video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2963
|
videos/HRA_part0/2963.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, wearing a classic black vest, white shirt, and black tie, serves a bobcat perched on a bar stool at an outdoor poolside bar. The bobcat, looking surprisingly at ease, has its paw on a cocktail glass. In the background, a group of people enjoys a day at the pool, with some swimming leisurely, creating a surreal yet serene atmosphere under the clear blue sky. The waiter, maintaining his professional demeanor, interacts with the wild guest, adding an unexpected twist to a typical day by the pool.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2967
|
videos/HRA_part0/2967.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": "Bad. The bird's claws in the video are deformed, and its wings do not spread during flight, which does not meet the conditions for flying, and there are problems with the generation of the beak."
}
] |
seed46_1455
|
videos/HRA_part2/1455.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a white apron over a blue checkered shirt and khaki pants, abandons his culinary pursuits to embrace a different kind of artistry. Holding a paintbrush in his right hand, he applies vibrant red paint to a wall, creating an abstract design reminiscent of a Jackson Pollock masterpiece. The room, with its white walls and wooden floorboards, serves as a blank canvas for his newfound passion. As he works, his concentration is palpable, revealing a side of him that finds fulfillment beyond the kitchen. The transformation of the space from a simple dining area into a colorful, artistic haven underscores his creative versatility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2378
|
videos/HRA_part0/2378.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical dry forest, dappled sunlight filters through sparse leaves onto a woman wearing a khaki tank top and brown capri pants, standing near a tree trunk. She wipes her face with a white cloth, revealing beads of sweat. Nearby, a backpack rests against a tree, and the landscape is dotted with cacti and shrubs, indicating the arid environment. The woman's action conveys the physical exertion and determination associated with exploring such a unique ecosystem.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2273
|
videos/HRA_part1/2273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting illuminated by vibrant neon lights, a diligent worker clad in a gray jumpsuit and helmet stands on a sleek, anti-gravity vehicle. The vehicle, featuring a metallic finish and aerodynamic design, hovers above a clean, white platform. The worker is engaged in wiping the vehicle's surface with a cloth, ensuring its spotless condition. Behind the scene, a vast hangar filled with advanced technology and equipment can be seen, emphasizing the high-tech environment in which the worker operates. The worker's focused expression and meticulous attention to detail highlight their commitment to maintaining the anti-gravity vehicle's pristine state.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the arm is twisted, the hand is deformed, and the cloth in the hand is also twisted."
}
] |
seed44_1802
|
videos/HRA_part1/1802.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a red and white striped shirt, dark pants, and a vibrant tiger head costume, energetically dances in front of a large crowd at a lively pep rally. The atmosphere is electric, filled with cheering fans and the spirit of school pride. The young man, donning the mascot's full-body suit complete with furry orange and black stripes, performs dynamic dance moves to the beat of an upbeat marching band, captivating the audience with his animated antics. Surrounded by enthusiastic supporters waving banners and flags, the scene pulses with excitement and unity, perfectly capturing the essence of collegiate spirit.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and twisted legs."
}
] |
seed42_1603
|
videos/HRA_part0/1603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his chiseled jawline and dark, neatly styled hair, stands on a wooden chair in a spacious, modern living room. He wears a casual, fitted black t-shirt and dark jeans, and is engaged in the everyday task of changing a light bulb. The room is furnished with a brown leather sofa and a large flat-screen TV on the wall. The actor's focused gaze and confident posture suggest his ease in handling both dramatic roles and practical household chores. The warm, diffused lighting from other fixtures illuminates the scene, highlighting the actor's profile as he completes the relatable task with a touch of understated elegance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2701
|
videos/HRA_part2/2701.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly surreal scene, a mongoose, typically a small terrestrial carnivore, is depicted engaging in an extraordinary activity. It is shown riding a horse, specifically a Mars horse, which could imply a horse adapted to the conditions of Mars or having Martian features, across a barren, rocky landscape reminiscent of the Martian surface. The mongoose, now a rider, steers the horse with determination as they race through the rugged terrain. The action intensifies as they begin to run at full speed, the horse's hooves kicking up red dust, while the mongoose holds on tightly, its small size contrasting with the grandeur of the Martian environment. This fantastical scenario combines elements of adventure, science fiction, and nature in a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1990
|
videos/HRA_part1/1990.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a majestic raven perched on a branch, its glossy black feathers shimmering under the sunlight, revealing hints of blue and green. The bird has striking yellow eyes that seem to hold a world of wisdom. Its beak is curved and sharp, a testament to its carnivorous nature. The raven is surrounded by lush green foliage, and in the background, misty mountains add to the mystical atmosphere. Occasionally, the raven caws, a deep, resonant sound that echoes through the dense forest, asserting its presence in the serene wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1512
|
videos/HRA_part1/1512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dynamic montage begins with a charismatic musician wearing a space-themed outfit, strumming an electric guitar under the glow of neon lights, surrounded by cosmic visuals. The scene shifts to a historic moon landing, featuring a space-suited astronaut planting a flag on the lunar surface, with the Earth visible in the distance. Lastly, we see a determined athlete sprinting across a track, the focus on their powerful legs and the intensity in their eyes, pushing towards the finish line against a backdrop of cheering spectators. Each scene is seamlessly connected through a thematic thread of human achievement and exploration.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes. When the astronaut runs on the moon, there is a sudden change in the legs."
}
] |
seed46_1882
|
videos/HRA_part2/1882.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated female nurse, clad in a white uniform and wearing her hair in a bun, attentively checks a smoke detector mounted on the ceiling in a modern hospital hallway. The space is pristine and well-lit, with pale green walls and white trim, exuding a sense of cleanliness and professionalism. The nurse, displaying her commitment to safety, uses a long, red-handled tool to test the device, ensuring it functions properly in the healthcare environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_1748
|
videos/HRA_part0/1748.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in a formal suit, complete with a tie and dress shoes, finds himself unexpectedly paired with a costumed individual in a full-body rabbit outfit, both engaging in a whimsical dance under the night sky. They twirl and leap across a moonlit stage, surrounded by an audience of stuffed animals and woodland creatures, all watching in silent amusement. The scene is surreal, with a touch of magic in the air, as the man and the rabbit continue their unlikely dance, lost in the joy of the moment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2795
|
videos/HRA_part0/2795.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a gray beard, wearing a gray t-shirt, blue jeans, and green rubber boots, tends to his garden on a bright, sunny day. He begins by standing near a lush green hedge, holding a pair of gardening shears, ready to prune. In the next scene, he is seen pruning the hedge with precision and care, showcasing his expertise. Then, he carries a large brown bag, possibly for collecting clippings, while walking across his well-manicured lawn. Finally, he waters the plants with a hose, ensuring each one receives the necessary hydration, all set against the backdrop of a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate shears, a large brown bag, or a water pipe."
}
] |
seed42_2354
|
videos/HRA_part0/2354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic juxtaposition, a rugged firefighter, clad in full gear and holding a fire hose, stands tall against a backdrop of scientific equipment and dark matter research posters. The scene shifts to focus on the firefighter gently caressing the side of a large, complex machine, symbolizing a tender connection between humanity and the pursuit of knowledge. The firefighter's protective clothing contrasts with the sterile environment of the research facility, creating a compelling visual narrative. Behind him, screens display data related to dark matter studies, emphasizing the unusual fusion of two vastly different worlds.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_258
|
videos/HRA_part2/258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate female veterinarian, wearing a white lab coat and blue scrubs, gently feeds a small dog from a spoon, her caring nature evident in her warm smile. The clinic room is clean and modern, with stainless steel equipment and a large window providing natural light. Behind her, a poster about pet nutrition hangs on the pale green wall. On a nearby table, various pet food samples are neatly arranged, emphasizing the importance of proper animal care. Throughout the scene, the vet's loving interaction with the dog highlights her dedication to animal welfare.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's fingers are deformed in the video, the face is distorted, there are issues with the dog's face, and the position of the tail and legs is incorrect."
}
] |
seed44_2166
|
videos/HRA_part1/2166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a gray jumpsuit with a yellow utility vest over it, diligently wipes down a pristine, metallic surface within a bustling space station habitat. The vibrant blue and white Earth can be seen through a large window in the background, providing a stunning contrast to the industrial interior. As he works, the man pushes a cleaning cart filled with various supplies, emphasizing his commitment to maintaining the cleanliness of the space station. Nearby, two fellow crew members, wearing matching gray jumpsuits with red accents, are engaged in a conversation, adding to the lively atmosphere of the space habitat. Throughout the scene, the janitor continues his task with a focused determination, highlighting the importance of his role in the maintenance of the space station.]"
},
{
"from": "gpt",
"value": "Bad. Actions are not continuous, there are sudden changes."
}
] |
seed42_2872
|
videos/HRA_part0/2872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird has a sturdy, sharp beak and intense, intelligent eyes that survey the surroundings. Its wings are slightly spread, showing the intricate layering of feathers, while the background is a blur of lush green foliage and dappled light. The crow then takes flight, its powerful wingbeats propelling it through the air against the vivid backdrop of the forest.]"
},
{
"from": "gpt",
"value": "Normal. There is an issue with the generation of the crow's wings in the video."
}
] |
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 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 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": "Good. No obvious problems."
}
] |
seed42_277
|
videos/HRA_part0/277.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda, with its distinctive black and white fur, sits in a lush bamboo forest. It holds a piece of bamboo in its paw, bringing it to its mouth as if tasting the fresh shoot. Suddenly, the panda wipes its mouth with its paw, a natural gesture after eating, leaving a trail of moisture on its furry face. The panda continues to munch on the bamboo, occasionally pausing to wipe its mouth again, all against the serene backdrop of the bamboo forest.]"
},
{
"from": "gpt",
"value": "Normal. The panda's paws were generated incorrectly, and the bamboo was not fully generated."
}
] |
seed46_2698
|
videos/HRA_part2/2698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmhand, clad in a khaki shirt, beige trousers, and brown shoes, walks purposefully across a well-kept yard. In the foreground, a vibrant red barn provides contrast against the clear blue sky. The worker pauses, bending down to pick up a lively chicken, its feathers a mix of brown and white, before continuing on his path, the bird calmly tucked under his arm. They stroll together, the worker's gait steady and the chicken seemingly unperturbed, encapsulating the peaceful rhythm of life on the farm.]"
},
{
"from": "gpt",
"value": "Bad. The scene of the chicken in the worker's arms was not generated."
}
] |
seed44_294
|
videos/HRA_part1/294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate teacher, donning a red top and black leggings, executes a captivating zero-gravity dance in a spacious, well-lit room. She leaps and twirls effortlessly, mimicking the weightlessness of space, as if defying Earth's gravity. Seamlessly transitioning, she begins running in place, her movements fluid and energetic, demonstrating the illusion of floating while maintaining contact with the ground. Throughout, her expressive face conveys the exhilaration and freedom of movement in a zero-gravity environment.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's facial features in the video are generated blurily, and the limbs are distorted. The teacher's limbs suddenly disappear or appear in the middle frames."
}
] |
seed42_2313
|
videos/HRA_part0/2313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 golden jackal leaps gracefully over a log in the middle of a grassy savanna, its body stretched mid-air, showing agility and strength. The jackal, with its keen eyes and alert posture, exhibits a powerful jump, clearing the obstacle effortlessly. The scene captures the animal's dynamic movement against a backdrop of tall grasses swaying in the breeze, highlighting the beauty and resilience of this wild canine in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The limbs and tail of the golden jackal in the video are missing, and the face is slightly blurry."
}
] |
seed44_2904
|
videos/HRA_part1/2904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bull moose, antlers wide and impressive, runs through a lush, green meadow under a clear blue sky, with a distant mountain range visible on the horizon. Its powerful legs propel it forward in a graceful gallop, kicking up small clouds of dust from the dry earth beneath its hooves. The moose's coat is a deep brown, nearly black, and its large body ripples with muscles as it bounds across the landscape, the embodiment of wild strength and freedom. In the background, tall trees frame the edges of the clearing, their leaves whispering softly in the breeze, while birds take flight, startled by the majestic creature's sudden movement.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1771
|
videos/HRA_part2/1771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a duty belt and a radio, is seen kneeling on a polished wooden floor in a residential setting, attentively wiping the muddy paws of a large, brown dog. The officer wears a serious expression, focused on the task at hand, ensuring the canine's paws are clean. The environment is warm and welcoming, with a Christmas tree in the background, decorated with colorful ornaments and lights, adding a festive touch to the scene. The officer's careful actions and the presence of the holiday decorations create a sense of care and community during the holiday season.]"
},
{
"from": "gpt",
"value": "Normal. The facial expressions of the police officer and the generation of the hands and the dog's paws in the video have issues."
}
] |
seed44_1988
|
videos/HRA_part1/1988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprawling mall, a middle-aged janitor, clad in a yellow high-visibility vest and dark pants, runs with purpose through the corridors. The scene begins with him standing alert, mop in hand, amidst the vibrant retail environment. Then, he sprints past various storefronts, the motion blur from his movement emphasizing his haste. As he continues, he deftly maneuvers around a corner, demonstrating agility in his work boots. Lastly, he is shown running with determination across a checkered tile floor, the bustling mall life continuing around him, highlighting his role in maintaining the facility's cleanliness amidst the daily hustle and bustle.]"
},
{
"from": "gpt",
"value": "Normal. The man's limbs in the video are missing, his face is blurry, and the mop in his hand is deformed."
}
] |
seed46_1505
|
videos/HRA_part2/1505.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, plump quail with brown and black speckled feathers stands prominently in the foreground, nestled among lush green foliage that includes leaves, ferns, and tall grasses. It faces left, its head turned slightly toward the camera, revealing its distinctive facial features, including a small beak and alert eyes. The bird's textured feathers are intricately detailed, and its legs are visible as it perches on the forest floor, surrounded by the vibrant flora.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2347
|
videos/HRA_part0/2347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a spacesuit adorned with NASA patches and a backpack, pauses his cleaning duties on a Martian landscape under a starry sky. He looks up, captivated by the celestial beauty, before engaging in a joyful dance, spinning and moving gracefully against the backdrop of Mars' red terrain and the twinkling stars above. His movements are fluid and expressive, a stark contrast to the barren, rocky surface of the planet beneath him. Despite the harsh environment, the janitor finds a moment of joy and wonder, encapsulating the spirit of exploration and the human capacity for finding beauty in unexpected places.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's limbs and body are distorted, and the face is deformed."
}
] |
seed44_1096
|
videos/HRA_part1/1096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space reality TV set, an antelope, wearing a small golden bell around its neck, stands calmly against a backdrop of stars and galaxies. The animal is gently caressed by a human figure dressed in a spacesuit, conveying a sense of comfort and companionship in the vastness of space. The astronaut's gloved hand softly touches the antelope's face, while the creature looks on serenely, the golden bell shining under the starlight, creating a surreal and touching moment in an extraterrestrial environment.]"
},
{
"from": "gpt",
"value": "Normal. The movements are uncoordinated, but the action of stroking the antelope's cheek is possible."
}
] |
seed46_2795
|
videos/HRA_part2/2795.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a gray beard, wearing a gray t-shirt, blue jeans, and green rubber boots, tends to his garden on a bright, sunny day. He begins by standing near a lush green hedge, holding a pair of gardening shears, ready to prune. In the next scene, he is seen pruning the hedge with precision and care, showcasing his expertise. Then, he carries a large brown bag, possibly for collecting clippings, while walking across his well-manicured lawn. Finally, he waters the plants with a hose, ensuring each one receives the necessary hydration, all set against the backdrop of a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, hands, legs, and items in the hand are distorted in the video."
}
] |
seed44_2521
|
videos/HRA_part1/2521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A skilled musician, donning a black hat and dressed in a brown jacket over a white shirt, plays a wind instrument passionately in an art gallery filled with contemporary art pieces. Suddenly, a gazelle, a symbol of grace and freedom, jumps into the frame from the right side, leaping over a low sculpture, adding an unexpected yet harmonious element to the scene. The focus remains on the musician and the gazelle, with the vibrant artwork providing a stimulating backdrop, all captured in a single, continuous shot.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_128
|
videos/HRA_part0/128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its greenish-blue body with orange highlights and yellow fins, swims gracefully among the coral reefs. Its intricate scales resemble armor, providing a unique texture. It explores its underwater world, surrounded by various corals of purple, red, and orange, creating a stunning contrast against the blue water. The fish's beak-like mouth, a characteristic feature, is clearly visible as it feeds on algae-covered rocks, demonstrating its natural behavior in its marine habitat.]"
},
{
"from": "gpt",
"value": "Bad. The fish's fins in the video are generated too large, and an extra eye is unreasonable."
}
] |
seed46_2232
|
videos/HRA_part2/2232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a green apron over a gray shirt and dark pants, runs down a dimly lit corridor in a large cinema complex. The hall is lined with red carpeting and features a series of doors leading into various screening rooms. The man's facial hair and glasses are distinctive, and he carries a cleaning tool in his right hand. As he sprints, his eyes are set forward, and he passes by a sign with movie titles and showtimes, creating a sense of urgency in the vast, quiet space. The scene captures the hurried pace and isolated environment of the janitor's duties within the cinema.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate the cleaner's tools."
}
] |
seed44_186
|
videos/HRA_part1/186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of cheerful children, ranging from toddlers to preteens, are engaged in the task of cleaning windows on a bright, sunny day. They wear casual clothes, including t-shirts, shorts, and sneakers, and sport various hairstyles, from pigtails to afros. The kids use squeegees and rags to wipe down the glass, leaving streaks of water and soap behind. They work together, laughing and chatting, as they tackle the large window panes of a suburban home, with lush greenery visible through the transparent surfaces. The atmosphere is one of teamwork and fun, with the youngsters taking pride in their chores under the warm glow of the sun.]"
},
{
"from": "gpt",
"value": "Normal. The children's actions of cleaning the glass in the video are not continuous and there are abrupt changes."
}
] |
seed46_2312
|
videos/HRA_part2/2312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male chef, donning a white chef's uniform with black stripes and a matching cap, meticulously washes dishes in a commercial kitchen. The room is illuminated by bright overhead lights, casting a glow on the stainless steel sink and countertops. Steam rises from the hot water, creating a misty atmosphere. The chef's sleeves are rolled up to his elbows, revealing tattoos, as he focuses intently on cleaning each plate with precision and care. In the background, the bustling kitchen is visible, with other chefs preparing meals and the sounds of clattering pots and sizzling pans adding to the lively ambiance.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_329
|
videos/HRA_part1/329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy, yellow chick with a small, red beak is seen crawling across a surface covered in hay, its tiny feet moving steadily as it explores its surroundings. The chick pauses momentarily, looking around with bright eyes, before continuing its crawl. The camera captures the chick from various angles, highlighting its downy feathers and the texture of the hay beneath it. Throughout the video, the chick remains the central focus, its curious movements and adorable appearance captivating the viewer's attention.]"
},
{
"from": "gpt",
"value": "Normal. The chick's movements are not smooth."
}
] |
seed44_2378
|
videos/HRA_part1/2378.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical dry forest, dappled sunlight filters through sparse leaves onto a woman wearing a khaki tank top and brown capri pants, standing near a tree trunk. She wipes her face with a white cloth, revealing beads of sweat. Nearby, a backpack rests against a tree, and the landscape is dotted with cacti and shrubs, indicating the arid environment. The woman's action conveys the physical exertion and determination associated with exploring such a unique ecosystem.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, and the item in hand is distorted."
}
] |
seed46_1774
|
videos/HRA_part2/1774.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene set within the lush environment of a tropical dry forest, a young, smiling female cashier, wearing a red apron over a white blouse and black pants, energetically jumps over a small log. She lands gracefully, holding a miniature baseball bat, as if ready for an unexpected game amidst the dense vegetation. The vibrant green foliage and dappled sunlight create a vivid contrast against her outfit, capturing the spirit of adventure and playfulness in an unconventional setting.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a small log, and the baseball bat was not fully generated."
}
] |
seed46_2875
|
videos/HRA_part2/2875.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating close-up, a tiny weasel, no larger than a human hand, emerges from a hole in a tree trunk set against the vast, snow-covered taiga. Its bright eyes curiously scan its surroundings. It then playfully interacts with the bark, as if caressing it, showcasing a rare display of animal behavior. The camera then captures the weasel's face in detail, highlighting its sharp features and lively demeanor. Lastly, it returns to the hole, pausing once more to look back, offering a final glimpse of its charming presence in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The weasel can be seen stroking the tree bark in the video, the action is basically normal, but there is slight disharmony."
}
] |
seed42_2187
|
videos/HRA_part0/2187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse with short brown hair, wearing a blue uniform and a stethoscope around her neck, playfully interacts with a ferret on a clean, white examination table in a well-lit veterinary clinic. The ferret, displaying its natural agility, leaps from the nurse's hands as she gently tosses it upwards. The nurse, with a joyful smile, catches the ferret mid-air, showcasing a tender bond between the caregiver and the small animal in a serene medical environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous."
}
] |
seed44_3202
|
videos/HRA_part1/3202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green jacket, beige shirt, and khaki pants, stands in a studio, passionately gesturing with his hands. Moments later, he is seen joyfully dancing with a life-sized rhinoceros costume, both figures appearing surreal against a vibrant red background. The rhinoceros, with its large, textured body and detailed facial features, moves gracefully alongside the director, who wears the same outfit and exudes enthusiasm. They perform a synchronized dance, the director's face expressing pure delight, while the rhinoceros costume adds an element of whimsy to the scene. Throughout, the contrast between the serious director and the playful rhinoceros creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The director's face generation in the video is blurry, the fingers are deformed, and there are issues with the rhinoceros's head and limbs."
}
] |
seed46_2836
|
videos/HRA_part2/2836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and whimsical scene, a small, cartoonish grey elephant, adorned with a red polka-dotted bow around its neck, is shown mid-jump, its trunk lifted playfully. Against a vivid, clear blue sky, this joyful creature leaps from a lush green meadow dotted with yellow flowers, capturing a moment of pure delight and fantasy. The elephant's large ears are spread wide, adding to the comical effect, while its tiny eyes are closed in sheer happiness, creating a charming and unforgettable visual.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1333
|
videos/HRA_part1/1333.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lively brown and white dog bounds through the shallow waters of a serene lake at sunset, its fur glistening with droplets. It shakes vigorously, sending water flying in a sparkling mist, while standing on the sandy shore. Against the backdrop of a tranquil lake and a stunning sunset, the energetic canine leaps into the air, capturing the essence of joy and freedom. As it lands, it shakes again, creating a captivating spray against the golden hour light, highlighting every droplet in the air. Throughout, the dog wears a red collar, adding a pop of color against the natural hues of the landscape.]"
},
{
"from": "gpt",
"value": "Bad. The dog's jumping in the video is not smooth and the movements are uncoordinated."
}
] |
seed42_1231
|
videos/HRA_part0/1231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter wearing a black vest, white shirt, and black trousers leaps into the air, displaying an unexpected burst of energy, against a backdrop of lush subtropical shrubland. The landscape is filled with vibrant green bushes and trees, creating a vivid contrast to the waiter's formal attire. As he jumps, his posture suggests both playfulness and professionalism, blending the elements of surprise and elegance in an outdoor setting characterized by rich vegetation and natural beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1559
|
videos/HRA_part1/1559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a crisp uniform consisting of a navy blue shirt, matching trousers, and a peaked cap, is engaged in an unusual task inside a busy restaurant district. He is meticulously wiping down a row of outdoor tables, each set with white tablecloths and surrounded by patrons enjoying their meals. The backdrop features a variety of restaurants, ranging from elegant dining establishments to casual eateries, all bustling with activity. The scene captures the unexpected sight of law enforcement taking on a service role, contributing to the cleanliness and ambiance of the dining area.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2435
|
videos/HRA_part2/2435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic stork, distinguished by its gray feathers and black wingtips, is captured in a series of poses. Initially, it stands tall on a grassy bank, legs firmly planted, looking alert. Then, it spreads its wings wide, ready for flight, with a serene lake and lush greenery serving as a backdrop. Next, the bird is seen in mid-flight, gracefully soaring over the water's surface, with its wings fully extended and head held high. Finally, it lands elegantly, tucking its wings and extending its long legs, touching down on the grass near the water's edge, completing the sequence of its daily activities by the lakeside.]"
},
{
"from": "gpt",
"value": "Bad. The stork's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_1075
|
videos/HRA_part0/1075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and khaki pants, stands in a lush, green forest clearing, gently wiping mud off the antlers of a majestic deer using a soft cloth. The deer, with large, inquisitive eyes, tolerates the man's ministrations, standing still as the man carefully cleans each tine of the impressive antlers. Sunlight filters through the canopy above, casting dappled shadows on the scene below, highlighting the tender interaction between the man and the wild creature.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2640
|
videos/HRA_part2/2640.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a brown coat, black pants, and a white shirt with a tie, walks through a dense forest, his eyes intently scanning the surroundings. As he strides, a small squirrel scurries across the path in front of him, pausing momentarily to look up at the towering figure before continuing on its way, encapsulating a moment of human interaction with nature's tiny inhabitants in a woodland setting.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel and character movements in the video are not smooth."
}
] |
seed44_1505
|
videos/HRA_part1/1505.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, plump quail with brown and black speckled feathers stands prominently in the foreground, nestled among lush green foliage that includes leaves, ferns, and tall grasses. It faces left, its head turned slightly toward the camera, revealing its distinctive facial features, including a small beak and alert eyes. The bird's textured feathers are intricately detailed, and its legs are visible as it perches on the forest floor, surrounded by the vibrant flora.]"
},
{
"from": "gpt",
"value": "Bad. The quail's feet in the video are deformed, and the beak is disproportionate."
}
] |
seed46_2495
|
videos/HRA_part2/2495.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 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 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": "Good. Basically correct."
}
] |
seed44_2264
|
videos/HRA_part1/2264.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous firefighter, clad in full gear and a helmet, leaps into action from a weathered wooden pier extending over a body of water, the afternoon sunlight casting a dramatic glow. The firefighter, equipped with a life vest over his protective clothing, jumps off the end of the pier, the water shimmering beneath him as he descends. In the background, a firetruck is visible, parked on the pier, its red color contrasting against the blue sky and water, adding to the intensity of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2736
|
videos/HRA_part1/2736.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit cave, a small brown bat, with leathery wings folded against its body, walks along the rocky ground with deliberate steps. Its face, framed by long, curved ears, is keenly observant. The bat pauses momentarily, revealing its tiny feet and claws as it navigates the stone surface. The focus then shifts to the bat's head, highlighting its intricate facial features and alert eyes. Finally, the bat is seen walking away, its silhouette set against the textured cave wall, creating a captivating scene of a bat navigating its environment on foot.]"
},
{
"from": "gpt",
"value": "Bad. The bat's claws and wings are deformed in the video, and the face is generated blurry."
}
] |
seed46_141
|
videos/HRA_part2/141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy room filled with natural light, two young children sit cross-legged on a wooden floor, engrossed in crocheting a vibrant blanket. One child, wearing a yellow T-shirt and denim shorts, focuses intently on their work, their tongue slightly protruding in concentration. The other, dressed in a pink sweater and khaki pants, looks up momentarily, a smile playing on their lips, before returning to the colorful yarn in their hands. The atmosphere is warm and inviting, with the half-finished blanket spreading across their laps, a testament to their patience and creativity. Beside them, a basket of yarn in various shades adds a touch of whimsy to the scene, as the children continue to crochet, their movements steady and practiced.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2549
|
videos/HRA_part2/2549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, wearing a beige jacket and dark trousers, sits on a wooden dock by the water's edge. He gently caresses a small, curious otter that has climbed onto his lap, looking into its eyes with a warm smile. The otter, with its sleek brown fur and bright, inquisitive gaze, seems comfortable and at ease in the actor's presence. The scene is set against a serene backdrop of gently lapping waves and lush greenery, capturing a tender moment between human and animal in a peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes, and the man's hand appears deformed."
}
] |
seed44_1561
|
videos/HRA_part1/1561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut, clad in a sleek silver spacesuit and helmet, leaps into the air against the backdrop of a distant galaxy, stars shimmering in the vast cosmic landscape. The astronaut's pose conveys a sense of weightlessness and freedom as he appears to float in zero gravity, with the vibrant colors of far-off celestial bodies providing a dramatic contrast to his metallic attire. The scene captures the exhilaration and mystery of interstellar exploration, with the astronaut seeming to defy the laws of physics in the boundless expanse of space.]"
},
{
"from": "gpt",
"value": "Normal. The astronaut's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_2781
|
videos/HRA_part2/2781.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": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_1475
|
videos/HRA_part2/1475.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman wearing a yellow shirt and black leggings stands before a large aquarium filled with exotic fish, carefully cleaning the glass with a magnetic cleaner in her right hand. The fish swim curiously around the algae-covered areas she has yet to clean, while the bubbles from her cleaning tool ascend gently. The room is softly lit, casting a warm glow on the woman's focused face as she leans into her task. Behind her, a window lets in natural light, illuminating the space and highlighting the water droplets on the outside pane. Throughout, she remains engrossed in her work, ensuring each section of the tank is spotless.]"
},
{
"from": "gpt",
"value": "Normal. The movements are uncoordinated, but the action of cleaning the fish tank can be seen."
}
] |
seed44_2427
|
videos/HRA_part1/2427.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist dons a spacesuit and helmet, adorned with vibrant colors and patterns, resembling a solar sail, as they crawl across a barren lunar landscape, backlit by the Earth's glow. The suit, with its reflective, sail-like design, catches the sunlight, creating mesmerizing reflections and shadows. The artist moves slowly, emphasizing the suit's unique texture and the dramatic contrast between the suit and the moon's surface. This artistic portrayal on the moon's surface, with the distant Earth providing a serene backdrop, highlights the intersection of art and space exploration.]"
},
{
"from": "gpt",
"value": "Normal. The artist's limbs generation in the video has problems."
}
] |
seed46_2356
|
videos/HRA_part2/2356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white lab coat over a blue shirt and khaki pants, sneezes dramatically while working in a clean, well-lit laboratory filled with advanced technology and scientific equipment. The scene captures the unexpected moment as he leans over a workstation, his glasses momentarily fogging up, surrounded by computers and high-tech machinery, emphasizing the contrast between the precision of his work and the human element of a simple sneeze.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has uncoordinated movements."
}
] |
seed42_3043
|
videos/HRA_part0/3043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, attired in a crisp white shirt, black vest, and trousers, strolls through dense, lush green thickets, carrying an empty silver tray. The vibrant flora envelops him as he walks, the sunlight filtering through the leaves creating a dappled effect on his path. The setting, reminiscent of an English garden, is filled with various plants and trees, providing a rich, textured backdrop for his leisurely walk. Despite the wild surroundings, the waiter maintains a professional demeanor, his attire and posture suggesting a formal occasion amidst nature's embrace.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2525
|
videos/HRA_part0/2525.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sci-fi setting, a large moose, adorned with a futuristic, glowing harness, stands calmly beside a colossal space elevator. The moose is being gently caressed by a figure dressed in a spacesuit, creating an unexpected yet tender moment between species. The vastness of space looms overhead, with stars and distant galaxies visible, contrasting with the intimate interaction on the ground. The space-suited individual continues to stroke the moose affectionately, while the majestic animal remains serene, its eyes reflecting curiosity and trust in this otherworldly encounter.]"
},
{
"from": "gpt",
"value": "Normal. The moose's head, harness, and hands in the video have generation issues, with the hands disappearing in the middle frames."
}
] |
seed44_2940
|
videos/HRA_part1/2940.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its wings outstretched, revealing a span of at least six feet. It glides effortlessly over a rugged mountainous landscape, the peaks dusted with snow against the vibrant backdrop of a pine forest. The eagle's piercing yellow eyes remain fixed ahead, while its sharp, curved beak points skyward. Its powerful talons are visible beneath its body, ready to snatch prey from the ground or water below. The sunlight reflects off its brown and white plumage, highlighting the intricate feather patterns as it navigates the thermals with regal poise.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1215
|
videos/HRA_part0/1215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stethoscope around her neck and a name badge on her scrubs, speaks earnestly with a concerned patient in a hospital room. The nurse, with her brown hair pulled back into a bun, leans forward attentively, making direct eye contact, while holding a clipboard with medical records. Moments later, she smiles warmly, offering reassurance and hope, as she continues the conversation. Throughout, the setting remains within the sterile, yet comforting environment of the hospital room, with machines beeping softly in the background.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2329
|
videos/HRA_part0/2329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow vest and hard hat, stands in awe, experiencing time dilation as he watches a kangaroo jump in slow motion against a backdrop of a bustling city skyline at sunset. The kangaroo, mid-leap, appears weightless and graceful, its powerful hind legs propelling it forward. The worker's expression reflects a mix of surprise and fascination, as if witnessing a surreal moment where the laws of physics seem to bend. The scene is bathed in golden hour light, adding to the dreamlike quality of the encounter.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2063
|
videos/HRA_part0/2063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 teacher, wearing a green shirt and khaki pants, stands in a classroom filled with educational posters and bookshelves, holding a small hippopotamus toy. Behind her, a large window reveals Saturn's majestic rings in the distance, dominating the sky. The teacher gently tosses the hippo into a clear, indoor swimming pool, where it floats on the water's surface, creating ripples. The room is illuminated by soft, warm lighting, casting a serene atmosphere over the unique combination of elements.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1713
|
videos/HRA_part0/1713.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a dark jacket and casual attire, steps out of a modern building into the urban night, holding a black garbage bag. He approaches a large, industrial dumpster under the dim glow of streetlights, surrounded by concrete walls and parked cars. As he lifts the dumpster lid, his directorial composure contrasts with the mundane task of disposing waste. The scene captures the unexpected juxtaposition of creative leadership and everyday chores, highlighting the director's relatable human side amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, face, and legs of the character in the video are twisted and deformed."
}
] |
seed46_1737
|
videos/HRA_part2/1737.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, wearing a brown jacket and khaki pants, sits on a wooden chair in a spacious, empty room with high ceilings and large windows, stitching a button onto his garment with a look of intense concentration. The button, which matches the color of his jacket, is being sewn back on with a strong thread, as the man holds the fabric taut with his free hand. The room is bathed in soft, natural light, casting gentle shadows across the floor and highlighting the dust motes that dance in the air. The janitor's face is set in a serious expression, his brow furrowed in determination as he carefully guides the needle through the fabric, ensuring the button is securely fastened. Behind him, a row of neatly arranged brooms and cleaning supplies stand against the wall, a testament to his hard work and dedication to keeping the space clean and orderly.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's hand in the video has generation issues, with the line in their hand suddenly disappearing or reappearing in middle frames."
}
] |
seed44_1757
|
videos/HRA_part1/1757.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman wearing a green tank top and khaki shorts is playfully running in a spacious, grassy area under a clear blue sky, with a koala perched on her back. The koala, clinging to her shoulder, is holding a branch, adding a touch of whimsy to the scene. The woman's joyful expression and the koala's relaxed demeanor create a harmonious and delightful moment, encapsulating the essence of carefree fun and the unexpected companionship between human and animal.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs in the video have issues, her fingers are not fully generated, and her face is blurry. The koala's limbs are missing, and its facial features are not generated."
}
] |
seed44_3062
|
videos/HRA_part1/3062.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a thoughtful writer sits at a cluttered desk, typing away on a laptop with determination. Suddenly, the scene focuses on a small vole, its fur a mix of brown and gray, crawling out from beneath the wooden desk. The rodent explores its surroundings, nibbling on a pencil and climbing onto a pile of books, all while the writer continues to work, seemingly unaware of the tiny creature's presence.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the vole's movements are uncoordinated, and the writer's typing does not have obvious problems."
}
] |
seed44_185
|
videos/HRA_part1/185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, clad in a casual black jacket and gray trousers, runs energetically across a large, open room within a space-themed educational facility. The room is adorned with detailed models of the Apollo spacecraft and other historical rockets, highlighting the center's focus on space exploration. As he moves, the director passes by a group of attentive students seated at tables, each engaged with interactive exhibits about space missions. The vibrant atmosphere reflects the excitement and educational value of the space center, emphasizing its commitment to inspiring the next generation of astronauts and scientists.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3136
|
videos/HRA_part0/3136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a red astronaut suit with gold accents, crawls across a rocky Martian landscape as a vibrant orange and red sunset illuminates the horizon. The chef's outfit includes a matching helmet, which reflects the dramatic sunset, and a tool belt filled with cooking utensils. The rocks beneath him are various shades of brown and red, typical of Mars' surface, while the distant mountains and sandy dunes complete the alien yet stunning scenery. Despite the harsh environment, the chef's determination to explore and perhaps cook under the unique conditions of Mars is evident.]"
},
{
"from": "gpt",
"value": "Normal. The chef in the video moves basically normally, with slight awkwardness."
}
] |
seed42_1720
|
videos/HRA_part0/1720.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large grouper fish, displaying a mottled brown and white skin pattern, swims serenely in clear blue waters, its wide mouth and curious eyes prominent. It passes by a vibrant coral reef, home to smaller, colorful fish darting in and out of the crevices. The sunlight filters through the water, casting dappled light on the sandy ocean floor and highlighting the intricate details of the grouper's body and its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the grouper's mouth in the video is problematic."
}
] |
seed42_1489
|
videos/HRA_part0/1489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished chef, donning a pristine white apron and cap, walks barefoot on a serene, sandy beach, with the sun casting a warm glow over the calm sea. He holds a large, colorful fish in his hands, a symbol of fresh ingredients, while the beach's natural beauty, including lush greenery and clear skies, provides a stunning backdrop. The chef's attire, complete with the traditional uniform, contrasts beautifully with the relaxed coastal setting, highlighting his connection to nature and the source of his culinary inspiration.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3153
|
videos/HRA_part0/3153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a brown jacket and blue jeans, walks along a wooden path near a lake, holding a green notebook. An otter swims in the foreground, its head occasionally popping up from the water, mirroring the writer's pace. The writer stops, looking thoughtful, then continues walking, passing a wooden post and a tree with orange leaves, suggesting an autumn day. The otter follows suit, diving under the water and reappearing alongside the writer, who now looks down at the playful creature, sharing a moment of connection in nature.]"
},
{
"from": "gpt",
"value": "Normal. The otter's movements in the video are not smooth."
}
] |
seed46_3048
|
videos/HRA_part2/3048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a traditional white uniform and cap, takes a break from her medical duties to paint a hospital room a soothing shade of light blue. Holding a paintbrush in her gloved hand, she carefully applies the paint to the wall, creating a fresh and welcoming environment for the patients. The room is brightly lit, with medical equipment neatly arranged on a side table, and a window letting in natural light, casting a warm glow on the freshly painted walls. The nurse's dedication to improving the space highlights her commitment to patient care beyond her regular responsibilities.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2286
|
videos/HRA_part1/2286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a black beret and glasses, is seen in a studio filled with vibrant paintings and art supplies. He exhibits a range of emotions, from frustration to determination, as he shakes his head vigorously. Against the backdrop of a vividly painted wall, the artist's movements are exaggerated, emphasizing his passionate engagement with his craft. His expressive face and animated gestures convey the intensity of his creative process, offering a glimpse into the emotional rollercoaster of artistic expression.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1497
|
videos/HRA_part1/1497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college-aged male student, wearing a grey jacket and blue jeans, is crawling along a grassy path on a university campus, surrounded by trees and foliage indicative of early autumn. The scene opens with him crawling under a wooden park bench, suggesting playful or unusual behavior. Next, he crawls beneath the low-hanging branches of a tree, highlighting his determination or whimsy. Then, he crawls across a stone walkway, the textured stones providing a tactile contrast to the grass. Finally, he crawls through a tunnel formed by intersecting tree branches, the dappled sunlight creating a dynamic interplay of light and shadow on his form.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2911
|
videos/HRA_part2/2911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casual outfit of a gray sweater and blue jeans, sits cross-legged on a wooden floor inside a cozy room, surrounded by bookshelves. In front of her is a small, curious hedgehog, slowly crawling across a white towel, exploring its immediate environment with keen interest. The student watches the hedgehog intently, her face a mix of fascination and care, as she gently interacts with the animal, creating a heartwarming scene of connection between human and nature indoors.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, hands are distorted, and the hedgehog's face is distorted."
}
] |
seed42_1469
|
videos/HRA_part0/1469.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow high-visibility jacket, blue jeans, and brown work boots, walks purposefully near a yellow Bobcat excavator, which is positioned on a building site filled with sand and dirt. The excavator boasts a wide bucket and sits on the sandy terrain of the lot, while the worker strides with determination, hard hat in hand, past the heavy machinery, embodying the industrious spirit of a bustling worksite.]"
},
{
"from": "gpt",
"value": "Normal. The character's arms and legs are twisted."
}
] |
seed42_2237
|
videos/HRA_part0/2237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, majestic tuna fish glides through the crystal-clear waters of the ocean, its sleek silver body cutting through the water with grace and power. The sunlight filters down from the surface above, casting shimmering patterns across the tuna's scales. Schools of smaller fish scatter in its path, the tuna's presence commanding respect in the underwater realm. In the distance, the silhouette of a reef can be seen, adding depth and context to the tuna's aquatic habitat. The video captures the tuna from various angles, showcasing its size and strength as it navigates its natural environment with ease.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the reef generation."
}
] |
seed42_2489
|
videos/HRA_part0/2489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative juxtaposition, a male cashier, clad in a gray shirt and black pants, is seen sprinting energetically across a vast, open space, reminiscent of a track field. Behind him, an enormous screen displays a stunning, high-definition image of Jupiter's iconic Great Red Spot, creating a surreal and captivating visual contrast between the terrestrial and the celestial. The cashier's focused expression and determined stride add a sense of urgency and dynamism to the scene, while the imposing presence of the gas giant's storm serves as a dramatic and awe-inspiring backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1385
|
videos/HRA_part1/1385.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a whole, raw Atlantic cod fish, eyes glassy and intact, laid upon a bed of ice chips, its skin shimmering under bright market lights. The fish is sizable, with a length suggesting it weighs several pounds, and is presented head-on, showcasing its freshness in a fishmonger's display. The setting is a bustling, open-air market, with other seafood visible in the background, emphasizing the variety and vibrancy of the scene. The cod's mouth is slightly agape, and its body lies across the ice, evoking the traditional presentation of fresh catches in coastal communities.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1144
|
videos/HRA_part1/1144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vibrant kitchen filled with the warm glow of overhead lights, a diverse group of four people, two women and two men, collaborate on preparing a feast. One woman, wearing a patterned apron over a floral dress, chops vegetables on a wooden cutting board placed on a granite countertop. Beside her, a man in a chef's jacket stirs a large pot on a professional stove, steam rising from the simmering contents. Another woman, donning a red bandana and denim jacket, carefully seasons a dish with herbs and spices, while the last man, clad in a checkered shirt, monitors the grill, flipping sizzling meats with tongs. The atmosphere is lively, with laughter and clinking utensils adding to the sense of camaraderie and shared purpose among the cooks.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_223
|
videos/HRA_part2/223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 station interior resembling a bank, a muscular firefighter, now a space hero, crawls through a narrow air duct lit by blue emergency lights. Dressed in a high-tech firefighting suit with a red helmet, he stealthily moves forward on a mission. He continues crawling, his gear and determination evident, as the dimly lit vent and complex machinery surround him. Suddenly, the focus is on his intense face, showcasing his resolve through the visor of his helmet, as he prepares for action. Lastly, our hero is seen in a crouched position, ready to leap into danger, his advanced firefighting equipment at the ready, within the confined space of the air duct.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, legs, and arms."
}
] |
seed42_3098
|
videos/HRA_part0/3098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest environment, two individuals wearing khaki safari outfits are seen running alongside a chimpanzee, engaged in playful interaction. The scene is vibrant and full of life, with the humans and the chimpanzee moving together in harmony. They dash across a dirt path, surrounded by dense vegetation, as the chimpanzee exhibits its natural agility and strength. The trio's energetic run is captured in high detail, highlighting the dynamic movement and the unique bond between humans and this primate in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_3201
|
videos/HRA_part2/3201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, attired in a red jacket and black leggings, runs across a barren desert landscape, with a lone coyote mirroring her movements at a distance. The woman's clothes flap in the wind as she sprints, her eyes fixed ahead, determined. Meanwhile, the coyote, its sandy fur blending with the surroundings, lopes alongside, its gaze following the woman's every stride. The two continue their parallel race, the woman's red jacket and the coyote's silhouette stark against the vast, sandy terrain, under a wide, cloud-dotted sky.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1972
|
videos/HRA_part1/1972.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a gray spacesuit with a NASA logo, is seen running energetically across the barren, rocky landscape of a distant planet, with a large, complex space station visible in the background. His movements are dynamic, showing determination and purpose. The vast, alien terrain, dotted with craters and boulders, stretches out behind him, while the dimly lit space habitat, complete with solar panels and satellite dishes, looms large. The janitor's spacesuit bears a name tag and various patches, adding to the realism of this futuristic scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_258
|
videos/HRA_part2/258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate female veterinarian, wearing a white lab coat and blue scrubs, gently feeds a small dog from a spoon, her caring nature evident in her warm smile. The clinic room is clean and modern, with stainless steel equipment and a large window providing natural light. Behind her, a poster about pet nutrition hangs on the pale green wall. On a nearby table, various pet food samples are neatly arranged, emphasizing the importance of proper animal care. Throughout the scene, the vet's loving interaction with the dog highlights her dedication to animal welfare.]"
},
{
"from": "gpt",
"value": "Normal. The doctor and the dog's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed44_2082
|
videos/HRA_part1/2082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 chef, wearing a traditional white uniform and a tall hat, finds himself in an unexpected encounter with a bobcat. They stand on a dirt path winding through a dense forest, the sunlight filtering through the trees casting dappled shadows on the ground. The chef, holding a basket presumably filled with fresh ingredients, looks surprised yet calm as he meets the gaze of the wild feline. The bobcat, equally intrigued, pauses in its walking, standing tall on the path, its ears perked and tail swishing gently, as if acknowledging the chef's presence in its natural habitat. The two share a moment of mutual respect and curiosity before continuing on their respective paths, the chef moving forward with purpose and the bobcat melting back into the underbrush, both figures disappearing into the lush greenery of the forest.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1040
|
videos/HRA_part2/1040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene set against the backdrop of a bustling harbor, a snake charmer dressed in traditional attire, complete with a red turban and colorful vest, plays an enchanting melody on his pungi. The cobra, coiled and alert, rises from its basket, swaying hypnotically to the music under the golden glow of the setting sun. The charmer's skilled hands guide the snake into a mesmerizing dance, captivating the audience gathered around the harbor, where boats gently rock in the water and seagulls circle overhead. The cobra's movements, synchronized with the charmer's music, create a powerful display of control and grace against the maritime setting.]"
},
{
"from": "gpt",
"value": "Normal. The cobra's dancing movements in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed44_174
|
videos/HRA_part1/174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest setting, a mature monkey tenderly caresses a smaller monkey, possibly its child, against a backdrop of vibrant foliage and dappled sunlight. The older monkey, with a fur color that appears dark brown or black, gently holds the smaller monkey, whose fur is lighter in color, perhaps blonde or sandy. The interaction is intimate and caring, with both monkeys seated on a branch amid the dense vegetation. This heartwarming scene captures the essence of primate affection in their natural habitat, surrounded by the rich textures and colors of the forest environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2805
|
videos/HRA_part2/2805.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy blue uniform with a badge and name tag, stands tall on a bustling city sidewalk, holding a walkie-talkie in his right hand. Behind him, a busy street scene unfolds, complete with pedestrians, traffic, and urban architecture. The officer's authoritative stance and alert demeanor convey a sense of duty and readiness, embodying the role of law enforcement in the heart of the city. His left hand rests on his belt, which holds various tools of his trade, while his eyes survey the surroundings with watchful vigilance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1309
|
videos/HRA_part1/1309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous firefighter, clad in full gear and a yellow fire-resistant jacket, leads a calm brown horse into a shallow, clear lake during a sunny day. The firefighter gently guides the horse, which is adorned with a red blanket, into the water. Both the firefighter and the horse are knee-deep in the refreshing lake, surrounded by lush greenery and a peaceful environment, creating a heartwarming and unexpected scene of tranquility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1981
|
videos/HRA_part0/1981.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast 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 chefs in white mentioned in the caption are not shown preparing meals in the video."
}
] |
seed42_2193
|
videos/HRA_part0/2193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman with brown hair tied back in a ponytail, wearing a gray cardigan over a white blouse and jeans, meticulously dusts furniture in a classroom. She moves with precision, her facial expression one of concentration. The room is filled with sunlight, illuminating the specks of dust floating in the air. She pauses for a moment, her hands on her hips, surveying her work before continuing. The classroom is mostly empty, save for a few desks and chairs, giving the impression of a quiet, orderly space. Throughout the scene, she remains focused on her task, her movements deliberate and efficient.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2968
|
videos/HRA_part0/2968.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic grouse, distinguished by its brown plumage speckled with white and black, struts proudly across a lush, green meadow under a bright, sunlit sky. The bird's robust body, complete with a red wattle above its beak, is prominently displayed as it moves with regal confidence. Moments later, it's seen in profile, its intricate feather patterns and textured wings highlighted against the vibrant vegetation. Then, it turns its head, revealing piercing eyes and a sharp beak, set against the backdrop of a dense forest and clear blue sky. Lastly, the grouse is captured mid-stride, its legs moving swiftly, demonstrating the strength and agility of this woodland creature, all set against a serene natural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the grouse walking on the grass, but the movements are not very continuous and smooth."
}
] |
seed44_2355
|
videos/HRA_part1/2355.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman in a yellow swimsuit, adorned with a floral-printed headscarf, laughs joyously as she swims in a clear blue pool, surrounded by lush greenery. Accompanied by a playful golden retriever, who energetically paddles alongside her, they both exude pure delight. The woman's infectious laughter and the dog's wagging tail encapsulate the essence of their shared aquatic adventure, set against a backdrop of swaying palm trees and bright sunlight filtering through the leaves, casting dappled shadows on the water's surface.]"
},
{
"from": "gpt",
"value": "Normal. The woman's face and hands in the video have generation issues."
}
] |
seed46_1815
|
videos/HRA_part2/1815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 opens with a koala, typically terrestrial, surprisingly adept in water, swimming in a serene, clear blue pool. Its brown fur glistens as it paddles with determination, showcasing an unexpected talent. The koala, wearing a small yellow swim cap, navigates the water with surprising grace, its limbs moving rhythmically. Moments later, it emerges from the pool, shaking off droplets, revealing a cozy green towel wrapped around its body. The koala then sits on the edge of the pool, seemingly pleased with its aquatic adventure, the sunlight sparkling on the water behind it.]"
},
{
"from": "gpt",
"value": "Bad. The koala's body is twisted, its arms are twisted, its claws are twisted, and its face is distorted."
}
] |
seed44_175
|
videos/HRA_part1/175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space medical facility, a man wearing a clean, white lab coat and blue surgical mask diligently wipes down advanced, high-tech equipment with precision and care. The room is illuminated by soft, ambient lighting, highlighting the sterile environment. The man's focused gaze and meticulous movements convey a sense of professionalism and dedication to maintaining the cleanliness of the facility. Around him, the walls are lined with monitors and medical devices, emphasizing the cutting-edge technology used in this extraterrestrial healthcare setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_313
|
videos/HRA_part1/313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished male doctor, wearing a white lab coat over a navy blue shirt, khaki pants, and brown shoes, meticulously dusts antique furniture in a well-lit room with large windows. He carefully cleans a wooden dresser, revealing the care and attention to detail he applies to his task. The doctor then moves to dust a vintage chair, his movements deliberate and focused, showcasing his commitment to maintaining the cleanliness of his surroundings. Throughout the scene, the doctor's attire remains impeccable, underscoring the contrast between his professional role and the domestic activity he performs.]"
},
{
"from": "gpt",
"value": "Bad. Failed to generate brown shoes."
}
] |
seed46_1477
|
videos/HRA_part2/1477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating scene, a distinguished film director, clad in a black jacket, blue jeans, and brown boots, stands on a rocky outcropping, passionately directing the action. Nearby, an agile ibex leaps over a boulder with remarkable grace, its brown fur and curved horns vivid against the craggy landscape. The camera focuses on the ibex mid-jump, capturing the animal's strength and agility, while the director observes intently, his silhouette framed against the dramatic mountain scenery.]"
},
{
"from": "gpt",
"value": "Normal. The sheep's movements are not smooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.