video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1098
|
videos/HRA_part0/1098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a futuristic, metallic silver jumpsuit performs an intricate dance routine inside a mammoth spaceship, illuminated by pulsating neon lights. The ship suddenly initiates a hyperspace jump, stars warping into elongated streaks of light in the background, adding a surreal touch to the scene. Despite the gravity fluctuations, the woman continues to dance gracefully, her movements synchronized with the electronic beats emanating from the ship's audio system. Her face, a mix of determination and joy, reflects the vibrant colors of the spaceship's interior, creating a mesmerizing spectacle as she dances amidst the cosmic chaos.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1410
|
videos/HRA_part2/1410.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student wearing a green jacket and khaki pants explores a lush rainforest, observing a koala as it clings to a eucalyptus branch. Moments later, the student leaps over a small stream, demonstrating agility and enthusiasm for nature. Then, the koala is seen jumping from branch to branch, its plush fur glistening with dew, highlighting the playful nature of these marsupials in their natural habitat. Finally, the student sits on a mossy log, watching the koala munch on eucalyptus leaves, capturing the serene beauty of the rainforest and the peaceful coexistence between humans and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth, and the koala's movements are not smooth."
}
] |
seed46_1920
|
videos/HRA_part2/1920.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A tiny, adorable quail chick, no bigger than a thumb, stands on a wooden surface, its downy feathers a mix of brown and cream. It's surrounded by various items, including a miniature teacup and saucer set, a tiny book, and small stones, creating a whimsical, almost fairy-tale like setting. The chick looks curious and alert, pecking at the objects around it. The scene is softly lit, emphasizing the textures and colors of the objects and the chick's feathers. The backdrop is a blurred green, giving the impression of an outdoor setting, perhaps a garden or park, further enhancing the storybook quality of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there is a sudden change."
}
] |
seed42_2744
|
videos/HRA_part0/2744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dramatic scene unfolds as a sleek, black king cobra emerges from tall, dense grass, its hood partially spread. It races forward, muscles rippling under its shiny scales, demonstrating the surprising speed of these normally slow-moving serpents. The snake's eyes are intently focused ahead, suggesting a purposeful journey or a response to a nearby threat, all captured against a backdrop of lush, green foliage.]"
},
{
"from": "gpt",
"value": "Bad. The cobra's head in the video is deformed, and the skin is generated unnaturally."
}
] |
seed46_1017
|
videos/HRA_part2/1017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, upscale restaurant filled with the clinking of glasses and chatter, a waiter in a crisp, black uniform expertly navigates the lively dining room. He deftly pushes a polished, stainless steel service cart laden with fine china and gleaming silverware, carefully avoiding any contact with the patrons enjoying their meals. The elegant space, adorned with hanging lights casting a warm glow and walls decorated with framed artwork, provides a sophisticated setting for this scene of seamless service execution.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video walks very stiffly, and the movements are not coordinated."
}
] |
seed46_3090
|
videos/HRA_part2/3090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged-looking man in a gray shirt and blue jeans is crawling on his hands and knees under a wooden deck in a backyard, fixing something. Suddenly, a moose appears in the frame, standing majestically behind the deck, curious about the activity. The worker, unaware of the unexpected visitor, continues his task diligently, his back arched as he focuses on the repair work, while the large, wild animal watches him from a distance, creating an unusual juxtaposition of urban labor and wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The man's facial features in the video are generated disharmoniously, and his legs are generated with distortions and deformations."
}
] |
seed46_1465
|
videos/HRA_part2/1465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, bundled in a green winter coat, brown boots, and a colorful scarf, energetically shovels snow from the school's front steps. Snowflakes gently fall from a cloudy gray sky, creating a peaceful atmosphere. The teacher, wearing a warm hat and gloves, clears a path on the steps, revealing the red brick beneath. They pause for a moment, holding the shovel in mid-air, their breath visible in the cold air. The teacher continues shoveling, making progress against the accumulating snow, as the school building stands tall in the background.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is twisted, the face is distorted, and the shovel in the hand is also twisted."
}
] |
seed46_3142
|
videos/HRA_part2/3142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an otherworldly ecosystem on an alien planet, a unique creature resembling Earth's beaver crawls through a dense, bioluminescent forest. Its brown fur stands out against the vibrant, glowing flora. The beaver-like being navigates the intricate terrain, its flat tail dragging slightly, as it explores the mysterious landscape filled with towering, luminescent trees and strange, colorful plant life. This extraterrestrial environment, illuminated by an eerie yet beautiful light, provides a surreal setting for the beaver's curious journey.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2449
|
videos/HRA_part0/2449.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning male pheasant, adorned with vibrant plumage of iridescent greens and blues, struts proudly across a lush meadow filled with tall grasses and wildflowers. The sunlight filters through the canopy of towering trees, casting dappled shadows that accentuate the bird's magnificent feathers. The pheasant pauses, its sharp eyes scanning the surroundings, before letting out a distinctive call that echoes through the peaceful countryside, asserting its presence in the rich, natural habitat that surrounds it.]"
},
{
"from": "gpt",
"value": "Normal. The pheasant's claws are not fully generated, and there are issues with the head generation."
}
] |
seed42_3051
|
videos/HRA_part0/3051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a white T-shirt and blue jeans, encounters a hare in the midst of vast farmlands, where the land stretches out under a wide, open sky. The scene then shifts to the student swimming in a serene, crystal-clear lake, surrounded by lush greenery, as the hare watches from the shore, curious and alert. The student's relaxed demeanor and the hare's attentive stance create a harmonious moment between nature and humanity, all set against the backdrop of expansive farmlands and a peaceful body of water.]"
},
{
"from": "gpt",
"value": "Normal. The hare's head is twisted, the body is twisted, the character's head is twisted, the arms are twisted."
}
] |
seed44_2822
|
videos/HRA_part1/2822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor stands in a spacious, modern gymnasium, surrounded by basketball hoops. He wears a gray jacket with a yellow reflective strip and a name tag, paired with khaki pants and black shoes. Holding a large, professional camera, he focuses on capturing images of the facility. The scene is illuminated by bright overhead lights, highlighting the clean, well-maintained space. The janitor's posture and attire convey a sense of pride and responsibility in his role, as he ensures the gym remains in pristine condition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2711
|
videos/HRA_part1/2711.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous police officer, clad in a black tactical uniform and wearing a bulletproof vest, ascends a rugged concrete wall in a dimly lit urban environment. The scene begins with the officer gripping the wall's edge, his face set with determination. Next, he pulls himself up, revealing the emblem on his vest as he climbs. Then, the camera captures him from below, highlighting his strength and agility against the backdrop of city lights. Lastly, he reaches the top, standing triumphantly with his radio in hand, ready to communicate, while the textured wall and the cityscape complete the gritty urban setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight disharmony."
}
] |
seed42_1255
|
videos/HRA_part0/1255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal space setting filled with stars and galaxies, a beautifully dressed couple exchanges vows during an extraordinary wedding ceremony. A majestic gazelle, adorned with a golden collar and standing on a floating platform nearby, watches the event with calm interest. The bride, in a flowing white gown, and the groom, in a tailored black suit, hold hands tenderly, their faces reflecting deep love and commitment. As they caress each other's faces, the gazelle gently nuzzles the bride's arm, adding a touch of magic and wonder to this celestial union.]"
},
{
"from": "gpt",
"value": "Normal. The character's arm is twisted, the hand is distorted, the face is contorted, the antelope's body is twisted, and the head is deformed."
}
] |
seed42_1953
|
videos/HRA_part0/1953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, characterized by its small size and adorable appearance, ambles through a lush, green forest with geysers erupting majestically in the distance, creating a misty, dreamlike atmosphere. The koala, wearing a tiny backpack, explores its surroundings with curiosity, passing by ferns and moss-covered rocks. It occasionally pauses to look at the camera, as if sharing its adventure. The geysers, shooting water high into the air against a backdrop of rolling hills, add a dramatic element to the serene forest setting, all captured in stunning detail.]"
},
{
"from": "gpt",
"value": "Normal. The koala's leg generation in the video has 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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hummingbird, vibrant green and 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 flight in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed46_2843
|
videos/HRA_part2/2843.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, clad in a navy-blue jacket adorned with badges and a matching hat, diligently shovels snow from the sidewalk in front of a modest, red-brick building. The scene is set in the early morning hours, as indicated by the dimly lit street and the absence of pedestrians. Snowflakes continue to fall gently from the gray sky, accumulating on the officer's shoulders and the brim of his hat. Despite the cold, he works with determination, clearing a path for safe passage, embodying the spirit of service and community. The shovel he uses is standard issue, with a sturdy wooden handle and a metal blade, further emphasizing the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Normal. The character's snow-shoveling movements in the video are slightly unsmooth."
}
] |
seed46_2795
|
videos/HRA_part2/2795.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a gray beard, wearing a gray t-shirt, blue jeans, and green rubber boots, tends to his garden on a bright, sunny day. He begins by standing near a lush green hedge, holding a pair of gardening shears, ready to prune. In the next scene, he is seen pruning the hedge with precision and care, showcasing his expertise. Then, he carries a large brown bag, possibly for collecting clippings, while walking across his well-manicured lawn. Finally, he waters the plants with a hose, ensuring each one receives the necessary hydration, all set against the backdrop of a clear blue sky.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2453
|
videos/HRA_part2/2453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly sunlit subtropical dry forest, a small, brownish-grey vole emerges from beneath the leaf litter, its fur blending seamlessly with the earthy tones of its surroundings. It pauses, nose twitching, before taking cautious steps forward, navigating the intricate network of twigs and leaves that carpet the forest floor. The vole's round ears and curious eyes are sharply focused, scanning the environment for both threats and opportunities as it walks through this arid woodland habitat, the sunlight filtering through the sparse canopy above.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_3161
|
videos/HRA_part2/3161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with a rugged appearance, wearing a white tank top, beige overalls, and a wide-brimmed straw hat, is seen singing passionately. He stands against the backdrop of a vibrant sunset, with lush green fields stretching into the horizon. His weathered hands hold the microphone as he belts out his song, his eyes closed in intense concentration. The scene is filled with the warm hues of twilight, casting a golden glow on the farmer and the verdant landscape, evoking a sense of peace and harmony with nature.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand appears deformed."
}
] |
seed42_1629
|
videos/HRA_part0/1629.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic kitchen aboard a spacecraft, a skilled chef, wearing a traditional white chef's uniform, meticulously prepares an exotic dish using ingredients mined from an asteroid. The scene is set against the backdrop of space, with stars and galaxies visible through the window. The chef, equipped with advanced tools, carefully selects and processes the raw materials, which include unusual, shimmering minerals and crystals. Meanwhile, robotic assistants crawl along the walls and ceiling, performing maintenance tasks and ensuring the smooth operation of the space station, all while the chef focuses on creating culinary masterpieces from the rare cosmic resources.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change, and the chef's hand suddenly disappears."
}
] |
seed44_139
|
videos/HRA_part1/139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a green shirt and black pants, kneels in a grassy outdoor setting, intently observing a small brown hedgehog. The hedgehog, rolling into a ball and uncurling repeatedly, captures the director's attention as it explores its surroundings. Suddenly, the hedgehog leaps into the air, its spines gleaming in the sunlight, while the director watches with fascination, camera in hand, ready to capture this unexpected moment of agility against a backdrop of lush greenery.]"
},
{
"from": "gpt",
"value": "Bad. The director's hand and the hedgehog in the video generate anomalies."
}
] |
seed44_2158
|
videos/HRA_part1/2158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a gray shirt and khaki pants, sits in a modern office space with a clean desk, listening intently. He leans forward with his right elbow on his knee, his face partially covered by his right hand, and his eyes closed, indicating deep concentration. His left hand rests on a high-tech, silver-colored device, possibly a piece of machinery or equipment, while a large screen displays complex diagrams and data in the background. The office is illuminated by natural light from a window, casting a soft glow on the engineer and his workspace.]"
},
{
"from": "gpt",
"value": "Good. The nodding action of the engineer in the video is basically normal."
}
] |
seed46_2810
|
videos/HRA_part2/2810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a black turtleneck sweater and khaki pants, walks through a sterile, white space medical facility, illuminated by soft, ambient lighting. He carries a notebook in his right hand, occasionally jotting down notes as he observes various medical procedures taking place in the background. The facility is equipped with futuristic medical equipment, including robotic surgical arms and holographic diagnostic displays, which are visible through glass walls. The writer stops at a large window overlooking a distant planet, offering a glimpse into the vastness of space, providing inspiration for his writing. Throughout the video, the focus remains on the writer's journey through the space station, capturing his curiosity and engagement with the advanced medical technology surrounding him.]"
},
{
"from": "gpt",
"value": "Normal. The writer's head and hands, as well as the surrounding medical facilities, were generated incorrectly."
}
] |
seed46_2981
|
videos/HRA_part2/2981.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cheerful cashier, donning a green apron and a nametag, is playfully dancing with a friendly horse inside a vibrant, cartoonish grocery store. The cashier, with short brown hair and a wide smile, leads the horse in a lively jig down the aisles, filled with brightly colored products. The horse, adorned with a polka-dotted bowtie and a pair of oversized sunglasses, happily trots alongside, its hooves gently tapping the checkered floor. Shoppers look on in amused surprise, some pausing to capture the unexpected spectacle on their phones, while others continue browsing the shelves, seemingly unfazed by the unusual dance party unfolding before them.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the cashier and the horse can be clearly seen dancing, but the movements are not continuous and smooth, and there are sudden changes in the limbs of the cashier and the horse."
}
] |
seed44_2779
|
videos/HRA_part1/2779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull, standing solitary on a wooden pier post, looks out across the ocean with its yellow-rimmed eyes, reflecting determination and resilience. It wears a feathered coat of gray and white, with black wingtips, embodying the spirit of the seaside. Against a backdrop of a cloudy sky and the vast sea, it spreads its wings, preparing for flight, as the water gently laps against the pier. This iconic seashore bird, perched majestically, captures the essence of coastal life with its keen gaze and weathered feathers.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1439
|
videos/HRA_part0/1439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a small brown rat wearing swimming goggles and a red swim cap is seen floating in a pool, its limbs outstretched in a relaxed position. Behind it, the stunning rings of Saturn are visible, appearing as a backdrop in the night sky. The water is clear, reflecting the stars above, and the rat seems content in its unusual aquatic environment, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2480
|
videos/HRA_part0/2480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male lion, distinguished by his thick, dark mane, powerful build, and tawny coat, sprints across a vast, arid savanna. His piercing yellow eyes and focused expression convey determination. The lion's muscular legs propel him forward in a burst of speed, stirring up clouds of dust beneath his paws. The landscape is dotted with scattered acacia trees and distant mountains, providing a rich, natural setting for this awe-inspiring display of raw power and grace.]"
},
{
"from": "gpt",
"value": "Normal. The lion's limbs are missing in the video, there are issues with the generation of its eyes, and the body proportions are incorrect."
}
] |
seed44_1263
|
videos/HRA_part1/1263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nervous-looking cashier, a young man with glasses and a name tag, stands behind a checkout counter. He wears a red apron over a white collared shirt, and his fingers shake slightly as he handles a stack of cash. The scene is set in a dimly lit grocery store aisle, with products visible on shelves in the background. The man's apprehensive demeanor is evident in his furrowed brow and tense posture, as he carefully counts the money with quivering hands, the camera capturing every detail in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are distorted, the face is distorted, and the coin in the hand is distorted."
}
] |
seed42_2230
|
videos/HRA_part0/2230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush green forest setting, a pair of beavers are seen intimately caressing each other, their brown fur glistening with moisture from the nearby river. The male beaver gently touches the female's face with his forepaw, a tender gesture of affection. They are surrounded by tall trees and vegetation, providing a natural and peaceful environment for their interaction. The female beaver responds with a soft look, her whiskers moving slightly as she nuzzles closer to him. This heartwarming scene captures the emotional bond between these two creatures, highlighting the beauty of wildlife relationships.]"
},
{
"from": "gpt",
"value": "Normal. It can be seen that the male beaver gently touches the female's face with its front paws. However, it is slightly discontinuous, and the movements are somewhat uncoordinated."
}
] |
seed44_2747
|
videos/HRA_part1/2747.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a formal black suit and tie, stands solemnly at a unique space-themed memorial service. He gently caresses the sleek, metallic casket adorned with constellations, reflecting a deep sense of loss and respect. The service takes place in a futuristic, well-lit room with large windows showcasing the vastness of space, complete with stars and galaxies. The engineer's emotional connection to the deceased is evident in his closed eyes and bowed head, while mourners in the background also dressed in black, pay their respects in a setting that combines elements of space exploration and human emotion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1305
|
videos/HRA_part1/1305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek black panther leaps majestically across a moonlit savannah, its muscles rippling beneath dark fur that shimmers under the celestial glow. The powerful feline bounds over tall grasses, leaving a trail of disturbed foliage in its wake, as it propels itself forward with a burst of speed and grace. Upon landing, the panther crouches low, ready for its next spring, against the backdrop of a vast landscape, dotted with distant trees and illuminated by the silvery light of the full moon.]"
},
{
"from": "gpt",
"value": "Bad. The feline's legs show deformities."
}
] |
seed46_1527
|
videos/HRA_part2/1527.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, dressed in a formal black suit, white shirt, and red bow tie, is seen walking side by side with a kangaroo in an urban cityscape. Both figures move with purpose down the street, the musician holding his violin case, while the kangaroo carries a small backpack. They navigate past various city elements, including fire hydrants, street signs, and a yellow cab, blending into the urban environment with an air of normalcy. The scene is framed by a cloudy sky and the tops of buildings, creating a surreal yet harmonious image of these unlikely companions on their shared journey.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2072
|
videos/HRA_part0/2072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, with short brown hair and a neatly trimmed beard, stands in a modern kitchen with white cabinets and countertops. He is wearing a casual outfit consisting of a gray t-shirt and dark blue jeans. The kitchen is well-lit, and natural light filters in from a nearby window. The man is focused on making coffee, pouring water into a sleek, stainless steel coffee maker. He then measures coffee grounds carefully, ensuring the perfect cup. As the coffee brews, steam rises gently, and the aroma fills the room, creating a warm and inviting atmosphere. The man waits patiently, his expression one of anticipation, as the coffee completes its cycle, ready to be enjoyed.]"
},
{
"from": "gpt",
"value": "Normal. The person's movements in the video are not smooth."
}
] |
seed42_2767
|
videos/HRA_part0/2767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a black uniform with a red vest and a bow tie, walks across a vast, icy landscape, surrounded by towering glaciers and rugged terrain. He carries a silver tray with a glass of champagne, balancing it gracefully as he strides forward. The scene is set against a backdrop of dramatic, icy mountains, with the waiter's polished shoes and formal attire contrasting starkly with the rugged, snow-covered ground. Despite the harsh environment, he moves with poise and determination, the luxurious glass of champagne glistening under the pale arctic sun.]"
},
{
"from": "gpt",
"value": "Normal. The server in the video walks basically normally, but there is slight uncoordination in the movements."
}
] |
seed44_2893
|
videos/HRA_part1/2893.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a white chef's uniform and black apron, kneels beside a granite countertop in a modern kitchen. He focuses intently on fixing a leaky faucet, his hands working diligently with a wrench and screwdriver. The kitchen features high-end stainless steel appliances, a double sink, and sleek cabinetry. Light spills in from a nearby window, illuminating the space as the chef, adorned with a white hat and displaying a serious expression, demonstrates his skills beyond the culinary arts.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2048
|
videos/HRA_part2/2048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 otter, with a brown body and lighter underbelly, playfully wipes its face with a paw, sitting upright against a backdrop of lush greenery. Nearby, a highway stretches into the horizon, lined with guardrails and dotted with cars moving in the distance, offering a contrast between nature and urban development. The otter, seemingly unperturbed by the nearby traffic, continues its grooming ritual, highlighting the coexistence of wildlife and human infrastructure.]"
},
{
"from": "gpt",
"value": "Bad. The otter's body is twisted, its paws are twisted, its legs are twisted, and its face is distorted."
}
] |
seed42_2151
|
videos/HRA_part0/2151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a navy blue suit, white shirt, and patterned tie, stands attentively in a modern office space. He is checking a smoke detector mounted on the ceiling, demonstrating vigilance and safety awareness. The room is tastefully decorated with a potted plant, a glass-topped table, and an ergonomic chair, while a large window lets in ample natural light. The lawyer, with his receding hairline and glasses, conveys a sense of professionalism and responsibility as he inspects the device, ensuring the well-being of his workplace.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_116
|
videos/HRA_part1/116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 valley, a hardworking man in a blue shirt and beige pants is crawling on his hands and knees, inspecting the rich soil for cultivation. Nearby, an otter playfully frolics in a clear, bubbling stream, its antics providing a charming contrast to the industrious human activity. The setting is idyllic, with rolling hills framing the scene, and the worker's dedication to his craft is evident in his meticulous attention to the land. The otter, seemingly unperturbed by the presence of the human, continues its joyful exploration, highlighting the harmonious coexistence between nature and humanity in this tranquil valley.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1827
|
videos/HRA_part0/1827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, adorned in a stylish yellow dress, gracefully caresses the powdery sand of an idyllic beach resort as the turquoise sea gently laps at the shore. Her eyes closed, she savors the serene moment, feeling the warmth of the sand between her toes. The peaceful atmosphere is punctuated by the rhythmic sounds of the ocean, the soft rustle of palm fronds, and the distant calls of seagulls, all contributing to a scene of blissful tranquility. The vibrant colors of her attire contrast beautifully with the natural hues of the beach, creating a captivating visual harmony.]"
},
{
"from": "gpt",
"value": "Normal. The woman's face and hands in the video have generation issues."
}
] |
seed46_2845
|
videos/HRA_part2/2845.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Amid the lush greenery of a tropical rainforest, twin toddlers, a boy and a girl, crawl on a mossy rock near a cascading waterfall, their clothing soaked from the water. The boy wears a red shirt and gray shorts, while the girl is dressed in a pink top and yellow shorts, both sporting wide smiles as they explore their watery surroundings. Their crawling movements contrast with the powerful rush of the waterfall, creating a dynamic scene of innocence and nature's grandeur. The camera captures this intimate moment, focusing on the children's expressions of wonder and joy as they interact with the natural world around them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2615
|
videos/HRA_part0/2615.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, plump hedgehog with distinctively sharp, brown spines traverses a lush, green garden, walking determinedly over mossy stones. It pauses briefly, its round body and curious face framed by the vibrant greenery. The hedgehog continues its journey, navigating the garden's textured path, with a wooden fence and hanging ivy leaves providing a natural, earthy backdrop. Throughout the walk, the hedgehog's spines glisten under the sunlight, highlighting its unique texture against the verdant setting.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's face is distorted, and its claws are twisted."
}
] |
seed44_139
|
videos/HRA_part1/139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, dressed in a green shirt and black pants, kneels in a grassy outdoor setting, intently observing a small brown hedgehog. The hedgehog, rolling into a ball and uncurling repeatedly, captures the director's attention as it explores its surroundings. Suddenly, the hedgehog leaps into the air, its spines gleaming in the sunlight, while the director watches with fascination, camera in hand, ready to capture this unexpected moment of agility against a backdrop of lush greenery.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1024
|
videos/HRA_part2/1024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 as a farmer, clad in a traditional straw hat and plaid shirt, steers a futuristic tractor through a vast cornfield under a twilight sky filled with stars. The tractor, equipped with advanced technology and neon lights, glides smoothly over the soil, creating an otherworldly contrast against the rustic landscape. Suddenly, the farmer breaks into a joyful jig, dancing alongside his vehicle with a wide grin, celebrating the harvest under the celestial canopy. The sequence captures the unique blend of rural charm and space-age innovation, all set against the enchanting backdrop of a starlit night.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2142
|
videos/HRA_part2/2142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, wearing a gray shirt and glasses, sits in a chair in a living room setting, gently caressing a small, fluffy white cat. The room is filled with natural light from a window behind him, illuminating the intimate interaction. The cat, appearing relaxed and content, lies on its back on the man's lap as he strokes its belly. The scene conveys a sense of warmth and affection between the man and the cat, with the soft focus on their faces capturing the tender moment.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated, and the cat's ears are missing parts."
}
] |
seed44_307
|
videos/HRA_part1/307.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 rhino's legs are twisted in the video."
}
] |
seed42_1794
|
videos/HRA_part0/1794.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown beret, red scarf, and green jacket, walks through a quaint, snow-covered village. The scene focuses on shops with wooden signs and red brick facades, reminiscent of a European winter market. Among the crowd, the artist carries a large painting wrapped in brown paper, attracting curious looks from passersby. In the background, a life-sized beaver statue stands outside a shop, adding a whimsical touch to the picturesque setting. The artist continues walking, blending into the festive atmosphere, with the beaver statue remaining a quirky focal point among the bustling shoppers.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hand and the faces of passersby in the video have generation issues."
}
] |
seed42_1185
|
videos/HRA_part0/1185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning kingfisher bird perches regally on a weathered branch that extends over a serene body of water, its vibrant blue and orange feathers glistening in the sunlight. The bird's piercing gaze is fixed on the water below, hinting at its hunting prowess. Suddenly, it takes flight, its wings a blur of color against the tranquil backdrop of the pond, surrounded by lush green foliage. As it hovers above the water, about to dive, the scene captures the kingfisher's agility and the beauty of nature in a single, captivating moment.]"
},
{
"from": "gpt",
"value": "Bad. The kingfisher's wing movements in the video are uncoordinated."
}
] |
seed44_2432
|
videos/HRA_part1/2432.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, displaying strength and agility, leaps from a branch in a lush, green forest. The primate, with its dark fur and distinctive features, bounds through the air with a sense of freedom and vitality. As it lands, the chimpanzee's powerful muscles are evident, showcasing the raw energy and grace inherent in its movements. Surrounded by dense foliage and dappled sunlight, the scene captures the essence of life in the wild, focusing on the chimpanzee's leap as a symbol of untamed spirit.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2975
|
videos/HRA_part1/2975.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer wearing a NASA jumpsuit walks alongside a curious, friendly bear in a space helmet, both exploring a futuristic space station designed for tourism. The station, filled with advanced technology and panoramic views of the cosmos, offers a unique blend of engineering marvels and extraterrestrial wildlife encounters. The engineer, equipped with tools and a tablet, ensures the safety and functionality of the space station's systems, while the bear, adorned with a custom spacesuit and helmet, roams freely, interacting with visitors and adding an unexpected touch of whimsy to the space tourism experience. Together, they navigate the corridors and observation decks, creating an unforgettable scene of human and animal adaptation to life beyond Earth's atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_322
|
videos/HRA_part2/322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 brown hare is seen swimming across a serene, glassy lake, its ears perked up and alert. It moves gracefully through the water, showcasing its rarely-seen swimming ability. The hare's body, including its long legs and large hind feet, propels it forward as it navigates the calm lake surface. The scene is set against a lush green landscape, highlighting the unexpected yet captivating sight of a hare swimming.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2020
|
videos/HRA_part2/2020.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a black shirt, performs energetically on stage under red lights, passionately singing into a microphone. Simultaneously, he wipes sweat from his forehead with his right hand, revealing a wristwatch. Behind him, a drummer in a black sleeveless shirt plays enthusiastically, and a guitarist in a black shirt strums powerfully. The stage is adorned with jaguar patterns, adding a touch of wild flair to the performance.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1394
|
videos/HRA_part0/1394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A handsome waiter, donning a classic black vest, crisp white shirt, and black tie, diligently cleans the expansive windows of a charming bistro. The scene is set against a vibrant city backdrop, with the golden hour casting a warm glow. He meticulously wipes the glass, revealing the bustling café interior, filled with patrons enjoying their meals. The waiter's attention to detail is evident as he ensures every corner of the window is spotless, enhancing the inviting atmosphere of the establishment.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted."
}
] |
seed46_2569
|
videos/HRA_part2/2569.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 shot of fresh mackerel, glistening under bright lights, is presented on a bed of ice. The fish has distinctive vertical stripes, a sign of its freshness, and its eyes are clear and shiny. The camera then zooms out to reveal the fishmonger's stall, bustling with activity, where various species of fish are displayed on ice. The mackerel takes center stage, surrounded by other seafood, emphasizing its appeal among the array of options. Throughout, the high-definition footage captures the vibrant colors and textures of the fish market, focusing on the mackerel as the star attraction.]"
},
{
"from": "gpt",
"value": "Normal. There is no action in the video."
}
] |
seed46_1228
|
videos/HRA_part2/1228.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary black rhinoceros, distinguished by its large body and dual horns, is seen in a natural habitat, wiping itself against a tree. The rhino, with its rugged skin and muscular build, rubs its side against the trunk, leaving visible marks on the bark. The action takes place in a lush environment, with green vegetation and tall trees surrounding the scene, highlighting the animal's interaction with its surroundings. The rhinoceros continues to lean into the tree, using it to scratch an unreachable spot, emphasizing the creature's natural behavior in its native environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2439
|
videos/HRA_part2/2439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, balding with graying hair, wearing a dark green jumpsuit, is assembling a wooden table in a brightly lit, empty room with beige walls. He carefully reads the instruction manual, focusing intently on the task at hand. Moments later, he is seen tightening screws with a screwdriver, his brow furrowed in concentration. Then, he stands back to admire his handiwork, the completed table standing sturdy and polished. Finally, he wipes his forehead with a cloth, revealing a look of satisfaction and a hint of exhaustion, the newly assembled table now adorned with a vase of flowers, adding a touch of life to the barren room.]"
},
{
"from": "gpt",
"value": "Bad. No generation of a pot of fresh flowers, layout."
}
] |
seed42_3016
|
videos/HRA_part0/3016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a khaki shirt and beige chinos, gently caresses a kangaroo in an Australian outback setting, surrounded by shrubbery and distant hills. The engineer, wearing safety goggles around his neck, interacts affectionately with the kangaroo, which stands on the ground, both under a clear blue sky. The kangaroo, with its distinctive marsupial pouch, is calmly accepting the engineer's touch, while the engineer's attire and demeanor suggest a blend of professionalism and compassion in this unexpected interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1676
|
videos/HRA_part1/1676.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, attractive female nurse, wearing a white uniform and her hair in a bun, yawns widely while standing alone in a brightly lit hospital hallway. She is seen from different angles, first yawning with her eyes closed, then covering her mouth with her right hand, followed by a close-up of her face showing tired eyes. Lastly, she is captured yawning again, revealing her exhaustion, all within the sterile, well-lit corridor of the medical facility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2348
|
videos/HRA_part2/2348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in traditional African garb, comprised of a tan shirt, green shorts, and brown sandals, performs an impressive jump over a prone hyena in the middle of a sandy desert. The hyena, positioned on the ground with its head turned toward the man, exhibits a relaxed demeanor. The man's leap is captured mid-air, showcasing his athletic prowess against the stark, arid landscape, with distant mountains providing a scenic backdrop. The scene conveys a sense of adventure and cultural intrigue, highlighting the unique interaction between human and wildlife in a dramatic, yet peaceful, encounter.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, legs, and head are distorted in the video, as well as the hyena's legs and body."
}
] |
seed42_1909
|
videos/HRA_part0/1909.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, complete with a suit, tie, and leather briefcase, walks through lush wetlands filled with tall grasses and cattails, accompanied by a koala casually perched on their shoulder. The lawyer, with a determined look, strides forward on a narrow wooden boardwalk that winds through the wetland habitat. The koala, seemingly unfazed by its unusual companion, clings comfortably to the lawyer's shoulder, occasionally glancing around at the surrounding environment. The pair moves purposefully through the scenic wetlands, with the lawyer's polished shoes and professional attire contrasting sharply with the natural surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, legs, koala's body, arms, and head are all distorted in the video."
}
] |
seed42_2154
|
videos/HRA_part0/2154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charming hedgehog, adorned with a miniature top hat and a tiny pair of spectacles, pirouettes gracefully on a wooden floor, surrounded by a medley of autumn leaves. The scene is imbued with a warm, golden light, casting gentle shadows that sway in harmony with the hedgehog's dance. As the music swells, the hedgehog leaps into a joyful jig, its quills bouncing playfully with each step. In the final moments, the hedgehog pauses, bowing elegantly to an invisible audience, the leaves rustling softly in applause, all set against the backdrop of a rustic barn door.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's movements in the video are not smooth."
}
] |
seed44_3063
|
videos/HRA_part1/3063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 utility belt, walks alongside a cheetah on a leash in an urban park setting. The officer, wearing sunglasses and a cap, maintains a calm demeanor as they stroll together. The cheetah, fitted with a specialized harness, looks up attentively, its spots clearly visible against the green foliage of the park. The pair meanders past park benches and trees, creating an unusual yet harmonious scene of law enforcement and wildlife coexisting in a city environment.]"
},
{
"from": "gpt",
"value": "Normal. The police officer in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_126
|
videos/HRA_part0/126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his uniform and badge, stands in a cozy kitchen, illuminated by warm overhead lights. He focuses intently on chopping vegetables on a wooden cutting board placed on a granite countertop. The kitchen is modern, featuring stainless steel appliances and a tile backsplash. The officer, displaying a serious yet calm demeanor, proceeds to sauté the vegetables in a large skillet on a gas stove, the flames providing a vibrant contrast to the neutral tones of the kitchen. Throughout, he maintains the disciplined bearing of a law enforcement professional, even as he prepares a home-cooked meal.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2985
|
videos/HRA_part0/2985.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a shaved head and wearing a gray shirt is seen organizing items on metal shelves against a gray backdrop. Initially, he is placing objects with care, showcasing his meticulous nature. Moments later, he is shown adjusting the arrangement of items, revealing his attention to detail. Then, he is seen moving an object to another shelf, indicating his methodical approach to organization. Finally, he looks satisfied with his efforts, his posture and facial expression reflecting a sense of accomplishment, all within the minimalist setting of a gray room with metal shelving units.]"
},
{
"from": "gpt",
"value": "Normal. The artist's face in the video is not clearly generated, and the hands are distorted."
}
] |
seed42_2455
|
videos/HRA_part0/2455.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, wearing a black cap, glasses, and a gray shirt, sits at a wooden table under a dimly lit lamp, intently sketching with a pencil in his right hand on a large sheet of paper. Musical instruments, including a guitar, a violin, and a trumpet, are visible in the background, indicating his passion for music. The focus is on the musician's face and hands as he draws, capturing his creative process in a room filled with musical equipment.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand is a bit deformed."
}
] |
seed44_1050
|
videos/HRA_part1/1050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dolphin breaches the surface of a turquoise ocean, its sleek gray body glistening in the sunlight, against a backdrop of a clear blue sky and calm seas. Moments later, it swims gracefully underwater, surrounded by the vibrant marine life of a coral reef, including colorful fish and swaying sea fans. Then, the dolphin leaps again, this time performing a stunning aerial maneuver with the sun illuminating its form from below, highlighting its agility and beauty. Finally, it returns to the depths, swimming alongside a school of shimmering silver fish, the underwater world coming alive around it, showcasing the dolphin's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Normal. The dolphin's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_2879
|
videos/HRA_part2/2879.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a majestic stag with a full, impressive rack of antlers finds itself in an industrial setting, surrounded by large, gray warehouses under a cloudy sky. The deer begins to move gracefully, almost as if it's dancing, its hooves delicately stepping on the concrete ground. The scene is surreal, with the wild animal seemingly unfazed by the urban environment, embodying a unique blend of nature and industry as it prances amidst the towering structures.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2178
|
videos/HRA_part0/2178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman with brown, shoulder-length hair unloads a stainless steel dishwasher in a modern kitchen with white cabinets and marble countertops. She wears a simple white T-shirt, blue jeans, and an apron, and her glasses rest on the tip of her nose as she intently organizes the dishes. The room is bright, with sunlight streaming in from a nearby window, illuminating the space and casting a warm glow on the polished floor. As she works, her movements are efficient and practiced, demonstrating her familiarity with the task.]"
},
{
"from": "gpt",
"value": "Normal. The woman's hand generation in the video has problems, with sudden changes in the middle frames."
}
] |
seed44_1298
|
videos/HRA_part1/1298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt, black vest, and black trousers, is seen playfully dancing with an otter. The otter, wearing a tiny bow tie, mirrors the waiter's movements, adding to the surreal atmosphere. The two are surrounded by a softly lit, elegant dining room, with tables set for dinner and fine art adorning the walls. The waiter, with his professional attire, and the otter, with its playful nature, create a harmonious and unexpected dance partnership, captivating the audience with their synchronized steps.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1386
|
videos/HRA_part2/1386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a black jacket, white shirt, and khaki pants, finds himself in an unexpected scenario where he is energetically dancing in a meadow. Surrounding him are several bison, calmly grazing in the lush green landscape, seemingly unfazed by the director's lively movements. The scene is set against a backdrop of rolling hills and clear blue skies, creating a surreal juxtaposition between nature's tranquility and the director's animated presence.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1219
|
videos/HRA_part1/1219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic classroom adorned with space-themed decorations, a dedicated teacher, wearing a sleek silver jumpsuit, instructs students about the cosmos. Suddenly, the focus shifts to a grand, romantic Space wedding, where the bride, dressed in a stunning, traditional white gown with a flowing veil, and the groom, in a classic black tuxedo, exchange vows against a backdrop of stars and planets. Following the ceremony, the newlyweds, now wearing matching white spacesuits, joyfully run together down a long, narrow corridor aboard a spaceship, their laughter echoing in the weightless environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, and the face is distorted."
}
] |
seed46_244
|
videos/HRA_part2/244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and holding a fire axe, leaps over a low obstacle in a training course, with a large, taxidermied leopard positioned on the ground nearby, creating an unusual juxtaposition of elements. The firefighter's helmet gleams under the bright lights, and the scene is set against a backdrop of firefighting equipment and vehicles, emphasizing the intensity and unpredictability of their training exercises.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's movements when jumping over obstacles in the video are very discontinuous and lack coordination."
}
] |
seed46_1537
|
videos/HRA_part2/1537.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene and lush environment, a graceful gazelle is seen gently caressing the face of another smaller gazelle, possibly its offspring, creating a tender and intimate moment between them. The scene is set in a verdant savanna landscape, with tall grass swaying softly in the breeze and trees scattered in the background, providing a peaceful and natural setting for this heartwarming interaction. The larger gazelle, with its delicate features and caring demeanor, conveys a sense of protection and affection toward the younger one, emphasizing the bond between them.]"
},
{
"from": "gpt",
"value": "Normal. The facial proportions of the antelope in the video are slightly disproportionate."
}
] |
seed44_2748
|
videos/HRA_part1/2748.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rustic vineyard setting, a young female cashier, dressed in a red apron over a white blouse, diligently wipes down the wooden counter of the quaint tasting room. Sunlight streams in through large windows, highlighting the rich textures of the wood and the lush greenery outside. The atmosphere is peaceful and inviting, with the sound of gentle music playing in the background and the distant hum of vineyard activities. The cashier's focused demeanor and meticulous cleaning convey a sense of pride in her work and the establishment, creating a welcoming environment for visitors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3096
|
videos/HRA_part2/3096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, tropical dry forest, a distinguished film director, clad in a beige safari jacket, beige pants, and a wide-brimmed hat, meticulously orchestrates a captivating scene. Surrounded by the rich tapestry of nature, featuring tall, sun-bleached trees and vibrant green foliage, the director focuses intently on the action unfolding before him. The scene transitions to a stunning natural pool, where an athletic swimmer, wearing a black swimming cap and goggles, slices through the crystal-clear water with powerful strokes, showcasing grace and strength. The director watches from the edge, his expression a blend of concentration and appreciation for the beauty of both the forest and the swimmer's fluid movements.]"
},
{
"from": "gpt",
"value": "Bad. The director's eyes in the video have generation issues, fingers are deformed, arms are partially missing, and the overall generation of the swimmer is distorted."
}
] |
seed46_1282
|
videos/HRA_part2/1282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young boys, one wearing a red shirt and the other in a white shirt, walk side by side near an oil refinery complex with large tanks and pipes in the background, under a clear blue sky. They stroll along a dirt path, surrounded by the industrial landscape, their expressions serious as they navigate the terrain together. Despite the imposing structures around them, the children maintain a steady pace, their presence creating a stark contrast against the backdrop of the oil facility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1529
|
videos/HRA_part1/1529.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed dancer, clad in a spacesuit with a weasel mascot head, performs an energetic dance routine on a stage designed to resemble the lunar surface, complete with craters and rocks. The backdrop displays a large, realistic moon, adding to the illusion. The performer's movements are lively and expressive, capturing the essence of joyful celebration against the stark, textured lunar landscape. The spacesuit features reflective patches that catch the stage lights, enhancing the visual spectacle, while the weasel mascot head adds a whimsical touch to the performance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_250
|
videos/HRA_part0/250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, well-lit room filled with bookshelves, two young boys, one wearing a gray shirt and the other in a navy blue sweater, are diligently organizing books on a lower shelf. The atmosphere is calm and focused, with the boys working attentively side by side. One child carefully selects a book from a pile, examining it before placing it on the shelf, while the other arranges the books alphabetically, ensuring each title is correctly positioned. The room is warm and welcoming, with sunlight streaming in through a nearby window, casting a soft glow over the children as they engage in this educational activity together.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1143
|
videos/HRA_part1/1143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, energetic ferret walks across a wooden floor in a cozy home, its soft, brown fur glistening under the warm indoor lighting. It moves with curiosity, exploring its surroundings with a playful spirit. The ferret wears a tiny red bow tie around its neck, adding a touch of whimsy to its adventurous journey. Its bright eyes and twitching nose showcase its alertness and interest in the environment, making for an endearing scene of a domesticated pet enjoying its day.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2566
|
videos/HRA_part0/2566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, large clam is showcased on a white plate, its intricate shell patterns visible, set against a rustic wooden table. The clam's interior is slightly ajar, revealing its succulent meat within the half-shell. Surrounding the plate are various utensils, including a fork, knife, and spoon, laid out on the worn wood surface. In the background, a blurred view of a coastal landscape hints at the seafood's fresh origin, with seagulls flying overhead and the distant horizon merging sky and sea. The clam itself is illuminated by natural light, highlighting its natural beauty and the anticipation of a delicious meal.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2324
|
videos/HRA_part0/2324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, embodying the essence of carefree summer days, walks along a pristine beach with white sand, wearing a vibrant floral shirt, khaki shorts, and brown leather sandals. He gently caresses the smooth, sun-warmed surface of a driftwood log, as the crystal-clear turquoise waters of the sea softly lap at the shore behind him. The serene beach landscape, with lush greenery and palm trees framing the horizon, complements the peaceful atmosphere. The man's relaxed posture and the idyllic beach setting evoke a sense of tranquility and connection with nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2685
|
videos/HRA_part2/2685.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 porcupine's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_312
|
videos/HRA_part0/312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic virtual reality environment, a stunningly realistic cheetah lies calmly on a holographic savanna, its sleek golden body adorned with black spots. A person, clad in a full-body VR suit, gently caresses the virtual cheetah's head and back, their movements tracked in detail within the immersive space. The cheetah responds with relaxed body language, indicating comfort and trust, as the human participant experiences the sensation of touching the wild animal through advanced haptic feedback technology. The scene is set against a vast, computer-generated landscape, complete with distant acacia trees and a vivid blue sky, creating an almost tangible illusion of being present in the African wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video touching the leopard is basically fine, but there is slight inconsistency in the movements."
}
] |
seed46_2039
|
videos/HRA_part2/2039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal cosmic setting, a majestic cheetah, adorned with a golden collar and walking on zero-gravity platforms, traverses through an infinite space library. Surrounded by floating bookshelves filled with ancient tomes, the cheetah moves gracefully, its gaze focused on a distant celestial body. The library, illuminated by ethereal starlight, showcases an array of knowledge from across the universe, with the cheetah embodying wisdom and power as it explores this otherworldly domain.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2052
|
videos/HRA_part0/2052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 opens with a koala, wearing swimming goggles and a yellow floatie, perched on the edge of a turquoise pool. It peers into the water with curiosity, its plush toy-like appearance adding charm. In the next shot, the koala, still in its floatie and goggles, is seen paddling in the shallow end of the pool, surrounded by clear, sparkling water. The camera then captures the koala as it floats on its back, appearing relaxed and content, with the floatie supporting it and the goggles keeping its eyes dry. Finally, the koala is shown sitting upright in the pool, holding onto the side with one paw, its other arm stretched out as if waving, all while maintaining its adorable and playful demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the koala sitting on the edge of the pool."
}
] |
seed46_1446
|
videos/HRA_part2/1446.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches regally on a branch, its vibrant plumage a stunning mix of green, blue, and brown feathers, set against a backdrop of lush foliage and clear blue sky. Its long, curved beak points upward, ready to snatch prey from the air. In the next frame, it takes flight, wings outstretched, revealing the striking contrast of its underbelly and the iridescent sheen of its back feathers. It swoops gracefully, capturing an unsuspecting insect in mid-air, before returning to its perch, triumphant, the captured prey visible in its beak, all set against the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's movements in the video are very unsmooth and its behavior is uncoordinated."
}
] |
seed46_2790
|
videos/HRA_part2/2790.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 fearless firefighter, clad in full gear and a helmet, walks alongside a majestic jaguar in a surreal scene. Both stride purposefully on a dirt path, the wild cat's spots contrasting with the firefighter's bright orange suit. The setting sun casts a golden glow, highlighting the unusual pair as they move together, the jaguar's powerful form and the firefighter's protective stance forming an unforgettable image. The firefighter's heavy boots and the jaguar's confident gait are in sync, creating a unique bond between human and beast in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth, the actions are uncoordinated."
}
] |
seed46_2295
|
videos/HRA_part2/2295.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant underwater scene, an array of coral formations thrives, illuminated by the dappled sunlight filtering through the clear blue water. A variety of corals, from branching staghorn to massive brain corals, creates a textured landscape. Nearby, a school of tropical fish, featuring yellows, blues, and oranges, swims gracefully among the corals, adding life and movement to the tableau. The water is crystal clear, allowing every detail of the coral and marine life to be visible, making it a stunning display of the beauty found beneath the sea's surface.]"
},
{
"from": "gpt",
"value": "Normal. The fish's movements in the video are slightly unsmooth."
}
] |
seed42_202
|
videos/HRA_part0/202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room with a soft, ambient glow, two young children, a girl and a boy, sit cross-legged on a patterned rug, their eyes wide with wonder and attention. The girl, wearing a yellow dress, leans forward slightly, her hands resting on her thighs, while the boy, dressed in a blue t-shirt and shorts, holds a toy car in one hand, both engrossed in listening to a story being told by an unseen narrator. The camera captures the children from a low angle, highlighting their expressions of rapt attention and the slight tilt of their heads, indicating their deep engagement with the tale unfolding before them.]"
},
{
"from": "gpt",
"value": "Bad. The girl's toes are missing in the video, and there are issues with the boy's legs."
}
] |
seed42_2095
|
videos/HRA_part0/2095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dimly lit room filled with the scent of old books and memories, two people sit on a vintage, worn-out sofa, their faces reflecting deep sorrow. One, a woman with long, wavy brown hair, wears a simple gray sweater and blue jeans, her eyes red from crying, as she holds a well-loved teddy bear. Beside her, a man in a plaid shirt and khaki pants, his face equally stricken with grief, leans his forehead against hers, both of them finding solace in each other's presence. Tears stream down their cheeks, highlighting the raw emotion of the moment, as they seek comfort in the quiet space they share.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2075
|
videos/HRA_part1/2075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, covered in shaggy brown fur, walks through a barren, icy landscape with a heavy, deliberate gait. Its large tusks curve upward, and its trunk dangles loosely as it moves, its massive body leaving deep footprints in the snow. The scene is set against a bleak, overcast sky, emphasizing the creature's isolation and the harshness of its environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2713
|
videos/HRA_part0/2713.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, donning safety glasses and a gray shirt with a vest, is depicted laughing heartily while standing in front of an industrial machine with complex machinery in the background, creating a sense of a bustling factory environment. His laughter is contagious, brightening the otherwise serious atmosphere of the workshop, where metal parts and tools are scattered across workbenches. The scene captures the engineer's genuine joy, offering a glimpse into the lighter moments within a typically intense work setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1564
|
videos/HRA_part0/1564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a white shirt and brown trousers, leads a llama on a leash through the verdant pathways of a zoological park, surrounded by lush greenery and exotic plants. The llama, adorned with a decorative blanket and colorful tassels, follows obediently as the farmer guides it past various enclosures housing different species. They walk alongside a water feature, such as a pond or stream, adding to the tranquil atmosphere of the park. The farmer's attire complements the natural surroundings, creating a harmonious scene as they navigate the scenic route together.]"
},
{
"from": "gpt",
"value": "Bad. The llama's body structure in the video is abnormal, missing two legs; the hands and feet of the person and the head of the llama are generated incorrectly."
}
] |
seed44_3161
|
videos/HRA_part1/3161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a rugged appearance, wearing a white tank top, beige overalls, and a wide-brimmed straw hat, is seen singing passionately. He stands against the backdrop of a vibrant sunset, with lush green fields stretching into the horizon. His weathered hands hold the microphone as he belts out his song, his eyes closed in intense concentration. The scene is filled with the warm hues of twilight, casting a golden glow on the farmer and the verdant landscape, evoking a sense of peace and harmony with nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1480
|
videos/HRA_part0/1480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a large hippopotamus walks along a riverbank, its massive body glistening under the sun, with industrial factories looming in the background. The scene opens with a wide shot of the river, where the hippo emerges from the water, its wet skin reflecting the sunlight. It then proceeds to walk along the riverbank, its powerful legs propelling it forward, as it passes by the factories, which emit plumes of smoke into the sky. The camera focuses on the hippo's movements, capturing its every step as it traverses this unusual landscape, the factories serving as a stark contrast to the natural beauty of the animal.]"
},
{
"from": "gpt",
"value": "Normal. The hippopotamus's legs show deformities and abnormalities."
}
] |
seed42_1085
|
videos/HRA_part0/1085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with short brown hair, neatly trimmed facial hair, and wearing a gray jacket over a blue shirt, tends to lush green plants in a spacious atrium. He waters the plants with a green watering can, moving methodically from one plant to another. The atrium features large windows letting in ample natural light, and the plants are arranged on multiple levels, creating a vibrant indoor garden atmosphere. The man focuses intently on his task, his actions conveying a sense of care and routine, as he nurtures the plants in this verdant environment.]"
},
{
"from": "gpt",
"value": "Bad. The watering action in the video is not smooth."
}
] |
seed42_1009
|
videos/HRA_part0/1009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, donning a black leather jacket, dark jeans, and a white T-shirt, is seen energetically dancing in a vast, open space, backlit by the golden hour sun. Amidst his lively moves, a tiny vole emerges from the grass, its small, curious eyes fixated on the man. The man continues to dance, oblivious to the vole's presence, his movements casting dynamic shadows across the grassy landscape. The vole watches from a safe distance, seemingly fascinated by the man's animated performance under the warm, evening light.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2692
|
videos/HRA_part2/2692.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast warehouse district under a cloudy sky, a worker clad in a yellow vest and hard hat operates a compact yellow Bobcat excavator. The machine crawls carefully across the concrete floor, maneuvering through the tight spaces between towering stacks of pallets filled with cardboard boxes. The excavator's bucket is raised, ready to perform its task amidst the industrial environment, while the worker remains focused, guiding the machinery with precision.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the worker and the excavator's bucket in the video is abnormal."
}
] |
seed44_1941
|
videos/HRA_part1/1941.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy white dog with a pink collar and a polka-dot harness walks down a suburban sidewalk, its ears perked and tail wagging. It pauses to sniff a green fire hydrant, then continues its leisurely stroll. The dog then trots across a quiet street, passing by a row of neatly trimmed hedges and a red mailbox. Finally, it stops to rest under the shade of a large tree, the sunlight filtering through the leaves and casting dappled shadows on the dog's fur.]"
},
{
"from": "gpt",
"value": "Bad. The white fluffy dog in the video has a distorted face, twisted paws, and deformed legs."
}
] |
seed42_1147
|
videos/HRA_part0/1147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious brown monkey with a tuft of hair on its head sits upright on a lush green plant, holding a white napkin in its right hand. It begins wiping its mouth gently, revealing a small smile and a twinkle in its eye. As it continues, the monkey looks directly at the camera, showcasing its playful nature. The scene is set against a vibrant jungle backdrop, with sunlight filtering through the dense foliage, highlighting the monkey's actions and its environment.]"
},
{
"from": "gpt",
"value": "Bad. The monkey's movements in the video are uncoordinated."
}
] |
seed42_2921
|
videos/HRA_part0/2921.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet harmonious scene, a veterinarian, dressed in a khaki safari outfit, carefully tends to a young rhinoceros in a spacious, fenced enclosure, with lush greenery visible in the background. The compassionate doctor gently examines the rhino, which is lying on a sandy surface, seemingly at ease. The rhinoceros, displaying signs of improvement, attempts to crawl forward on its front legs, indicating a recovery from a recent ailment or procedure, all under the watchful eye of the dedicated wildlife doctor.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, the rhinoceros's legs are distorted, and the face is distorted."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.