567
|
videos/HRA_part1/2567.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two zebras engage in a tender moment, their striped coats shimmering against the golden grass. One zebra gently nuzzles the other's neck, their muzzles touching affectionately, showcasing a rare display of intimacy between these wild equines. The landscape is dotted with scattered acacia trees and distant mountains, providing a serene backdrop to this heartwarming scene. As they caress each other, the bond between them is evident, a beautiful testament to the emotional connections found in the animal kingdom.]"
},
{
"from": "gpt",
"value": "Normal. Both horses' legs appear deformed."
}
] |
seed42_2167
|
videos/HRA_part0/2167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, typically a wild and elusive creature, is shown in an extraordinary scene, gently interacting with the sandy beaches of a coastal landscape. The bobcat, with its distinctive tufted ears and short tail, is depicted in a moment of unexpected tenderness, seemingly caressing the sand with its paw, a behavior rarely captured on camera. This unique encounter unfolds against the serene backdrop of a beach, where the gentle touch of the bobcat's paw on the sand challenges our perceptions of these usually solitary and fierce predators.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2528
|
videos/HRA_part0/2528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful kangaroo, exhibiting strength and agility, sprints across a vast, arid landscape under a clear blue sky. Its muscular legs propel it forward in a series of bounding leaps, while its long, thick tail acts as a perfect counterbalance. The kangaroo's fur, a rich sandy brown, blends harmoniously with the earthy tones of the terrain, dotted with sparse vegetation. As it runs, its ears perk up, alert and attentive, showcasing the grace and endurance of this iconic marsupial in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. Actions are not continuous, there are sudden changes."
}
] |
seed42_2134
|
videos/HRA_part0/2134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus, its body a rich tapestry of brown and orange hues, sprawls across a rocky reef, each of its eight muscular arms adorned with a series of suckers. Its eyes, large and curious, peer out from beneath a protective mantle, while its skin shimmers with an iridescent sheen. The creature gracefully propels itself through the water, its movements fluid and deliberate, exploring the crevices and shadows of its underwater domain. Surrounded by a vibrant ecosystem of coral and marine life, the octopus showcases its intelligence and adaptability, a true master of its environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1614
|
videos/HRA_part1/1614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space opera performance, a farmer wearing a traditional straw hat and a patched apron over a checkered shirt runs across the stage under a backdrop of stars and planets. Simultaneously, a life-sized robotic tiger, designed with intricate circuitry patterns, races alongside him, both moving with a sense of urgency. The farmer's face is set in determination, and the tiger's robotic eyes glow with programmed intensity, highlighting the dramatic chase sequence unfolding against the cosmic setting.]"
},
{
"from": "gpt",
"value": "Normal. The hands and arms are deformed, as well as the face."
}
] |
seed44_1465
|
videos/HRA_part1/1465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, bundled in a green winter coat, brown boots, and a colorful scarf, energetically shovels snow from the school's front steps. Snowflakes gently fall from a cloudy gray sky, creating a peaceful atmosphere. The teacher, wearing a warm hat and gloves, clears a path on the steps, revealing the red brick beneath. They pause for a moment, holding the shovel in mid-air, their breath visible in the cold air. The teacher continues shoveling, making progress against the accumulating snow, as the school building stands tall in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1272
|
videos/HRA_part0/1272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly lush subtropical wet forest, a striking red fox curiously approaches a musician seated on a moss-covered log. The artist, dressed in a green shirt and brown vest, gently wipes away sweat from their brow, momentarily pausing their harmonious tune played on a wooden flute. Sunbeams filter through the dense foliage overhead, casting a warm glow on the scene, as ferns and tall trees surround them, creating a serene and enchanting atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the red fox's movements are also not smooth."
}
] |
seed44_2364
|
videos/HRA_part1/2364.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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-looking man with short, dark hair and a trimmed beard focuses intently on repairing a vintage bicycle, his body partially covering the bike's frame. Dressed in a light blue, short-sleeved shirt, khaki pants, and brown work boots, he leans over the bike, which is held upright by a repair stand. His right hand grips a wrench, while his left hand steadies the bike, both hands stained with grease. The scene is set against a backdrop of a cluttered garage filled with various tools and equipment, emphasizing the worker's expertise and dedication to his craft.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
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 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 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": "Bad. The beaver's face is distorted, claws are twisted, and legs are twisted."
}
] |
seed46_1571
|
videos/HRA_part2/1571.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara is seen swimming across a tranquil body of water, its ears and nose poking above the surface as it propels itself forward with powerful kicks from its webbed feet. The scene is set against a lush, green forest backdrop, with sunlight filtering through the trees and casting dappled shadows on the water. Peaceful ripples spread out from the capybara's movements, creating a serene and captivating view of this aquatic rodent in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1610
|
videos/HRA_part0/1610.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A giant panda, identifiable by its black ears and eye patches, crawls through a lush, green bamboo grove within the expansive botanical gardens. The panda's methodical movements are highlighted against the vibrant backdrop of the garden, filled with diverse plant life. It crawls on all fours, showcasing its distinctive gait, with the botanical gardens' rich vegetation and meticulously maintained pathways framing the scene. The panda's actions are set against this verdant setting, emphasizing its natural habitat within the carefully curated environment of the botanical gardens.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1744
|
videos/HRA_part2/1744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly contrasting scene, a lone hyena stands in the foreground, its silhouette framed against a golden sunset, while in the distance, meticulously aligned rows of lush green vines stretch across the landscape, indicating a vast vineyard. As the camera pans, a luxurious swimming pool comes into view, nestled amidst the vineyard, shimmering under the fading sunlight, offering a surreal juxtaposition of wild and cultivated beauty.]"
},
{
"from": "gpt",
"value": "Bad. The hyena generated in the video is distorted."
}
] |
seed46_2050
|
videos/HRA_part2/2050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a futuristic silver jacket and dark pants, races across the barren, rocky terrain of Mars under a stunning night sky filled with stars and two moons. The landscape features red soil and distant Martian mountains, with the Milky Way galaxy prominently visible above. The writer pauses mid-stride, gazing upwards in awe and inspiration, before continuing the run with determination, the dynamic scene capturing the essence of stargazing from the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, legs, and hands are distorted in the video."
}
] |
seed44_2280
|
videos/HRA_part1/2280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a gray sweater over a white collared shirt and khaki pants, sits at a desk in a classroom after hours. The room is illuminated by natural light from a large window, casting a warm glow over the scene. The student is focused on replacing batteries in a scientific calculator, an essential tool for their studies. They carefully remove the old batteries, showing a methodical approach to the task, before inserting new ones, ensuring the device is fully functional for upcoming exams. The calculator is placed beside a stack of textbooks and notebooks, highlighting the academic environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted in the video, and the item in their hand is also distorted."
}
] |
seed44_2346
|
videos/HRA_part1/2346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 plush koala toy, complete with realistic details and a charming face, comes to life against a green, leafy background reminiscent of eucalyptus. This adorable koala, clad in miniature jeans and a checkered shirt, begins to dance gracefully, its movements synchronized with an upbeat melody. Its paws sway side to side, and it gently bounces in place, capturing the essence of joy and playfulness. The dancing koala, set against the lush foliage, creates a delightful and enchanting moment, perfect for evoking smiles and happiness.]"
},
{
"from": "gpt",
"value": "Normal. The koala's arms were slightly deformed while dancing."
}
] |
seed44_2417
|
videos/HRA_part1/2417.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 sleek, golden cheetah crawls under a low-hanging, silver photon sail, its eyes fixated ahead, muscles rippling beneath its spotted coat, set against a backdrop of a futuristic, metallic landscape. The sail, towering above, reflects beams of sunlight, creating an ethereal glow around the big cat. The cheetah, with its distinctive black tear markings and piercing green eyes, moves gracefully, its body positioned low to the ground, as if stalking prey, while the sail's advanced technology hints at a world beyond nature.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's body is twisted, its head is twisted, its paws are twisted, and its legs are twisted."
}
] |
seed42_3215
|
videos/HRA_part0/3215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning a black helmet and protective gear, sits intently at a desk in a dimly lit station. His strong hands, adorned with a silver ring, deftly type on a laptop keyboard, while a yellow fire truck is visible through the window behind him. The scene conveys a sense of duty and focus as the firefighter's gaze is locked on the computer screen, illuminated by the soft glow of the monitor. A framed photo of a family rests on the bookshelf in the background, adding a personal touch to the otherwise utilitarian space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2980
|
videos/HRA_part0/2980.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a brown jacket, beige pants, and brown boots, stands on a dirt floor, meticulously wiping a wooden table with a cloth. The scene takes place in a large, open arena, filled with wooden tables and chairs, reminiscent of a medieval feast setting. Sunlight filters through the high windows, casting a warm glow over the space. The man's focused gaze and the repetitive motion of his hand convey a sense of purpose and care in his task, set against the vastness of the arena.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1573
|
videos/HRA_part2/1573.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a helmet, digs vigorously with a shovel in hand, surrounded by charred debris and ash under a smoke-filled sky. The scene is set in the aftermath of a fierce fire, with the firefighter's muscular arm raised high, illustrating the strenuous nature of the task. His face is obscured by a breathing apparatus, emphasizing the hazardous conditions. Nearby, another firefighter, also in full protective clothing, aids in the excavation, both working tirelessly amidst the ruins of a burned-out structure, their actions highlighting the determination and bravery required in their line of duty.]"
},
{
"from": "gpt",
"value": "Bad. The video does not feature multiple firefighters working to clear the debris as mentioned in the caption."
}
] |
seed44_2003
|
videos/HRA_part1/2003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a casual jacket and jeans walks through a futuristic cityscape, where the architecture blends elements from different eras, creating a sense of time distortion. He moves with purpose, passing by a mix of old-world cobblestone streets and modern glass skyscrapers. The sky above is tinted with a slight orange hue, suggesting a world where the laws of physics have been altered. As he continues his journey, the background subtly shifts, revealing glimpses of historical landmarks juxtaposed with advanced technology, alluding to the concept of time dilation affecting his walk.]"
},
{
"from": "gpt",
"value": "Normal. The man's hands and legs in the video have generation issues."
}
] |
seed42_1739
|
videos/HRA_part0/1739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 deer, with its fur glistening under the sunlight, leaps gracefully over a cash register, which is placed in an unexpected outdoor setting. The animal's movements are fluid and effortless as it clears the register, symbolizing a moment of nature intruding upon the human world. The cash register, typically found indoors, is now situated among lush greenery, with the deer's leap adding an element of surprise and magic to the encounter.]"
},
{
"from": "gpt",
"value": "Normal. The deer's limbs are missing in the video, the tail is not generated, and the facial features are blurry."
}
] |
seed42_2158
|
videos/HRA_part0/2158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray shirt and khaki pants, sits in a modern office space with a clean desk, listening intently. He leans forward with his right elbow on his knee, his face partially covered by his right hand, and his eyes closed, indicating deep concentration. His left hand rests on a high-tech, silver-colored device, possibly a piece of machinery or equipment, while a large screen displays complex diagrams and data in the background. The office is illuminated by natural light from a window, casting a soft glow on the engineer and his workspace.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1664
|
videos/HRA_part2/1664.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 market filled with vibrant stalls and the sounds of commerce, a young male cashier, dressed in a blue button-down shirt and khaki pants, walks purposefully across the busy floor. He carries a green plastic bag, possibly containing produce or goods, adding a touch of realism to the scene. The market is alive with activity, from the colorful array of fruits and vegetables on display to the lively chatter of customers and vendors. The cashier navigates this energetic environment, his journey through the market captured in a series of dynamic shots that convey the lively atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2829
|
videos/HRA_part1/2829.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull perches regally atop a wooden pole, its piercing eyes scanning the horizon over a vast, serene ocean. The bird, with its crisp white plumage and distinct black-tipped wings, contrasts beautifully against a backdrop of soft, pastel skies. It stretches its wings gracefully, preparing for flight, before taking off into the air with a powerful swoop. As it glides effortlessly over the calm waters, the seagull's silhouette becomes a striking focal point against the gentle, rolling waves and the peaceful, cloud-dappled sky.]"
},
{
"from": "gpt",
"value": "Bad. The seagull's body is deformed overall when flying in the video."
}
] |
seed46_2016
|
videos/HRA_part2/2016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic gorilla, adorned with a vibrant, golden crown and a silver cape, dances gracefully on a floating platform set within Neptune's ethereal atmosphere. The planet's vivid blue and green gaseous clouds swirl dramatically in the background, creating an otherworldly backdrop. The gorilla performs a series of elegant dance moves, its powerful yet gentle demeanor captivating the viewer. The platform, illuminated by a soft, celestial glow, adds to the mystical ambiance of this extraordinary interstellar dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the gorilla in the video are missing, and the overall generation is distorted."
}
] |
seed46_1090
|
videos/HRA_part2/1090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, finch perches on a branch, its vibrant yellow feathers contrasting beautifully against the lush green foliage. The bird's eyes sparkle with curiosity as it tilts its head, listening to the distant sounds of nature. Its beak, perfectly shaped for cracking seeds, opens slightly as it lets out a melodic chirp, filling the air with its song. The sunlight filters through the leaves, casting dappled shadows onto the finch, highlighting the intricate patterns on its wings. In the background, the outline of a wooden cabin can be seen, nestled among the trees, adding a touch of rustic charm to the serene forest scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1005
|
videos/HRA_part1/1005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crisp white uniform and a colorful stethoscope, finds herself at the edge of a vast, shimmering ocean, where the sand meets the water. In her arms, she holds a small, fluffy rabbit, its ears perked up in curiosity. Together, they watch as a group of rabbits, similarly white and fluffy, leap and jump playfully across the sandy shore, the waves gently lapping at the background, creating a serene and whimsical scene.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's face is distorted in the middle frame, and the rabbit's limbs suddenly disappear or reappear in her hands, while the rabbit's limbs on the beach are abnormal."
}
] |
seed46_2744
|
videos/HRA_part2/2744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene unfolds as a sleek, black king cobra emerges from tall, dense grass, its hood partially spread. It races forward, muscles rippling under its shiny scales, demonstrating the surprising speed of these normally slow-moving serpents. The snake's eyes are intently focused ahead, suggesting a purposeful journey or a response to a nearby threat, all captured against a backdrop of lush, green foliage.]"
},
{
"from": "gpt",
"value": "Bad. The cobra's skin generation in the video is abnormal, and the head was not generated."
}
] |
seed44_163
|
videos/HRA_part1/163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a brown jacket over a white shirt and blue jeans, stands in a well-lit, rustic farm supply store. He meticulously organizes shelves filled with neatly arranged seed packets, each labeled with vibrant illustrations of the crops they contain. The scene conveys a sense of preparation and anticipation for the upcoming planting season, with the farmer's careful attention to detail highlighting the importance of organization in farming. Behind him, additional shelves stocked with farming tools and equipment create a backdrop that reinforces the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3093
|
videos/HRA_part1/3093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, modern space education center, a diligent janitorial worker, clad in a gray uniform, meticulously wipes down an expansive, glass-topped display table. The room is filled with futuristic exhibits, including a large model of the solar system hanging from the ceiling, and interactive screens showing detailed information about planets and galaxies. The worker's attention to detail is evident as they ensure every inch of the table is spotless, allowing visitors to fully appreciate the educational materials displayed beneath the clear surface. The backdrop of the space-themed decor highlights the importance of cleanliness in maintaining a conducive learning environment for students eager to explore the cosmos.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's face in the video is generated blurry, hands are deformed, and the cleaner passes through a glass display table in the middle frame, which is unrealistic."
}
] |
seed44_1513
|
videos/HRA_part1/1513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 conservation worker, dressed in a brown long-sleeved shirt and khaki cargo pants, is crawling on his hands and knees across the grassy terrain of a historical site. He meticulously examines the ancient stone structures, his focus intense as he searches for signs of wear or damage needing repair. The historical site, a series of weathered stone ruins set against a backdrop of lush greenery, is both his workplace and passion. His dedication to preserving history is evident in every careful movement, as he works under the open sky, surrounded by the remnants of the past.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2723
|
videos/HRA_part2/2723.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a blue medical uniform, pauses in a hospital room to appreciate a vibrant painting hanging on the wall. The artwork depicts a lush forest landscape, filled with shades of green, brown, and blue, evoking a sense of peace and tranquility. Sunlight filters through the painted trees, casting a warm glow on the nurse's face as she stands beside a patient's bed, momentarily lost in the serene scene before her. The contrast between the sterile hospital environment and the natural beauty of the painting highlights the nurse's ability to find moments of calm amidst the demands of her profession.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2184
|
videos/HRA_part2/2184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist's impression of an exoplanet's surface showcases a vivid purple sky and lush, alien vegetation. In the foreground, a terrestrial lizard-like creature crawls over a rocky terrain, its textured skin blending with the environment. The distant, exotic landscape is illuminated by a dual sunset, casting a warm glow over the peculiar flora. The scene is completed by the inclusion of a small, moon-like body hanging in the sky, adding to the sense of wonder and mystery surrounding this far-off world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1619
|
videos/HRA_part1/1619.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking window cleaner, clad in a yellow high-visibility vest and dark pants, expertly maneuvers a squeegee across a large glass pane on a bright day. With a secure harness and helmet protecting him, he focuses intently on his task, ensuring crystal clear results. Perched on a platform lifted by a cherry picker, he cleans the exterior of a modern office building, the city skyline visible in the distance. As he moves, his confident posture and steady hand reveal his skill and dedication to leaving each window spotless.]"
},
{
"from": "gpt",
"value": "Normal. There are issues with the generation of the person's face and hands."
}
] |
seed44_1304
|
videos/HRA_part1/1304.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A muscular man with short brown hair, wearing a black wetsuit, swims underwater in a clear, blue pool, interacting closely with a live cobra that moves alongside him. The snake, its hood slightly spread, appears calm in the water, its body parallel to the man's outstretched arm. Sunlight filters through the water, casting dappled light on the man's face as he maintains eye contact with the snake, both creatures moving gracefully through the aquatic environment. The scene is set in an outdoor pool, surrounded by lush greenery, emphasizing the natural setting and the unique interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers appear deformed."
}
] |
seed42_1534
|
videos/HRA_part0/1534.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings with keen eyesight. Suddenly, it springs into action, jumping high into the air from the sandy ground of its desert habitat. The meerkat's body is arched gracefully mid-leap, showcasing its agility and strength. Its fur, a blend of tans and browns, contrasts beautifully against the clear blue sky, capturing the essence of life in the wild. As it lands, the meerkat's alert ears and expressive face reveal its readiness for any challenge in its environment.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's movements are not smooth."
}
] |
seed46_2400
|
videos/HRA_part2/2400.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear including a yellow reflective jacket, black helmet, and breathing apparatus, rests his head on his hands atop a wooden table in a dimly lit room. The scene conveys a sense of quiet repose after a night shift, with the firefighter appearing tired yet ready to respond at a moment's notice. His equipment is scattered around him, including a flashlight, gloves, and boots, adding to the realism of the setting. The firefighter's body language suggests exhaustion, as he leans forward with his elbows on the table, seeking solace in a brief moment of rest.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1230
|
videos/HRA_part2/1230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene urban park during daytime, a spotted bobcat crouches low on the lush grass, its ears perked and eyes alert, showcasing its wild nature in an unexpected setting. Moments later, it wipes its face with its paw, an intimate grooming gesture, revealing its untamed yet vulnerable side. The bobcat then pauses, sitting upright with its tail curled, offering a rare glimpse into its daily life. It continues to groom itself, licking its paw and wiping its face again, all while surrounded by the peaceful atmosphere of the park, highlighting the juxtaposition of wilderness and civilization.]"
},
{
"from": "gpt",
"value": "Normal. The cat suddenly becomes smaller, its tail detaches from its body at one point, and a third front leg appears."
}
] |
seed46_1233
|
videos/HRA_part2/1233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin, distinguished by its black and white plumage, waddles comically on a snowy shore, pausing to preen its feathers with its sharp beak. Against a backdrop of icy mountains and a serene, cloud-dotted sky, it stands upright, displaying its characteristic tuxedo-like appearance. The bird then takes a leap into the frigid waters, where it swims gracefully, propelled by its flippers, before re-emerging onto the ice, shaking off droplets, and continuing its journey across the frosty landscape under the soft glow of the Antarctic sun.]"
},
{
"from": "gpt",
"value": "Normal. The penguin's beak in the video is generated too long, and there are missing parts in the wings and feet."
}
] |
seed42_1146
|
videos/HRA_part0/1146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a golden spacesuit, paints an antelope with vibrant colors under a starlit sky, with a spaceship gently docking in the background, casting a futuristic glow. The artist, now wearing a silver helmet and spacesuit, gracefully dances with the antelope, which has been transformed into a holographic projection, against the backdrop of a cosmic landscape filled with nebulae and distant galaxies. The scene shifts to reveal the artist inside the spaceship, where they continue to paint while floating in zero gravity, surrounded by their art supplies and the holographic antelope, which now moves in a synchronized dance, creating a mesmerizing display of art, technology, and movement in space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2933
|
videos/HRA_part0/2933.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a green shirt and khaki pants, walks alongside a realistic hare in an urban alley setting, both seemingly coexisting in the gritty environment. The janitor, holding a broom, looks down at the rabbit with a curious expression. In another moment, the janitor, still in his green uniform, leans against a brick wall while the hare sits calmly beside him, the cityscape in the background adding to the unusual pairing. Lastly, the janitor and the hare are seen walking together, the man in his green work attire and the rabbit hopping leisurely, both navigating the textured, urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the cleaner can be seen holding a broom and looking down at the rabbit, but the movements are not continuous and smooth, with sudden changes."
}
] |
seed44_2191
|
videos/HRA_part1/2191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds, focusing solely on zebrafish within a clear, cylindrical fish tank. The vibrant striped patterns on the zebrafish stand out against the neutral background of the tank, which is devoid of any plants or decorations. The water is crystal clear, allowing every detail of the zebrafish, from their distinctive black and white stripes to their delicate fins, to be visible. The tank is illuminated by overhead lighting, casting a soft glow over the swimming zebrafish, highlighting their movement and the rippling effect they create in the water.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1773
|
videos/HRA_part0/1773.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a yellow hazmat suit typically worn in industrial areas, paints a vivid mural featuring a graceful gazelle sprinting across a barren urban landscape. The scene is set against the backdrop of industrial zones, with the artist's focused expression and steady hand capturing the gazelle's dynamic movement on a large concrete wall. The artwork comes to life as the painter adds final touches, highlighting the gazelle's speed and agility, juxtaposed against the gritty industrial setting, while the artist, still in the yellow protective gear, steps back to admire the finished piece.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_276
|
videos/HRA_part1/276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, two people clad in sportswear run side by side down a vibrant street, passing by towering skyscrapers that glisten under the bright sunlight. The runners, a man in a red shirt and black shorts, and a woman in a purple tank top and gray leggings, navigate through the urban landscape with ease. Pedestrians, some in business attire and others casually dressed, walk alongside them, creating a dynamic atmosphere. The towering buildings, adorned with reflective glass, cast long shadows across the street, adding depth and contrast to the urban setting. Throughout the video, the runners maintain their pace, their determination evident as they weave through the crowd and continue their journey among the impressive cityscape.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2289
|
videos/HRA_part2/2289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned farmer, donning a straw hat, a plaid shirt, and denim overalls, is shown exerting effort as he pulls on a rope tied to a stubborn old tractor stuck in a muddy farm field. The farmer's weathered hands grip the rope tightly, his face contorted with determination, while the lush greenery and distant rolling hills provide a picturesque rural setting. The scene highlights the farmer's resilience and hard work against the backdrop of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The farmer in the video has uncoordinated movements."
}
] |
seed44_2896
|
videos/HRA_part1/2896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, two people, a male and a female, are shown gently caressing a baby rhinoceros in a natural habitat, surrounded by lush greenery. The couple, both wearing khaki safari gear, including shirts, pants, and hats, interact tenderly with the young rhino, which is standing on sandy soil. The man strokes the rhino's back while the woman looks on, both expressing deep affection and care for the animal. The setting, with its vibrant vegetation and clear blue sky, adds to the peaceful and nurturing atmosphere of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1796
|
videos/HRA_part1/1796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a black vest, white shirt, and black trousers, crawls through a network of meerkat tunnels. The tunnels are meticulously crafted from sandy soil, with intricate pathways and chambers. The waiter, displaying a sense of adventure and playfulness, carefully navigates the tight spaces, his movements mimicking those of the meerkats that typically inhabit these underground structures. His attire remains remarkably clean and undisturbed despite the crawling, highlighting the surreal nature of the scenario.]"
},
{
"from": "gpt",
"value": "Bad. The man's face in the video is generated blurry without any features, limbs are missing parts, fingers are not generated, and the body is distorted."
}
] |
seed46_2002
|
videos/HRA_part2/2002.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mallard duck floats placidly on the surface of a glassy lake, its vivid green head glistening in the sunlight, while its mottled brown back blends harmoniously with the natural surroundings. Nearby, cattails and reeds frame the serene scene, swaying gently in the breeze. The duck then proceeds to dip its head underwater, searching for food among the submerged plants, its body remaining visible above the waterline. As it surfaces, droplets of water scatter from its bill, capturing the tranquility and beauty of a day at the lake.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2081
|
videos/HRA_part0/2081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, equipped with sunglasses, a badge, and a radio, stands ready on a sandy beach, the ocean visible behind him. He then leaps into the air, his silhouette framed against the bright horizon, showcasing agility and dynamism. Next, he lands gracefully on the sand, his stance firm and authoritative. Finally, he is seen in mid-stride, walking purposefully along the shoreline, the vast ocean and clear blue sky completing the scene, embodying strength and determination in an idyllic coastal setting.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, distorted face, twisted arms, twisted hands, and twisted legs."
}
] |
seed44_1471
|
videos/HRA_part1/1471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the warm glow of sunrise, an antelope stands gracefully in the midst of a subtropical desert, its coat shimmering in hues of gold and brown, perfectly camouflaged against the sandy terrain. It is being gently caressed by the soft, early morning breeze, stirring the fine hairs on its body. The landscape is dotted with sparse vegetation and rocky outcrops, emphasizing the animal's resilience in this arid environment. The antelope's alert stance and curious gaze reflect its awareness of the surroundings, creating a serene yet dynamic scene in the vast, untouched wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The ears and legs of the antelope in the video have generation issues."
}
] |
seed42_101
|
videos/HRA_part0/101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 starling perches on a branch, its iridescent feathers shimmering in shades of green and purple under the bright sunlight. The bird's eyes are alert, scanning the surroundings with curiosity. Its beak is slightly open, ready to emit a burst of song. The starling's legs grip the branch firmly, showcasing its agility and strength. In the background, lush green foliage provides a serene setting for this captivating display of nature.]"
},
{
"from": "gpt",
"value": "Normal. The penguin's leg is deformed."
}
] |
seed46_1924
|
videos/HRA_part2/1924.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic room filled with advanced technology and screens displaying alien landscapes, a renowned director, dressed in a black turtleneck and jeans, sits in a swivel chair, intently observing a large screen. Suddenly, an otherworldly creature, resembling a cross between a mouse and an alien, emerges from the shadows. With a look of wonder and curiosity, the director gently extends a hand, initiating a tender caress of the creature's soft fur, highlighting a peaceful and unexpected interspecies connection. The scene is framed by high-definition visuals and enhanced by the ambient glow of the tech-filled environment, emphasizing the director's calm and respectful interaction with the unique being.]"
},
{
"from": "gpt",
"value": "Bad. The director's hand and the creation of the mysterious creature in the video have issues."
}
] |
seed44_2756
|
videos/HRA_part1/2756.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly moose stands in a hospital room, wearing a stethoscope around its neck, implying it plays the role of a doctor. The moose, with a caring expression, wipes the face of a seated patient, a child wearing a yellow shirt, using a soft cloth. The room is filled with natural light, highlighting the gentle interaction between the moose and the child, who looks up at the moose with trust and gratitude. Behind them, medical equipment and a hospital bed are visible, blending the elements of a healthcare setting with the unexpected presence of the animal.]"
},
{
"from": "gpt",
"value": "Normal. The action of the deer wiping the child's face with a soft cloth in the video is not smooth and coordinated."
}
] |
seed44_2360
|
videos/HRA_part1/2360.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man in outdoor gear, including a brown jacket, beige pants, and brown shoes, crawls on hands and knees across a grassy landscape under a cloudy sky. Beside him, a massive bison, its shaggy coat and large horns distinct, grazes on the lush vegetation, seemingly unperturbed by the man's presence. The scene conveys a sense of harmony between the man and the wild animal in their shared natural environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2874
|
videos/HRA_part0/2874.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 experienced engineer, clad in a futuristic spacesuit with an illuminated helmet, embarks on a critical space rescue mission. Against the backdrop of a vast, starlit cosmos, he is seen swimming through the emptiness of space, propelled by bursts from his suit's thrusters. With a focused gaze and a determination to save lives, he maneuvers towards a damaged spacecraft, its hull breached and systems failing. The engineer's suit, equipped with advanced technology, allows him to navigate the zero-gravity environment with precision and grace, as he reaches the stricken vessel to begin emergency repairs.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2769
|
videos/HRA_part1/2769.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a charcoal gray suit, white shirt, and red tie, sits at a large wooden desk in a traditional law office setting, which includes a bookcase filled with legal books and documents. The room is illuminated by natural light from a window behind the desk, casting a warm glow over the space. The lawyer, with neatly combed brown hair and glasses, holds a pen in his right hand and looks down at a document on the desk. Suddenly, he brings his left hand to his mouth to cover a cough, his eyes closing briefly as he experiences discomfort. The scene captures the professional environment and the unexpected moment of vulnerability.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's facial features in the video are generated disproportionately, and the fingers are deformed."
}
] |
seed42_1938
|
videos/HRA_part0/1938.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dedicated nurse, wearing a clean, white uniform and a green apron, is diligently scrubbing the bathroom floor in a hospital setting, her focused gaze and determined posture highlighting her commitment to hygiene. She uses a green scrub brush and a bucket of soapy water, her actions methodical and thorough. The bathroom is modern and well-lit, featuring stainless steel fixtures and a clean, white toilet, sink, and shower stall. The nurse's attention to detail and her professional demeanor underscore the importance of maintaining a sterile environment in the healthcare facility.]"
},
{
"from": "gpt",
"value": "Normal. The nurse in the video uses a green cleaning brush and a bucket of soapy water to scrub the bathroom floor, and her actions are basically normal, with only slight awkwardness."
}
] |
seed44_113
|
videos/HRA_part1/113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker in a power plant environment is seen wiping down a large turbine with a yellow cloth, dressed in a navy blue uniform, complete with a shirt, trousers, and safety shoes. The scene captures the maintenance aspect of power generation, with the worker focused on cleaning the metallic surface of the turbine. The power plant's interior is visible, featuring high ceilings, large machinery, and industrial pipes, all bathed in artificial lighting. The worker's attire, which includes a hard hat and protective gloves, emphasizes safety protocols in the industrial setting.]"
},
{
"from": "gpt",
"value": "Bad. The worker's hand generation in the video is problematic."
}
] |
seed46_1315
|
videos/HRA_part2/1315.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a yellow t-shirt and blue jeans, is playfully chasing a juvenile rhinoceros across a vast, grassy savannah under a bright blue sky. The action is captured from multiple angles, first showing the student's enthusiastic pursuit, followed by a shot of the rhino's surprised reaction as it turns its head back. Next, the scene focuses on the student's determined facial expression, highlighting the joy and energy of the chase. Finally, a side view captures the dynamic duo running in unison, the student's arms waving wildly and the rhinoceros' ears flapping, both enjoying the spontaneous adventure in the expansive landscape.]"
},
{
"from": "gpt",
"value": "Bad. The character's walking in the video is very unsmooth, and the movements are not coordinated. The rhino's movements are also unsmooth."
}
] |
seed46_2316
|
videos/HRA_part2/2316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, donning a gray turtleneck sweater and brown corduroy jacket, meticulously polishes silver cutlery using a white cloth, revealing a surprising domestic side. He sits at a large, cluttered wooden table, surrounded by an array of musical instruments, sheet music, and recording equipment, indicating his passion for music. The scene is set in a dimly lit room with vintage furniture, giving it a cozy, intimate atmosphere. The musician's focus is intense as he carefully cleans each piece of silverware, a task typically associated with waiters preparing for service, juxtaposed with his artistic profession.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers are missing in the video, and his eyes were not generated."
}
] |
seed46_1981
|
videos/HRA_part2/1981.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast warehouse environment filled with neatly stacked crates and industrial kitchen equipment, a chef clad in a white uniform and black trousers sprints down the aisles with determination. His arms swing energetically, and his gaze is set forward, indicating urgency and purpose. Behind him, the bustling activity of the kitchen continues, with chefs in white coats busily preparing meals. The chef races past stainless steel shelves stocked with food supplies, his black shoes pounding against the concrete floor, highlighting the dynamic energy of the scene. Throughout, the warehouse's high ceilings and industrial aesthetic provide a distinctive backdrop to the chef's energetic run.]"
},
{
"from": "gpt",
"value": "Bad. The man's running in the video is very unsmooth, and his movements are uncoordinated."
}
] |
seed46_3099
|
videos/HRA_part2/3099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savannah dotted with distant acacia trees, a large herd of African cape buffaloes gathers. The scene opens with a panoramic view of the herd, then zooms in on two buffaloes standing face-to-face, seemingly engaged in a dance-like interaction. The dominant male, with massive horns and a thick mane, takes a step forward, while the other male responds with a matching step, creating a rhythmic pattern. They continue this 'dance', mirroring each other's movements against the serene backdrop of the savannah, the clear blue sky, and the distant horizon, evoking a sense of primal connection and ritual within the herd.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the African wildebeest moving, with basically normal actions, but there is some lack of coordination."
}
] |
seed46_171
|
videos/HRA_part2/171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small ferret, wearing a miniature red scarf around its neck, is seen playfully dancing on a wooden floor in a rustic cabin. The creature twirls and leaps energetically to an unseen melody, its movements capturing the pure joy of dance. The natural light from a nearby window illuminates the scene, casting warm shadows across the room, highlighting the ferret's agile form as it continues its impromptu performance.]"
},
{
"from": "gpt",
"value": "Bad. The ferret's dancing movements in the video are not smooth and continuous, with sudden changes appearing in the middle frames."
}
] |
seed44_322
|
videos/HRA_part1/322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 European brown hare is seen swimming across a serene, glassy lake, its ears perked up and alert. It moves gracefully through the water, showcasing its rarely-seen swimming ability. The hare's body, including its long legs and large hind feet, propels it forward as it navigates the calm lake surface. The scene is set against a lush green landscape, highlighting the unexpected yet captivating sight of a hare swimming.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2495
|
videos/HRA_part1/2495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear including a yellow reflective jacket, black pants, and boots, meticulously irons his uniform in a room with a white wall and a table covered with a white cloth. The room is sparsely decorated, featuring a calendar and a portrait on the wall. The firefighter, sporting a well-groomed beard and a focused expression, demonstrates his attention to detail by carefully smoothing out the wrinkles in his uniform. The camera captures the steam from the iron as it glides over the fabric, highlighting the contrast between the firefighter's rugged appearance and the domestic task at hand.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_1403
|
videos/HRA_part2/1403.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 grey hoodie, beige khakis, and brown boots, runs across a grassy field under a clear blue sky, holding a remote control. Nearby, a squirrel scampers along the ground, its bushy tail bouncing. In the distance, an AI-piloted drone hovers, capturing aerial footage. The engineer occasionally glances upwards, monitoring the drone's position as it flies, while the squirrel continues its journey among the trees. The scene is set in a suburban park, with houses visible in the background, highlighting the integration of technology and nature in everyday life.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, the human limbs are uncoordinated."
}
] |
seed46_2546
|
videos/HRA_part2/2546.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer with short, dark hair and a neatly trimmed beard stands on a wooden chair, set atop a checkered floor, inside a rustic barn illuminated by soft, warm lighting. Dressed in a plaid shirt, blue jeans, and a brown vest, he reaches up to change a light bulb, his face reflecting concentration. The barn's wooden structure, adorned with tools and equipment, provides a backdrop for this everyday task, highlighting the farmer's practical skills and the cozy, well-lit interior of the barn.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2756
|
videos/HRA_part2/2756.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 friendly moose stands in a hospital room, wearing a stethoscope around its neck, implying it plays the role of a doctor. The moose, with a caring expression, wipes the face of a seated patient, a child wearing a yellow shirt, using a soft cloth. The room is filled with natural light, highlighting the gentle interaction between the moose and the child, who looks up at the moose with trust and gratitude. Behind them, medical equipment and a hospital bed are visible, blending the elements of a healthcare setting with the unexpected presence of the animal.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1498
|
videos/HRA_part1/1498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single zebra, its distinctive black and white stripes gleaming under the golden savanna sun, is sprinting across a vast, grassy plain. The muscles in its legs are taut, demonstrating raw power and grace as it leaps over tufts of grass. The zebra's mane flutters in the wind, adding to the sense of motion and freedom. Dust kicks up from the zebra's hooves as it races, highlighting the speed and agility of this magnificent creature. Behind the zebra, the landscape stretches to a distant horizon, dotted with acacia trees and the faint outlines of other wildlife, providing context for the zebra's natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2999
|
videos/HRA_part2/2999.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 grouper fish, with its distinct brown and white spotted pattern, swims serenely in a clear blue underwater environment. Its wide, flat head and protruding eyes are prominently featured as it navigates the aquatic space. Surrounding coral formations and gentle water currents add to the natural ambiance of the scene, providing a vivid portrayal of the grouper's habitat. The fish's powerful tail fin propels it effortlessly through the water, while smaller fish scatter in its presence, highlighting the grouper's dominant position in the marine ecosystem.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1079
|
videos/HRA_part2/1079.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single 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": "Good. Basically no problem."
}
] |
seed46_2728
|
videos/HRA_part2/2728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 artistic individual, donning a black beret and a red and black striped shirt, dances whimsically in a studio filled with vibrant paintings and art supplies. In their right hand, they hold a ferret that matches their playful energy, engaging in a synchronized dance that reflects their unique bond. The ferret, wrapped around their wrist like a furry bracelet, seems to enjoy the movement, adding a touch of eccentricity to the scene. The artist's left hand gestures expressively, complementing their dance moves, while the chaotic yet colorful environment around them enhances the creative atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly uncoordinated."
}
] |
seed44_1764
|
videos/HRA_part1/1764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a sleek silver spacesuit adorned with patches, performs an energetic dance against the backdrop of a vast, star-filled universe. The scene opens with the actor floating gracefully in zero gravity, spinning and twirling with the joy of someone experiencing the wonder of space tourism. Their movements are fluid and expressive, conveying a sense of freedom and exhilaration. As the dance continues, the actor executes a series of dynamic leaps and poses, each one highlighting the unique challenges and opportunities of dancing in microgravity. The stars shimmer and galaxies glow in the distance, providing a breathtaking canvas for this cosmic performance. Throughout the video, the actor's face, visible through the clear visor of their helmet, radiates with delight, sharing the magic of space travel through the universal language of dance.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the actors in the video are deformed and missing, with fingers not fully formed and the body twisted."
}
] |
seed46_1153
|
videos/HRA_part2/1153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male worker, wearing a brown shirt and green shorts, attentively wipes an Asian elephant's face using a small cloth. The elephant, with its trunk slightly raised, stands calmly next to a wooden structure within a spacious enclosure, possibly at a wildlife sanctuary. The man continues to clean the animal's eye area, showing care and familiarity, while the elephant remains still, indicating a trusting relationship between the two. Throughout, the worker focuses on his task, gently tending to the creature's needs in a peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1971
|
videos/HRA_part1/1971.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair, wearing a gray shirt, sits at a modern office desk cluttered with electronics and tools, knitting a red scarf with large needles. The focus is on her hands as they deftly manipulate the yarn and needles, while a laptop with coding screensaver and a blueprint of a circuit board are visible in the background. The office space is filled with tech gadgets, books, and papers, highlighting her professional environment, yet she finds time for a personal hobby, creating a vivid red scarf amidst the technical surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1218
|
videos/HRA_part0/1218.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diligent male artist applies paint to a large, colorful abstract artwork on a vertical easel, positioned outdoors against a sunny, clear blue sky. Dressed in a simple white tank top and khaki cargo shorts, he works intently, surrounded by various tools of his trade including brushes, a palette, and a small table holding additional supplies. His focused expression and the vibrant colors of the painting contrast sharply with the natural greenery and clear sky in the background, creating a dynamic scene of creative energy and artistic passion.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, and the hands are twisted."
}
] |
seed44_1761
|
videos/HRA_part1/1761.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 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 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": "Good. Basically correct."
}
] |
seed42_2448
|
videos/HRA_part0/2448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, characterized by its dark fur and physical strength, leaps powerfully from a low branch in a lush, green forest. The chimp, wearing a radio collar for tracking purposes, is seen mid-jump, demonstrating its agility and vitality. Its movement is captured in high definition, highlighting the details of its fur and the determination in its eyes. The chimpanzee propels itself forward, leaving the branch behind, showcasing its natural habitat and behaviors in a captivating, close-range shot.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1296
|
videos/HRA_part0/1296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged female worker sits on a wooden chair under the shade of a tree, knitting a long, colorful scarf with red, green, and yellow yarns. She wears a simple cotton dress and sandals, her hair tied back in a bun. The scene is set in a small courtyard surrounded by lush greenery and blooming flowers, with sunlight filtering through the leaves, casting dappled shadows on the ground. The woman's hands move deftly, the knitting needles clicking together in a steady rhythm, as she focuses intently on her work, occasionally glancing up to enjoy the peaceful surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands, face, and legs are distorted."
}
] |
seed42_2016
|
videos/HRA_part0/2016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic gorilla, adorned with a vibrant, golden crown and a silver cape, dances gracefully on a floating platform set within Neptune's ethereal atmosphere. The planet's vivid blue and green gaseous clouds swirl dramatically in the background, creating an otherworldly backdrop. The gorilla performs a series of elegant dance moves, its powerful yet gentle demeanor captivating the viewer. The platform, illuminated by a soft, celestial glow, adds to the mystical ambiance of this extraordinary interstellar dance performance.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2781
|
videos/HRA_part1/2781.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with complex machinery and scientific equipment, a police officer, dressed in a crisp uniform, carefully observes a quantum entanglement experiment. The officer, showing a surprising gentleness, caresses the edge of an intricate device, symbolizing a connection between law enforcement and cutting-edge science. Around him, scientists in lab coats monitor screens and adjust dials, creating an atmosphere of intense concentration and curiosity. The scene is bathed in the soft glow of monitors and the eerie blue light of lasers, highlighting the unusual juxtaposition of authority and scientific exploration.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video."
}
] |
seed44_1047
|
videos/HRA_part1/1047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, wearing a white shirt, blue overalls, and a wide-brimmed hat, stands in a lush green field under a clear blue sky. He is in mid-throw, tossing hay bales with ease, his strong arms and focused expression showcasing his expertise. The hay bales are wrapped neatly in plastic, indicating a modern farming technique. The farmer's stance, with one leg forward for balance, adds dynamism to the scene, while the rolling hills and distant trees provide a picturesque rural backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1698
|
videos/HRA_part1/1698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nimble squirrel, brimming with energy, leaps from a moss-covered branch in a lush, vibrant forest. The scene is bathed in a soft, golden light filtering through the dense canopy above. The squirrel's movement is captured mid-jump, its body arched gracefully in the air, showcasing its agility and speed. Its bushy tail trails behind, adding to the dynamic feel of the action. The background is a tapestry of green foliage, dotted with various tree trunks, providing a rich, textured setting for the squirrel's acrobatics.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's facial features and limbs are not fully generated, and the body is deformed, with incomplete paws."
}
] |
seed46_2433
|
videos/HRA_part2/2433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A director, distinguished by his brown hair and beard, along with round glasses, is seated in a director's chair on a set resembling a grassland heath. He interacts with a small gerbil, which scurries across the set's surface. The director is shown wiping his glasses with a cloth, revealing his blue eyes, while the gerbil continues its exploration nearby. The backdrop depicts a sunny day on the heath, complete with a blue sky and green vegetation, adding a natural element to the studio setting. Throughout, the director's focus alternates between the gerbil and wiping his glasses, capturing the unique dynamic between the two.]"
},
{
"from": "gpt",
"value": "Normal. There is no action of wiping the glasses."
}
] |
seed46_3059
|
videos/HRA_part2/3059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow high-visibility jacket and blue jeans, stands near a buffalo swimming in a serene, placid lake, surrounded by lush greenery. The buffalo, with its massive frame and shaggy coat, gracefully paddles through the clear water, creating ripples that extend outward. In the background, a wooden pier extends into the lake, and tall trees line the shore, providing shade and a sense of serenity. The janitor looks on, perhaps during a break from his duties, observing the buffalo in its natural habitat, a harmonious blend of nature and human presence.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.