video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1739
|
videos/HRA_part1/1739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a deer, with its fur glistening under the sunlight, leaps gracefully over a cash register, which is placed in an unexpected outdoor setting. The animal's movements are fluid and effortless as it clears the register, symbolizing a moment of nature intruding upon the human world. The cash register, typically found indoors, is now situated among lush greenery, with the deer's leap adding an element of surprise and magic to the encounter.]"
},
{
"from": "gpt",
"value": "Bad. The deer's limbs are partially missing in the video, the tail is not generated, and there are issues with the eyes and antlers."
}
] |
seed42_1594
|
videos/HRA_part0/1594.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park, a dedicated zookeeper clad in khaki shorts, a gray T-shirt, and a cap runs along a path lined with palm trees, demonstrating his commitment to fitness within the serene surroundings. The camera captures him passing by enclosures housing various animals, highlighting the unique setting of his workout. As he jogs, the peaceful atmosphere of the park is evident, with glimpses of giraffes, elephants, and monkeys in the background, creating a vivid contrast between human activity and the natural world.]"
},
{
"from": "gpt",
"value": "Bad. No giraffes, elephants, or monkeys were generated."
}
] |
seed42_2179
|
videos/HRA_part0/2179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a dark green winter jacket, gray gloves, and a matching hat, diligently shovels snow from a pathway in front of a red-brick building with a yellow door. Snowflakes continue to fall gently, accumulating on the ground and surrounding trees. The man, with a serious yet focused expression, works methodically, clearing the path section by section. His breath visible in the cold air, he pauses momentarily, looking up at the sky as if assessing the weather conditions, before resuming his task with renewed determination.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1964
|
videos/HRA_part0/1964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial markings and red tail feathers is perched on a branch, set against a blurred background of lush vegetation. The parrot, with its bright plumage and attentive expression, looks directly at the camera. It then opens its beak slightly, as if about to call out, showcasing its sharp, curved beak. The bird's stance on the branch, combined with its detailed feathering and colorful features, creates a captivating scene in the midst of a dense, verdant forest.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1068
|
videos/HRA_part1/1068.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An astronaut engineer, clad in a white spacesuit with a NASA logo, embarks on a critical space rescue mission, crawling through narrow, illuminated corridors inside a damaged spacecraft. The engineer's gloved hands and boots equipped with magnetic soles are prominent as they navigate the confined space. The scene is set against the backdrop of the Earth and stars, visible through a small porthole, emphasizing the perilous nature of the mission. Throughout, the engineer's determination and focus are evident as they work diligently to repair the vital systems of the stranded spaceship.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video has disproportionate limbs."
}
] |
seed44_1753
|
videos/HRA_part1/1753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attorney, wearing a dark suit and carrying a briefcase, walks through a desolate industrial park at dusk, under the glow of orange streetlights. He pauses to gently touch the rough surface of a concrete wall, his expression thoughtful. The scene shifts to show him seated on a bench, still in the industrial setting, now bathed in the blue hour light, as he caresses the worn wooden slats, deep in thought. Throughout, the juxtaposition of the lawyer's polished appearance against the gritty industrial backdrop highlights the unusual intimacy of his actions.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1047
|
videos/HRA_part1/1047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 seasoned farmer, wearing a white shirt, blue overalls, and a wide-brimmed hat, stands in a lush green field under a clear blue sky. He is in mid-throw, tossing hay bales with ease, his strong arms and focused expression showcasing his expertise. The hay bales are wrapped neatly in plastic, indicating a modern farming technique. The farmer's stance, with one leg forward for balance, adds dynamism to the scene, while the rolling hills and distant trees provide a picturesque rural backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's hand proportions in the video are abnormal, and there is no direct contact with the hay bale before the throwing action."
}
] |
seed44_2951
|
videos/HRA_part1/2951.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, donning a wide-brimmed hat and a brown leather vest, finds himself amidst a cosmic dust storm, its ethereal particles swirling around him like a celestial sandstorm under the night sky. Suddenly, the scene transforms to reveal the farmer diving into a tranquil oasis, the water shimmering with stardust from the storm, as he swims gracefully beneath the sparkling surface, encapsulating a surreal blend of earthy resilience and otherworldly enchantment.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's face and hands are distorted in the video."
}
] |
seed42_2986
|
videos/HRA_part0/2986.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful nurse wearing a green uniform jumps playfully over a fallen log in the lush rainforest, surrounded by vibrant green foliage, exotic flowers, and towering trees. She lands gracefully on the moss-covered ground, her smile conveying a sense of freedom and joy. Nearby, a small waterfall cascades into a crystal-clear pool, adding to the serene atmosphere of the tropical environment. The nurse's unexpected presence in the rainforest, combined with her playful leap, creates a captivating and memorable scene.]"
},
{
"from": "gpt",
"value": "Bad. The jumping action of the character in the video is not smooth."
}
] |
seed44_1952
|
videos/HRA_part1/1952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 young female cashier with a name tag, wearing a yellow shirt and black pants, is playfully jumping over a small, live hamster on the floor of a convenience store, capturing a lighthearted moment during her shift. The hamster, seen from above, scurries across the checkered floor, adding to the unexpected and amusing interaction. The cashier, still mid-jump, is framed by shelves of beverages and snacks, creating a surreal yet charming atmosphere in the store aisle. The scene is set under the bright lights of the shop, highlighting the unusual encounter between the employee and the tiny rodent.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_219
|
videos/HRA_part2/219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An endearing otter, with its distinct brown fur and charming face, sits on a wooden boardwalk, creating an unusual yet captivating scene. It reaches out with its paw, seemingly caressing the surface of the weathered wood, as if cherishing a familiar touch. The otter's playful demeanor and the texture of the boardwalk combine to form a narrative of unexpected encounters and gentle interactions in a natural yet built environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1942
|
videos/HRA_part1/1942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male chef, donning a traditional white chef's uniform with a name tag reading \"Chef Tyler,\" sits at a wooden table in a rustic, candlelit dining room. He savors a spoonful of his signature dish, a creamy risotto, with eyes closed in blissful concentration. His neatly trimmed beard and mustache, along with short brown hair, add to his distinguished appearance. Behind him, a bustling restaurant kitchen is visible through an open doorway, offering a glimpse into the energetic culinary environment. Throughout the scene, Chef Tyler continues to enjoy his meal, occasionally glancing up with a satisfied smile, embodying the essence of a passionate and accomplished chef relishing his own creation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1604
|
videos/HRA_part2/1604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a gray T-shirt and dark green shorts, carefully loads dishes into a stainless steel dishwasher in a modern kitchen. The room is brightly lit, casting clear shadows and revealing the intricate details of the kitchen, including the tile backsplash and granite countertops. The student, with short brown hair and glasses, methodically organizes the plates, bowls, and silverware, demonstrating responsibility and attention to detail. Throughout the process, the student maintains a focused demeanor, occasionally pausing to ensure each item is securely placed, all within the well-lit, contemporary kitchen environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2700
|
videos/HRA_part2/2700.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest setting, a majestic gray wolf gently caresses a smaller, white wolf with its nose, demonstrating a tender moment of affection between the two creatures. The gray wolf, with piercing yellow eyes, a thick, shaggy coat, and a muscular build, leans its head down to touch noses with the smaller white wolf, which looks up with a similar intensity. Both wolves are standing in a grassy clearing within the dense forest, surrounded by tall trees and patches of sunlight filtering through the leaves, creating a serene atmosphere for this intimate interaction.]"
},
{
"from": "gpt",
"value": "Normal. The gray wolf's eyes and mouth generation have issues, and the white wolf's mouth and eyes generation have issues."
}
] |
seed46_2674
|
videos/HRA_part2/2674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young college student, dressed in a green shirt, gray jacket, and khaki pants, walks through the bustling streets of a metropolis, passing by a glass office building with a reflection of the surroundings. Moments later, he continues his journey, navigating the urban landscape near a construction site with yellow barriers. He then crosses a busy street, dodging between pedestrians, cars, and a street sweeper. Finally, he reaches a subway station entrance, marked by a red canopy and illuminated signage, ready to descend into the underground network of the city.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1040
|
videos/HRA_part1/1040.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 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 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": "Bad. This person's hand is distorted, and the snake's head is twisted."
}
] |
seed42_3062
|
videos/HRA_part0/3062.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": "Good. No obvious issues."
}
] |
seed42_1872
|
videos/HRA_part0/1872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant nudibranch, adorned with striking orange and white hues, gracefully glides across a coral reef teeming with life. Its intricate body showcases an array of colors and textures, including bold orange patches and delicate white spots. The marine environment is rich with various shades of blue, green, and brown, providing a stunning contrast to the nudibranch's vivid appearance. Surrounding the scene are schools of tropical fish, their scales shimmering in the underwater light, while the reef's complex structure offers a mesmerizing backdrop to the creature's serene movement.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_307
|
videos/HRA_part0/307.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stark juxtaposition, a lone rhinoceros gallops across a barren landscape, its powerful form silhouetted against a backdrop of distant factories, their towering smokestacks reaching into the smoggy sky. The rhino's horn points forward determinedly as it runs, a symbol of resilience and strength in the face of industrial encroachment. Its muscular body strains against the weight of its own survival, each thundering step a testament to its enduring spirit. The factories, with their monolithic presence, stand as a reminder of the challenges faced by wildlife in an increasingly urbanized world. Yet, in this scene, the rhinoceros embodies a defiant hope, charging forward in a land where nature and industry collide.]"
},
{
"from": "gpt",
"value": "Normal. The rhinoceros's legs are twisted, and its face is distorted."
}
] |
seed42_2526
|
videos/HRA_part0/2526.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic giraffe, distinguished by its dark, jagged spots, gently caresses a smaller giraffe with its head, creating a tender moment in the midst of a lush, green savanna landscape. The taller giraffe, with a weathered face and long eyelashes, shows affection toward the younger one, which has lighter, less pronounced markings, standing against a backdrop of tall grasses and distant trees under a bright, sunny sky. This intimate scene captures the essence of giraffe behavior in their natural habitat, emphasizing the bond between two individuals against a vivid, verdant setting.]"
},
{
"from": "gpt",
"value": "Normal. The ears of the large giraffe were not generated, and there was an issue with the generation of the young giraffe's horns."
}
] |
seed42_161
|
videos/HRA_part0/161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, cosmic library filled with floating bookshelves and galaxies in the background, a majestic lion, adorned with a golden collar and a serious expression, is seen wiping the dust off ancient books with a delicate paw. The shelves are stocked with books of all sizes, and the lion moves between them, engaged in the meticulous task of cleaning. Surrounded by the grandeur of space and knowledge, the lion continues its duty, highlighting the serene yet awe-inspiring setting.]"
},
{
"from": "gpt",
"value": "Bad. The lion's movements in the video are not smooth and uncoordinated."
}
] |
seed44_1296
|
videos/HRA_part1/1296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 female worker sits on a wooden chair under the shade of a tree, knitting a long, colorful scarf with red, green, and yellow yarns. She wears a simple cotton dress and sandals, her hair tied back in a bun. The scene is set in a small courtyard surrounded by lush greenery and blooming flowers, with sunlight filtering through the leaves, casting dappled shadows on the ground. The woman's hands move deftly, the knitting needles clicking together in a steady rhythm, as she focuses intently on her work, occasionally glancing up to enjoy the peaceful surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2323
|
videos/HRA_part1/2323.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, identifiable by his gray lab coat over a casual button-up shirt and jeans, gently bathes a small, fluffy white dog in an elevated washbasin typically used for washing cars. The scene is set outdoors, with the dog standing on its hind legs, paws on the basin's edge, and the engineer tenderly pouring water over its head from a white jug. The engineer's caring demeanor contrasts with his professional attire, creating a heartwarming image of an unexpected task being performed with love and care.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and face are distorted in the video, as well as the dog's legs and face."
}
] |
seed44_1186
|
videos/HRA_part1/1186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a weathered wooden fence post, its distinctive black-and-white plumage gleaming under the soft sunlight. Against a backdrop of lush green foliage and clear blue skies, the bird's eyes sparkle with curiosity. It tilts its head to the side, seemingly observing its surroundings with interest. The vibrant colors of nature serve as a striking contrast to the magpie's striking feathers, highlighting its unique beauty in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1362
|
videos/HRA_part0/1362.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a museum after hours, a diligent worker in a blue uniform shirt crawls under an exhibit, focusing on maintenance tasks. The exhibit features ancient Egyptian artifacts, including a sarcophagus and hieroglyphic panels, with spotlights illuminating the space. The worker's attire includes safety gear, like gloves and a helmet, emphasizing the cautious approach required for handling historical items. The dimly lit museum hall, filled with glass display cases and statues, provides a dramatic setting for the solitary figure working beneath the exhibition platform.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2693
|
videos/HRA_part0/2693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a helmet, walks alongside a majestic elephant, both navigating through a lush, green environment. The firefighter's equipment includes a heavy-duty jacket, pants, boots, and gloves, signifying readiness for any emergency. The elephant, adorned with intricate patterns on its body, suggests a cultural or ceremonial context. Together, they traverse a dirt path surrounded by dense vegetation, creating an unexpected yet compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1253
|
videos/HRA_part1/1253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant scene set within lush wetlands, several figures clad in elaborate costumes dance energetically, their movements synchronized in a captivating performance. The dancers wear colorful outfits adorned with feathers and intricate patterns, their faces painted in festive designs. The backdrop showcases the beauty of the wetlands, with tall reeds swaying gently in the breeze and waterfowl flying overhead. Sunlight filters through the clouds, casting a warm glow on the dancers as they leap and twirl, embodying the spirit of nature in their lively dance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1137
|
videos/HRA_part1/1137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant outdoor festival setting, two joyful people, a man in a red shirt and blue jeans, and a woman in a yellow dress, dance energetically near a food truck, while a cheerful crowd gathers in the background. The man wears a cap, and the woman has her hair in a bun. They are accompanied by a playful brown dog, who is also participating in the dance, leaping and spinning alongside them. The trio moves to the beat of lively music, surrounded by a diverse group of onlookers, all sharing in the festive atmosphere under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the legs are severely distorted, and the dog's body is seriously deformed."
}
] |
seed46_2987
|
videos/HRA_part2/2987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant floral-print dress over her swimsuit, stands before a majestic waterfall cascading into a serene pool. She joyfully leaps into the water, her dress fluttering in the breeze, revealing her red swimwear beneath. Emerging from the pool, she playfully splashes water, her laughter echoing through the lush, green surroundings. As she exits the frame, a panoramic view of the waterfall and its misty spray enveloping the tranquil pool takes center stage, offering a peaceful contrast to the nurse's lively energy.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2249
|
videos/HRA_part1/2249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a firefighter, dressed in full gear except for a red chicken hat, crawls through a dimly lit, misty hot springs area. The water reflects the ambient light, creating an ethereal glow around the unique character. Surrounded by the steamy, rocky landscape of the hot springs, the firefighter continues to crawl, adding an element of intrigue to the surreal setting.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's eyes and hands in the video have generation issues, with sudden changes in hand movements in the middle frames."
}
] |
seed44_1102
|
videos/HRA_part1/1102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a black jacket over a gray shirt and dark pants, is engaged in an intense scene where he skillfully catches a falling glass bottle with his right hand, displaying remarkable agility and precision. His focused gaze and the dynamic motion of the catch are highlighted against a dimly lit, gritty urban setting, adding to the dramatic effect of the moment. The scene is shot in high definition, capturing every detail of the actor's expression and the fluidity of his movements as he successfully intercepts the bottle mid-air.]"
},
{
"from": "gpt",
"value": "Bad. The hand of the character in the middle frame would suddenly disappear or appear."
}
] |
seed42_2671
|
videos/HRA_part0/2671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a grey suit, white shirt, and patterned tie, walks purposefully across a grassy field under a twilight sky, carrying a large, transparent bag. In the distance, a comet streaks across the night sky, its tail glowing brightly. The lawyer pauses, turning his head to gaze up at the celestial phenomenon, his expression a mix of awe and determination. Despite the extraordinary sight, he continues his steady walk, the comet's light illuminating his path forward.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer generated in the video has problems and does not conform to real-life scenarios."
}
] |
seed46_1460
|
videos/HRA_part2/1460.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful red fox, its fur thick and lustrous, stands at the edge of a steaming hot spring nestled in a lush, green forest. The water bubbles gently, releasing tendrils of mist that swirl around the fox, creating a mystical atmosphere. The fox dips its paw into the warm water, seeming to caress the surface, its eyes closed in apparent bliss. The steam rises from the hot spring, enveloping the fox in a soft, glowing haze, while the dense foliage and tall trees surrounding the clearing provide a serene and secluded setting.]"
},
{
"from": "gpt",
"value": "Normal. The red fox has uncoordinated movements."
}
] |
seed44_2250
|
videos/HRA_part1/2250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 male farmhand, clad in a white shirt and brown apron, gently caresses a small, fluffy yellow chick with a tender smile on his face, showcasing a moment of care and connection in a rural setting. The scene is set against a backdrop of wooden crates and greenery, highlighting the peaceful atmosphere of the farm. His hands, rough from labor yet gentle in touch, cradle the delicate creature, emphasizing the bond between man and nature.]"
},
{
"from": "gpt",
"value": "Normal. The movements of the chick and the farmer in the video are basically normal, but there is slight disharmony."
}
] |
seed42_1179
|
videos/HRA_part0/1179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown bear, standing on its hind legs on a wooden stage, wears a golden hat and a red bow tie, engaging in a whimsical dance under the spotlight. The stage is set against a dark, starry night sky, with the bear performing a series of playful dance moves, including a twirl and a playful wave to the audience, all while maintaining its costume of the golden top hat and red bow tie.]"
},
{
"from": "gpt",
"value": "Normal. The bear's body is twisted, the arms are twisted, the paws are twisted, the face is twisted, and the legs are twisted."
}
] |
seed42_2505
|
videos/HRA_part0/2505.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing elephant, adorned with vibrant red and gold patterns on its body, stands on one leg with its trunk gracefully curved upwards, embodying a joyful dance move. Against a rich, textured green jungle backdrop, the elephant's eyes sparkle with delight, its large ears slightly flared, and its tusks gleaming in the sunlight. Accompanied by smaller elephants in the background, also decorated in red and gold, the scene radiates a festive atmosphere, capturing the essence of an elephantine dance party in the lush, verdant surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The elephant's head, feet, and legs are twisted in the video."
}
] |
seed42_1977
|
videos/HRA_part0/1977.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kingfisher bird, vibrant in its electric blue plumage and orange breast, perches on a thin branch overhanging a tranquil pond, its sharp eyes intently scanning the water's surface. The sunlight filters through the leaves above, casting dappled light onto the bird and the water below. Suddenly, the kingfisher dives headfirst into the water, its body slicing through the calm surface with precision. It emerges a moment later, triumphant, a small fish wriggling in its beak. The bird then returns to its branch, ready to enjoy its catch, the water still rippling from its dive and the surrounding foliage swaying gently in the breeze.]"
},
{
"from": "gpt",
"value": "Bad. The kingfisher's claws were not fully generated, the eyes were not generated, and the head was missing at times."
}
] |
seed46_1205
|
videos/HRA_part2/1205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative director, wearing a stylish black jacket and jeans, stands on a futuristic space stadium podium, passionately explaining the grand vision for an intergalactic sporting event. Below, a peculiar sight unfolds: a capybara, donning a sleek silver spacesuit and a determined look, prepares for the ultimate cosmic challenge. The rodent athlete crouches, ready to spring into action, against the backdrop of a vibrant, neon-lit cosmic arena, filled with alien spectators. The capybara leaps high into the air, propelling itself with incredible force, while the director watches intently from above, his eyes fixed on this extraordinary spectacle unfolding under the dazzling lights of the space stadium.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1334
|
videos/HRA_part0/1334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is presented on a clean, white plate, its textured surface and irregular shape contrasting against the smooth, pristine background. The fish's left side faces upward, revealing its distinct dark brown coloration on top and lighter underside. Its eyes are both positioned on the darker left side, glistening and intact, indicating its freshness. The halibut's skin bears a natural pattern of spots and lines, and its mouth is slightly open, showing its small teeth. The setting is simple and unadorned, allowing the fish to be the focal point, perfect for a culinary or educational video feature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2022
|
videos/HRA_part0/2022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a brown plaid shirt and blue jeans, stands in the shallow end of a clear blue swimming pool, looking curiously at a squirrel perched on the edge. The squirrel, standing upright on its hind legs, holds a nut in its paws and peers intently into the water. Sunlight filters through the leaves of nearby trees, casting dappled shadows on the pool's surface and the green grass surrounding it. The farmer, with a straw hat tilted back on his head, seems to share a moment of mutual interest with the bushy-tailed creature, both pausing in their day's activities.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2860
|
videos/HRA_part1/2860.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown mouse, with large ears and a long tail, crawls across a wooden surface, its movements quick and cautious. The mouse pauses momentarily, its nose twitching as it sniffs the air, before continuing on its path. The texture of the wood grain is visible beneath the mouse's tiny feet, which grip the surface as it navigates its environment. The scene is captured in high definition, allowing every detail of the mouse's fur and the wooden surface to be seen clearly. The background is a soft, neutral tone, ensuring the focus remains on the mouse as it crawls.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1353
|
videos/HRA_part1/1353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lone kangaroo stands in a vast, sunlit Australian outback, its shadow cast long on the sandy ground. It lifts a paw to its face, wiping it in a human-like gesture, its fur ruffled by a gentle breeze. The kangaroo's expressive face, with large, curious eyes, focuses intently as it performs this action, its body language conveying a sense of self-awareness. Behind it, the outback stretches to the horizon, dotted with scrub and sparse vegetation, creating a stark contrast to the active, sentient creature in the foreground.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2831
|
videos/HRA_part2/2831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a costumed musician, dressed in a vibrant green hippopotamus outfit, gracefully crawls across a dimly lit stage. The stage is adorned with a red velvet curtain, adding a touch of drama. The musician's movements are slow and deliberate, almost balletic, as they crawl with an air of performance art. The costume is complete with oversized hippo ears and a large, friendly smile, creating a surreal and captivating visual display.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2751
|
videos/HRA_part1/2751.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 street worker in Shanghai, wearing a green vest and holding a broom, gently caresses the concrete surface as he meticulously sweeps the city sidewalk. Behind him, a bustling urban landscape unfolds, with high-rise buildings, neon signs, and the occasional passerby, all set against the backdrop of a vibrant metropolis. The worker's focused gaze and the tender touch of his broom on the pavement convey a sense of care and routine amidst the dynamic energy of Shanghai's streets.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's head, fingers, and feet, as well as the broom in hand, are generated with problems."
}
] |
seed46_3159
|
videos/HRA_part2/3159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed man, wearing a dark gray t-shirt, sits at a wooden table in a dimly lit room with yellow walls and a red ceiling. He lifts a glass of water to his lips, pausing to drink. His gaze is directed away from the camera, towards another person sitting across from him. The atmosphere is relaxed and intimate, with the man's simple attire and the warm, homey setting creating a sense of comfort and familiarity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1944
|
videos/HRA_part2/1944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 silverback gorilla is depicted in a dense, lush forest, illuminated by patches of sunlight filtering through the canopy. Initially, it stands powerfully on all fours, its muscles rippling under its dark fur. It then charges forward, running with a burst of energy, showcasing its strength and agility. The gorilla's movement is captured in a series of dynamic poses, highlighting its powerful build and the determination in its eyes, set against the vibrant greenery of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2741
|
videos/HRA_part0/2741.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating male musician, clad in a brown leather jacket, blue shirt, and black pants, gently caresses his acoustic guitar while sitting on a wooden bench. Surrounded by lush, green ferns and towering trees in a dense forest, he looks down at his instrument with a serene smile. The scene is illuminated by the soft glow of sunlight filtering through the foliage, casting dappled shadows on the mossy ground. The musician's tender touch and loving gaze convey a deep connection with his guitar, set against the serene backdrop of nature's splendor.]"
},
{
"from": "gpt",
"value": "Normal. The fingers of the male musician in the video have generation issues."
}
] |
seed44_149
|
videos/HRA_part1/149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, clad in a tailored gray suit, white shirt, and striped tie, rearranges furniture in a sophisticated office space. Initially, he thoughtfully observes the room, considering the layout. Then, he pushes a modern desk aside, revealing a keen eye for design. Next, he skillfully pulls a sleek office chair into place, demonstrating attention to detail. Finally, he stands back, hands on hips, surveying his newly organized workspace with satisfaction, the room's minimalist decor and natural light enhancing the professional atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The chair and the character's hand suddenly appear in the middle of the video, and there are issues with the generation of the character's face and hand."
}
] |
seed44_2939
|
videos/HRA_part1/2939.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a bobcat, with distinctive ear tufts and a short tail, leaps over a checkout counter in slow motion, its muscles tensing and releasing with each bound. The cash register, with its glowing display and scattered coins, provides context to the setting. The cashier, wearing a red apron and a surprised expression, watches the wild cat jump, creating an unexpected and captivating moment. The bobcat's leap is captured in mid-air, highlighting its agility and grace, against the backdrop of a typical supermarket checkout area.]"
},
{
"from": "gpt",
"value": "Bad. The sable's movements in the video are not smooth."
}
] |
seed42_2813
|
videos/HRA_part0/2813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, stands next to a large, brown buffalo with a red saddle. The officer gently wipes the buffalo's face with a white cloth, showing care and attention. The scene takes place in a rural setting, with wooden fences and green fields stretching into the distance. The buffalo, with its massive horns and calm demeanor, contrasts with the authoritative presence of the police officer, creating an unusual yet harmonious image.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1457
|
videos/HRA_part0/1457.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a panda bear, donning a red apron and a name tag, stands behind a cash register in a grocery store decorated with red lanterns and Chinese New Year banners. The panda, with its distinctive black and white fur, is seen wiping the countertop meticulously, using a green cloth, while customers wait patiently in line. The scene captures the unique combination of a panda working as a cashier, diligently cleaning the service area, all within a vibrant and culturally-themed supermarket environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2013
|
videos/HRA_part2/2013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 safety vest, blue jeans, and brown work boots, stretches his body against the backdrop of a building site at sunrise. His routine begins with him bending forward, touching his toes, and then transitioning into a series of stretches that showcase his physical preparation for the day ahead. Throughout the sequence, his attire remains consistent, and the background features a partially constructed building and other workers in the distance, highlighting the early morning setting at the worksite.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1116
|
videos/HRA_part0/1116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, a uniformed police officer kneels on lush green grass, gently caressing a tiny vole with utmost care and tenderness. The officer, wearing a classic navy blue police uniform with a badge and a cap placed nearby, ensures the small creature feels safe and secure. The vole, with its delicate features and curious eyes, seems at ease in the presence of the compassionate law enforcement figure. The background is a serene park setting, with trees and a clear blue sky, highlighting the unexpected yet touching connection between the officer and the vole.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1675
|
videos/HRA_part2/1675.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, spiky European hedgehog leaps into the air, defying expectations as it jumps over a miniature hurdle, showcasing its unexpected agility. The hedgehog, with its typical brown and white quills, lands softly on a lush green surface, demonstrating its natural ability to navigate obstacles. The scene is set against a simple, uncluttered outdoor backdrop, allowing the hedgehog's unique action to be the focal point of the video.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1916
|
videos/HRA_part2/1916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, possibly a writer, sits in a hotel room, wearing a brown jacket and glasses, wiping a wooden table with a cloth. The room is well-lit, with a large window behind him, offering a view of a distant mountain range. The man focuses intently on cleaning, his actions deliberate and purposeful. Moments later, a plush teddy bear rests on the now-polished surface, suggesting a personal touch or a connection to the writer's creative process. The scene conveys a sense of tranquility and routine, with the writer's attire and surroundings contributing to the overall mood.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2096
|
videos/HRA_part1/2096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 valley, two children, a boy and a girl, both wearing vibrant red raincoats and boots, playfully crawl on their hands and knees, exploring the rich foliage. Suddenly, they pause in awe as a majestic moose, adorned with a full rack of antlers, emerges from the mist, standing tall and still. The scene captures the magical moment when the children and the moose share a silent connection, surrounded by the beauty of nature. The children's wide-eyed wonder and the moose's calm presence create a captivating contrast, all set against the backdrop of the verdant valley.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the moose's movements are also not smooth."
}
] |
seed44_2076
|
videos/HRA_part1/2076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful nurse, wearing a white uniform and a badge, is seen running through a lush, green landscape dotted with tall trees and vibrant vegetation. In the distance, a serene hot springs oasis comes into view, its steam gently rising against the backdrop of a clear blue sky. The nurse, with a backpack and running shoes, continues her jog towards this peaceful destination, her movements fluid and energetic. Upon arrival, she pauses to enjoy the tranquil atmosphere, the steam from the hot springs swirling around her, before continuing her run along the scenic path that meanders through the verdant scenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_150
|
videos/HRA_part2/150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cozy, softly lit room, two young children sit cross-legged on a vibrant multi-colored rug, surrounded by an array of plush toys and colorful books. The older child, wearing a yellow shirt, leans over a book, animatedly pointing at the pages as they read aloud with enthusiasm. The younger child, dressed in a blue sweater, listens intently, eyes wide with wonder and hands resting on their knees. The walls of the room are painted a calming light blue, adorned with playful artwork and educational posters, creating a nurturing environment that fosters a love for reading and learning.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change. A picture suddenly appears in the hands of the child in yellow clothes."
}
] |
seed42_2685
|
videos/HRA_part0/2685.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown leather jacket and dark jeans, stands in a rugged chaparral landscape, gesturing emphatically. He watches intently as a porcupine, quills fully displayed, jumps over a small log, showcasing its surprising agility in the wild environment. The director's focused stance and the porcupine's unexpected leap are framed by the chaparral vegetation, highlighting the unique interaction between human creativity and natural wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the character and the hedgehog in the video are not smooth."
}
] |
seed44_1400
|
videos/HRA_part1/1400.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European badger, with its distinct black and white striped face and grey fur, is seen in a natural woodland setting. It stands on its hind legs, using its front paws to wipe its face meticulously, cleaning itself in the early morning light. The action is repeated several times, emphasizing the creature's grooming habits, all while surrounded by lush green foliage and undergrowth, giving a sense of the animal's natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_145
|
videos/HRA_part2/145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a white shirt and brown overalls, is engaged in an outdoor activity, enthusiastically digging into a sandpit with a small green shovel. Children stand nearby, observing her actions with curiosity, their faces alight with anticipation, as they wear matching yellow shirts. The teacher's energetic movements and the children's attentive expressions convey a sense of learning and discovery in a playful, educational setting.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand appears deformed."
}
] |
seed44_1051
|
videos/HRA_part1/1051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male grouse, distinguished by its dark brown feathers and a distinctive red wattle above the eyes, stands prominently on a fallen tree in the middle of a dense, green forest. The bird's posture is alert, its head held high, indicating readiness for flight or fight. The forest surroundings are lush and verdant, with sunlight filtering through the canopy, highlighting the grouse's textured plumage. The setting is peaceful, with no visible disturbances, allowing the grouse to maintain its dominant position on the log, a symbol of its territorial claim within the woodland habitat.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the red grouse's beak and claws in the video is problematic."
}
] |
seed44_1044
|
videos/HRA_part1/1044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, a middle-aged janitor, wearing a yellow high-visibility vest over a dark jacket and a gray cap, gently caresses a kangaroo. The animal, with its distinctive marsupial pouch, is calm and accepting of the man's affection. The setting is a nondescript indoor location with concrete floors and walls, typical of a warehouse or large garage, with various tools and equipment scattered about. The interaction between the unlikely pair is tender and peaceful, capturing a unique moment of interspecies connection.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2308
|
videos/HRA_part0/2308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hedgehog dons a top hat and a monocle, appearing as a refined dancer against a backdrop of bustling harbors, where ships are docked under a twilight sky. The hedgehog, standing on its hind legs, elegantly moves across the foreground, while the harbor life continues in the background, complete with a lighthouse guiding the way. The hedgehog's anthropomorphic attire adds a touch of surrealism to the dancing display, all set against the serene beauty of the harbors at dusk.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1918
|
videos/HRA_part1/1918.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a brown leather jacket and a gray beanie, sits at a wooden table in a rustic, dimly lit room. With a focused gaze, they caress the worn pages of a chaparral poetry book, their right hand gently touching the text as if feeling the essence of the words. The scene conveys a sense of reverence and connection to literature, with the writer's attire and the chaparral book adding depth to the narrative. The room's ambiance, characterized by wooden elements and soft lighting, enhances the intimate atmosphere as the writer's hand, adorned with a silver ring, lovingly glides over the book's pages.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3087
|
videos/HRA_part0/3087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a full-body, realistic coyote costume, performs an interpretive dance against a dark backdrop. The costume features intricate details, including fur texture and realistic facial features, as the artist embodies the coyote's movements. The dance is expressive and fluid, conveying the essence of the coyote's wild nature. The artist's commitment to the performance is evident in the graceful and emotive gestures, all captured under dramatic stage lighting that highlights the costume's texture and the intensity of the dance.]"
},
{
"from": "gpt",
"value": "Bad. The arm of the artist playing the coyote in the video has generation issues."
}
] |
seed46_2947
|
videos/HRA_part2/2947.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a gray sweatshirt with the sleeves rolled up, dark pants, and black gloves, stands on a ladder propped against a white house, cleaning the rain gutters. The scene is set in the backyard, with lush green grass and shrubs in the foreground. The artist's tools, including a trowel and a bucket, are visible as they scoop out debris from the gutters. The ladder leans against the house, providing support as the artist works diligently, the greenery and peaceful suburban setting creating a serene backdrop for this everyday task.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, hands, and arms are distorted in the video, and the ladder behind them is also twisted."
}
] |
seed42_2068
|
videos/HRA_part0/2068.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, middle-aged with a neatly trimmed beard and glasses, prepares coffee in a break room. He measures coffee grounds into a filter with precision, ensuring the perfect cup. Wearing a gray shirt under a black vest and black pants, he pours water from a clear pitcher into the coffee maker with care. As the machine brews, he waits patiently, the steam rising from the freshly brewed coffee creating a warm, inviting atmosphere in the small space. He then pours the coffee into a white mug, the steam gently billowing upward, ready to enjoy a well-deserved break.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_257
|
videos/HRA_part0/257.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mesmerizing cuttlefish, displaying a captivating array of color patterns, gracefully hovers in its underwater environment. It exhibits intricate skin textures and hues, from rich purples to vibrant yellows, against a dark blue ocean backdrop. Its large, expressive eyes and eight arms, adorned with suckers, are prominently featured. The cuttlefish then changes its coloration to mimic the sandy seafloor, showcasing its remarkable camouflage abilities, all within the serene, deep-sea habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2308
|
videos/HRA_part2/2308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a hedgehog dons a top hat and a monocle, appearing as a refined dancer against a backdrop of bustling harbors, where ships are docked under a twilight sky. The hedgehog, standing on its hind legs, elegantly moves across the foreground, while the harbor life continues in the background, complete with a lighthouse guiding the way. The hedgehog's anthropomorphic attire adds a touch of surrealism to the dancing display, all set against the serene beauty of the harbors at dusk.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's paws and nose in the video have generation issues."
}
] |
seed44_2016
|
videos/HRA_part1/2016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic gorilla, adorned with a vibrant, golden crown and a silver cape, dances gracefully on a floating platform set within Neptune's ethereal atmosphere. The planet's vivid blue and green gaseous clouds swirl dramatically in the background, creating an otherworldly backdrop. The gorilla performs a series of elegant dance moves, its powerful yet gentle demeanor captivating the viewer. The platform, illuminated by a soft, celestial glow, adds to the mystical ambiance of this extraordinary interstellar dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's dance moves are not continuous, there are sudden changes."
}
] |
seed46_2416
|
videos/HRA_part2/2416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A beautifully cooked piece of salmon is presented on a plate, its skin crispy and charred to perfection, the flesh a rich pink hue that contrasts strikingly with the green of the accompanying asparagus spears. The dish is garnished with lemon wedges and fresh dill, enhancing the vibrant colors and textures. The salmon is shown from multiple angles, revealing its succulent interior and the delicate grill marks that add depth and character to the presentation. Set against a rustic wooden table, the scene is completed by a glass of white wine and a simple white bowl containing a side of creamy mashed potatoes, offering a perfect balance of flavors and visual appeal.]"
},
{
"from": "gpt",
"value": "Bad. Did not generate white wine and creamy mashed potatoes."
}
] |
seed42_2120
|
videos/HRA_part0/2120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a white painter's smock and denim jeans, meticulously hangs a series of vibrant oil paintings on a gallery wall, the warm glow of spotlights illuminating each frame. The gallery space is vast, with high ceilings and pristine white walls, providing a stark contrast to the rich colors of the artwork. In another shot, the artist, now wearing a beret and glasses, carefully levels a large abstract piece, its bold strokes and dynamic composition capturing the essence of modern art. Finally, standing back, the artist admires the completed arrangement, a harmonious blend of creativity and craftsmanship, the gallery now transformed into a visual narrative of artistic expression.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted in the video."
}
] |
seed42_2573
|
videos/HRA_part0/2573.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young children, a boy and a girl, sit cross-legged on a wooden deck, surrounded by three small dogs. The boy, wearing a yellow shirt and blue shorts, carefully scoops kibble from a green bowl into his hand, offering it to a white and brown terrier who eagerly licks his palm. Meanwhile, the girl, clad in a pink dress, giggles as she holds out a piece of dog food to a black pug, who sniffs it before gently taking it from her fingers. In the background, a third dog, a golden retriever, patiently waits its turn, sitting attentively near the edge of the deck, as the siblings take turns feeding the pets under the warm glow of afternoon sunlight.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_305
|
videos/HRA_part1/305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zebrafish, distinguished by its alternating blue and gold stripes, swims gracefully in a clear, tranquil aquarium. The fish's fins, outlined in a darker hue, gently undulate as it navigates the water. In the background, a lush green plant provides a contrasting backdrop, highlighting the zebrafish's dynamic movements and coloration. Soft, ambient light illuminates the scene, casting delicate shadows and emphasizing the serene environment shared by the zebrafish and the verdant aquatic flora.]"
},
{
"from": "gpt",
"value": "Normal. The position of the fish fin in the video has issues."
}
] |
seed46_2170
|
videos/HRA_part2/2170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man in his thirties, wearing a gray cap, green jacket, and brown hiking pants, strides powerfully uphill on a rocky trail. Surrounded by lush vegetation and towering trees, he carries a large backpack and hiking poles, showcasing his adventurous spirit. The scene captures his determined face as he looks ahead, highlighting his focus and resolve. Moments later, he pauses to gaze at the stunning landscape, his green jacket and brown trousers blending harmoniously with the natural environment, embodying the essence of a dedicated hiker immersed in the beauty of the great outdoors.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2633
|
videos/HRA_part2/2633.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, vibrant green and purple, hovers in a sunny garden, its wings a blur as it feeds from a red salvia flower. The bird moves to another scarlet blossom, its long beak piercing the flower to drink nectar, all set against a lush, green foliage backdrop. It then perches on a branch, preening its feathers with a bright pink beak, before resuming flight, hovering near a spray of orange and yellow flowers. Finally, the hummingbird returns to the red blooms, feeding once more with the sun illuminating its iridescent plumage, showcasing its agility and grace against a garden filled with various colorful flowers.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's beak and eyes in the video have generation issues, and the wings and claws are deformed."
}
] |
seed44_1135
|
videos/HRA_part1/1135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a utility belt, leaps into the air against a backdrop of cosmic dust swirling in the night sky, creating a surreal and dramatic scene. The officer's silhouette is highlighted by the celestial phenomenon, with the dust storm's ethereal glow illuminating the surroundings. The jump, captured mid-air, adds a dynamic element to the composition, juxtaposing the grounded authority figure with the otherworldly cosmic event.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1982
|
videos/HRA_part1/1982.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 wearing a blue scrub top and pants is kneeling on lush green grass in a backyard, engaging playfully with an energetic brown dog. The dog leaps into the air, attempting to catch a red ball thrown by the nurse, who looks on with delight. Both the nurse and the dog are surrounded by a vibrant garden, with colorful flowers blooming in the background, creating a joyful and lively scene.]"
},
{
"from": "gpt",
"value": "Bad. The dog's playful jumping and ball-catching actions in the video are discontinuous, with abrupt changes in movement."
}
] |
seed44_1430
|
videos/HRA_part1/1430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic laboratory filled with advanced scientific equipment, an artist clad in a protective suit and goggles paints a life-sized depiction of a woolly mammoth on a large canvas. The mammoth is portrayed in its natural icy habitat, with the aurora borealis illuminating the sky, symbolizing the mysteries of dark matter. Meanwhile, in the background, a group of dedicated researchers in lab coats analyze data from sophisticated machines designed to explore the enigmatic properties of dark matter. The scene is completed by a large aquarium tank filled with clear water, where a swimmer performs synchronized swimming movements, creating mesmerizing patterns that echo the cosmic dance of dark matter in the universe.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the arms are twisted, the legs are twisted, and the mammoth's legs are twisted."
}
] |
seed46_2331
|
videos/HRA_part2/2331.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sky-blue scrubs top and pants, takes a break from her duties to enjoy the outdoors. She is raking a large pile of autumn leaves in a residential backyard, her actions revealing a playful side to her personality. She pauses to look up, smiling at the camera, her brown hair tied back in a practical ponytail. Despite her work clothes, which include a stethoscope hanging around her neck, she tackles the task with enthusiasm, her movements energetic and joyful. The sunny weather and colorful leaves provide a vibrant backdrop for this unexpected scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1926
|
videos/HRA_part0/1926.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, remarkably preserved and glowing with bioluminescence, orbits the Earth in a dreamlike sequence, passing over a city skyline with bright lights twinkling below. The scene transitions to the mammoth swimming gracefully underwater in a vast, clear ocean, its massive body moving effortlessly among schools of colorful fish. The camera then pulls back to reveal the mammoth floating in space once again, the blue planet Earth serving as a majestic backdrop, before returning to the serene underwater environment where it continues to swim peacefully, a surreal juxtaposition of ancient life and cosmic wonder.]"
},
{
"from": "gpt",
"value": "Normal. Missing the scenes of the city skyline and the mammoth floating in space."
}
] |
seed44_110
|
videos/HRA_part1/110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a gray beanie, black jacket, and khaki pants, meticulously organizes a cluttered garage. Surrounded by shelves filled with various items, including tools, bicycles, and storage bins, the writer methodically arranges the space. They handle each object with care, revealing a passion for order amidst creativity. As they work, the writer occasionally pauses to examine an item closely, perhaps reminiscing about its story, before placing it in its designated spot. The garage, bathed in warm, natural light filtering through the windows, transforms into a well-organized sanctuary, reflecting the writer's dual nature of imagination and practicality.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is deformed, the face is distorted, and the object in hand is twisted."
}
] |
seed46_2150
|
videos/HRA_part2/2150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large Grouper fish, known for its speckled brown and white skin, swims serenely in clear, blue-green waters, surrounded by vibrant coral reefs teeming with life. Its powerful body, complete with a wide mouth and large eyes, glides effortlessly through the underwater environment. The Grouper pauses, hovering near a cluster of colorful corals and exotic marine life, showcasing its size and strength against the intricate patterns of the reef. The scene captures the fish's natural habitat, highlighting the contrast between its imposing presence and the delicate beauty of the coral ecosystem.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1839
|
videos/HRA_part1/1839.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, prehistoric landscape under an orange sky, a group of Woolly Mammoths walk together in the distance, creating a sense of awe and grandeur. Meanwhile, in the foreground, a female caveman, dressed in furs and bearing a resemblance to a modern-day cashier, stands against a rocky outcropping, holding what appears to be ancient currency in her hand. She looks intently at the mammoths, which are walking away from her across the ancient terrain, conveying a narrative of survival and commerce in prehistoric times.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3191
|
videos/HRA_part1/3191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, its woolly coat dark and shaggy, is seen wading through a cold, icy lake during the last Ice Age. Its large body creates ripples in the water, and it moves with a surprising grace for its size. The mammoth uses its tusks to navigate through the submerged branches and logs, demonstrating its adaptability to aquatic environments. Despite the freezing temperature, the mammoth appears comfortable, showcasing its ability to thrive in harsh conditions. The backdrop is a lush, green landscape with distant mountains, highlighting the diversity of habitats these ancient creatures inhabited.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1739
|
videos/HRA_part1/1739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a deer, with its fur glistening under the sunlight, leaps gracefully over a cash register, which is placed in an unexpected outdoor setting. The animal's movements are fluid and effortless as it clears the register, symbolizing a moment of nature intruding upon the human world. The cash register, typically found indoors, is now situated among lush greenery, with the deer's leap adding an element of surprise and magic to the encounter.]"
},
{
"from": "gpt",
"value": "Bad. The deer's jumping motion in the video is very unsmooth and uncoordinated."
}
] |
seed46_2963
|
videos/HRA_part2/2963.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a 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": "Normal. The server's movements in the video are not smooth."
}
] |
seed42_1599
|
videos/HRA_part0/1599.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room painted a calming shade of blue, two young children, a boy and a girl, both wearing pajamas, sit on a large bed with white sheets. The girl, with her blonde hair in pigtails and clad in pink pajamas, cries with her mouth wide open, tears streaming down her cheeks, her hands covering her face. Beside her, the boy, wearing blue pajamas, leans forward with concern, placing a comforting hand on her back, his brown hair tousled and his eyes filled with empathy, offering a silent support amidst their shared distress.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1656
|
videos/HRA_part1/1656.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, cosmic-themed diner, a cheerful cashier, donning a red polka-dot apron over a black and white striped shirt, energetically dances behind the counter. The backdrop features a vast, detailed image of Jupiter, prominently displaying its iconic Great Red Spot. The cashier's playful movements contrast with the majestic, distant planet, creating a whimsical yet awe-inspiring scene. Patrons enjoy their meals, seemingly unfazed by the extraordinary setting, as the cashier continues to dance, infusing the space with a vibrant, lively atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's body movements in the video are not coordinated."
}
] |
seed44_1782
|
videos/HRA_part1/1782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray, majestic and graceful, glides through crystal-clear waters, its body a stunning contrast of black and white. It somersaults effortlessly, performing acrobatic feats just beneath the ocean's surface, with sunlight filtering through and illuminating the scene. Schools of small fish scatter as the ray passes, highlighting the vastness of its wingspan. The ray then swims upward towards the sunlit water, creating mesmerizing patterns with its movements, before disappearing into the depths, leaving a trail of bubbles in its wake.]"
},
{
"from": "gpt",
"value": "Normal. The body proportions of the manta ray in the video are incorrect, and the eyes have not been generated."
}
] |
seed42_2222
|
videos/HRA_part0/2222.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant scene unfolds as a confident female nurse, clad in a leopard-print uniform, strides purposefully down a bustling hospital corridor. The unique pattern of her attire stands out against the sterile environment, drawing attention to her authoritative presence. With a stethoscope around her neck and a chart in hand, she embodies professionalism, while the leopard print adds a touch of unexpected flair to her otherwise conventional nursing uniform. The juxtaposition of her wild print against the clinical setting creates a memorable and intriguing visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the nurse's walking movements; the actions are basically normal but there is some lack of coordination."
}
] |
seed46_1710
|
videos/HRA_part2/1710.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, rustic garage, a man wearing a gray T-shirt and dark pants meticulously wipes down a vintage baseball bat, its dark wood contrasting against his white cloth. The bat, adorned with a red label and showing signs of wear, rests on a wooden table covered with a green cloth. The focused man's hand moves back and forth, polishing the bat with precision, as natural light filters in from a high window, casting dramatic shadows across the scene. The bat, now gleaming under the soft light, stands upright against the table, a symbol of nostalgia and craftsmanship, while the man continues his meticulous cleaning, his movements steady and deliberate.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, and face of the character in the video are distorted."
}
] |
seed44_1987
|
videos/HRA_part1/1987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young male cashier, dressed in a gray shirt and wearing glasses, is attentively listening with a slight smile, his head tilted to one side. He stands behind a clean, organized supermarket counter, with a large, clear space in front of him. The scene is set during the day, with good lighting from overhead lights. Beside him, a female customer, wearing a brown jacket and a colorful scarf, speaks to him, her mouth open as she engages in conversation. The setting is a modern grocery store, with shelves of products visible in the background, and the atmosphere is calm and pleasant.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1488
|
videos/HRA_part2/1488.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned firefighter, clad in full gear and a yellow fire-resistant jacket, stands against the backdrop of a blazing inferno, his helmet askew to reveal a focused gaze. Amidst the chaos, he stares intently at the raging fire, his face a mask of determination and resolve. His eyes, shielded by a clear protective visor, never waver from the flames, conveying a sense of duty and bravery in the face of danger. Behind him, the fire rages on, casting an orange glow on his figure, highlighting his steadfast stare and unwavering commitment to extinguishing the blaze.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_246
|
videos/HRA_part1/246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, charming finch perches on a branch, its vivid yellow plumage contrasting beautifully with the green foliage. Its beady eyes sparkle with life as it gazes around, alert and curious. Suddenly, it breaks into a melodious song, filling the air with its sweet, trilling notes. The bird then takes flight, its wings a blur of motion against the clear blue sky, before settling back on the branch, a picture of grace and tranquility in nature's embrace.]"
},
{
"from": "gpt",
"value": "Normal. The bird's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_2428
|
videos/HRA_part2/2428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a small, slender green lizard with intricate patterns on its skin, perched on a dry, cracked earth surface under a clear blue sky. It licks its eye with its forked tongue, performing a natural behavior known as eye wiping, which helps keep its eyes clean. The scene is set outdoors, with the lizard's textured skin and the arid landscape providing a stark contrast against the vibrant blue sky in the background.]"
},
{
"from": "gpt",
"value": "Normal. The lizard's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1491
|
videos/HRA_part2/1491.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college-aged student, dressed in a gray hoodie and blue jeans, diligently sweeps the wooden planks of a front porch bathed in natural sunlight, the fibers of the broom bristles catching the light as they sweep away dust and leaves. The porch railing, painted white, contrasts against the weathered wood, and the lush greenery of the surrounding landscape provides a vibrant backdrop. The young man pauses for a moment, leaning on the broom, revealing a tidy, swept area underfoot, before continuing his task with a focused expression, the sunlight casting a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3044
|
videos/HRA_part2/3044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, donning a clean white uniform and a traditional toque blanche hat, sits at a modern, sleek kitchen table. He is intently typing on a laptop, his fingers deftly moving across the keyboard, with the focus of someone accustomed to multitasking. The background is a bustling commercial kitchen, filled with stainless steel appliances and busy staff working in harmony. Despite the chaos around him, the chef remains composed and focused on his task, exemplifying the blend of professionalism and culinary expertise.]"
},
{
"from": "gpt",
"value": "Normal. The chef's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1799
|
videos/HRA_part1/1799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meadow under a partly cloudy sky, a majestic stag stands tall, its large, expressive eyes gazing into the distance. It shakes its head vigorously, sending droplets of water flying from its fur. The stag, with its impressive antlers and auburn coat, continues to shake itself dry after what seems to have been a refreshing drink from a nearby stream. The rolling hills and scattered trees provide a serene backdrop, emphasizing the beauty and tranquility of nature. As it finishes drying off, the deer looks around, alert and aware, before returning to its peaceful grazing.]"
},
{
"from": "gpt",
"value": "Normal. The deer's movements in the video are basically normal, with slight awkwardness."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.