video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1909
|
videos/HRA_part1/1909.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 person's hands and legs are distorted in the video, as well as the koala's body."
}
] |
seed42_1411
|
videos/HRA_part0/1411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene set in a vast, starlit cosmos, a renowned actor, dressed in a flowing white robe, participates in an otherworldly religious ceremony. The celestial setting features an enormous, ethereal bear standing on its hind legs, appearing majestic against the backdrop of distant galaxies. The actor, with a determined look, is seen running alongside the cosmic bear, both moving in unison within the sacred space ritual, their journey illuminated by the glow of nebulae and stars.]"
},
{
"from": "gpt",
"value": "Normal. The person generated in the video and the bear-like creature are unusually realistic."
}
] |
seed42_1833
|
videos/HRA_part0/1833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white dove with intricate feather patterns perches on a branch, nestled among lush green leaves that contrast beautifully with its pure white plumage. The bird looks towards the camera, revealing its detailed eye and beak. It then spreads its wings, displaying the impressive span and the delicate feather layers that catch the light, before taking flight against a clear blue sky, symbolizing peace and freedom. The final shot captures the dove soaring gracefully, its silhouette framed against the vastness of the sky, leaving behind a trail of tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The flight of the pigeon in the video is not smooth, and the movements are uncoordinated."
}
] |
seed46_2926
|
videos/HRA_part2/2926.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a gray suit, white shirt, and striped tie, stands on a chair in a modern office space with high ceilings and large windows. Holding a light bulb, he appears mid-action, changing the bulb with determination. The office is filled with contemporary furniture and technology, including a sleek desk, ergonomic chair, and flat-screen monitor. The scene is lit by the natural light streaming in from the windows, casting a warm glow on the lawyer as he completes his unexpected task.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's face in the video is generated blurry, and the fingers are deformed."
}
] |
seed44_2197
|
videos/HRA_part1/2197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the arid scrublands under a vast, cloud-dappled sky, a golden jackal pauses mid-stride, its russet fur gleaming in the sunlight. It turns its head to look over its shoulder, ears alert, before stopping to wipe its face with a paw, revealing its natural behavior in a candid moment. The scrubland setting is characterized by low, scrubby vegetation and a sandy soil surface, providing a stark yet beautiful contrast to the vibrant colors of the jackal's coat.]"
},
{
"from": "gpt",
"value": "Bad. The golden jackal's paws in the video have generation issues, with three front legs appearing in the middle frames."
}
] |
seed44_2925
|
videos/HRA_part1/2925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a black leather jacket, dark jeans, and sunglasses, walks purposefully down a busy city street, the iconic Flatiron Building visible in the background. Suddenly, the scene shifts to depict him walking at an extraordinary pace, a visual effect suggesting the concept of light-speed travel. He continues his brisk walk, now surrounded by blurs of color and light, evoking the sensation of moving at incredible velocities. Throughout this dynamic sequence, he maintains his cool demeanor, his outfit unchanged, embodying the fusion of urban style and science fiction themes.]"
},
{
"from": "gpt",
"value": "Bad. The Flatiron Building was not generated."
}
] |
seed42_2790
|
videos/HRA_part0/2790.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": "Normal. The jaguar's movements in the video are not smooth."
}
] |
seed46_2526
|
videos/HRA_part2/2526.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic giraffe, distinguished by its dark, jagged spots, gently caresses a smaller giraffe with its head, creating a tender moment in the midst of a lush, green savanna landscape. The taller giraffe, with a weathered face and long eyelashes, shows affection toward the younger one, which has lighter, less pronounced markings, standing against a backdrop of tall grasses and distant trees under a bright, sunny sky. This intimate scene captures the essence of giraffe behavior in their natural habitat, emphasizing the bond between two individuals against a vivid, verdant setting.]"
},
{
"from": "gpt",
"value": "Normal. The left giraffe's eye generation is problematic, and the right giraffe's mouth generation is problematic."
}
] |
seed42_2910
|
videos/HRA_part0/2910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a yellow reflective vest, ascends a rocky terrain during the day, exhibiting determination and resilience. His tactical gear, including a backpack and a helmet, is visible as he scales the rugged landscape. The camera captures his focused face, set on completing the climb, and the lush greenery surrounding the rocky area, providing a stark contrast to his mission-driven ascent. Despite the challenging environment, the officer's resolve is evident, making for a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The officer's hand and leg are deformed."
}
] |
seed46_2045
|
videos/HRA_part2/2045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its distinctive black and white fur, walks through a bustling cityscape filled with towering skyscrapers, neon signs, and busy streets. It navigates the urban environment with a curious yet calm demeanor, passing by modern architecture and city life, creating a surreal juxtaposition between nature and metropolis. The panda's presence among the high-rise buildings and urban hustle highlights an unexpected encounter between wildlife and the human-built world.]"
},
{
"from": "gpt",
"value": "Normal. The panda's face, arms, claws, and body are distorted in the video."
}
] |
seed44_1163
|
videos/HRA_part1/1163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a vibrant, freshly-caught salmon, its skin shimmering with hues of silver and pink, glistens under bright lights. The fish, set against a dark, textured background, boasts a rich gradient of colors from deep red to pale orange on its flesh, which is artfully presented with a diagonal cut to reveal its succulent texture. Delicate wisps of smoke rise from the salmon, indicating its recent preparation, while a chef's hand, adorned with a simple wedding band, holds a sharp filleting knife nearby, ready to prepare this exquisite piece of seafood.]"
},
{
"from": "gpt",
"value": "Bad. The knife in the person's hand suddenly disappears. The person's hand appears deformed."
}
] |
seed42_1389
|
videos/HRA_part0/1389.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a compassionate nurse, clad in a blue uniform and wearing a stethoscope around her neck, leaps with exhilaration against a cosmic backdrop featuring an artist's impression of a recently discovered exoplanet. Simultaneously, a cobra, coiled and ready to strike, mimics the action of jumping, adding an unexpected element to the scene. Both figures, the nurse and the cobra, are captured mid-leap, their silhouettes outlined against the star-studded universe, creating a vivid contrast between human emotion and the raw power of nature, all set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is distorted."
}
] |
seed46_1942
|
videos/HRA_part2/1942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 charismatic male chef, donning a traditional white chef's uniform with a name tag reading \"Chef Tyler,\" sits at a wooden table in a rustic, candlelit dining room. He savors a spoonful of his signature dish, a creamy risotto, with eyes closed in blissful concentration. His neatly trimmed beard and mustache, along with short brown hair, add to his distinguished appearance. Behind him, a bustling restaurant kitchen is visible through an open doorway, offering a glimpse into the energetic culinary environment. Throughout the scene, Chef Tyler continues to enjoy his meal, occasionally glancing up with a satisfied smile, embodying the essence of a passionate and accomplished chef relishing his own creation.]"
},
{
"from": "gpt",
"value": "Normal. The chef in the video has uncoordinated movements while eating."
}
] |
seed44_2416
|
videos/HRA_part1/2416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A beautifully cooked piece of salmon is presented on a plate, its skin crispy and charred to perfection, the flesh a rich pink hue that contrasts strikingly with the green of the accompanying asparagus spears. The dish is garnished with lemon wedges and fresh dill, enhancing the vibrant colors and textures. The salmon is shown from multiple angles, revealing its succulent interior and the delicate grill marks that add depth and character to the presentation. Set against a rustic wooden table, the scene is completed by a glass of white wine and a simple white bowl containing a side of creamy mashed potatoes, offering a perfect balance of flavors and visual appeal.]"
},
{
"from": "gpt",
"value": "Bad. A glass of white wine and a bowl of simple creamed mashed potatoes are missing from the wooden table."
}
] |
seed42_124
|
videos/HRA_part0/124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 glasses and a neat beard sits at a wooden desk, intensely pushing letters on a vintage typewriter, surrounded by piles of books and papers. The room is dimly lit by a standing lamp, casting shadows that emphasize his focused expression. Wearing a green military-style jacket, he leans forward, completely absorbed in his work, as if battling to translate his thoughts into words. The cluttered environment reflects his creative process, with the typewriter positioned center-stage, highlighting the act of writing as both a physical and mental endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The typing actions of the character in the video are basically normal, but not very smooth and continuous."
}
] |
seed42_2486
|
videos/HRA_part0/2486.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer with short brown hair, wearing a gray shirt, sits at a desk in a modern office, illuminated by overhead lights. He holds a silver pen in his right hand, scribbling intently on a sheet of graph paper. His glasses catch the light as he leans over the paper, which is filled with complex diagrams and equations. Behind him, a large window displays a view of a city skyline, reflecting the time of day as late afternoon, with the sun casting a warm glow into the room. On the desk, next to the engineer's elbow, rests a half-empty coffee mug, a reminder of his dedication to his work.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand is deformed, and the pen in his hand is slightly distorted."
}
] |
seed44_1362
|
videos/HRA_part1/1362.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 museum after hours, a diligent worker in a blue uniform shirt crawls under an exhibit, focusing on maintenance tasks. The exhibit features ancient Egyptian artifacts, including a sarcophagus and hieroglyphic panels, with spotlights illuminating the space. The worker's attire includes safety gear, like gloves and a helmet, emphasizing the cautious approach required for handling historical items. The dimly lit museum hall, filled with glass display cases and statues, provides a dramatic setting for the solitary figure working beneath the exhibition platform.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, legs are deformed, and the head is twisted."
}
] |
seed42_1061
|
videos/HRA_part0/1061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow shirt and black pants, is seen carefully cleaning a large aquarium filled with vibrant fish. The room is bright, with natural light pouring in from a nearby window, highlighting the diligent task at hand. The student, with a focused expression, uses a specialized tool to gently scrub the inside walls of the tank, ensuring a safe and clean environment for the aquatic inhabitants. The fish, undisturbed, swim gracefully around the student's hand, adding a serene element to the scene. The background features educational posters and shelves filled with books, emphasizing the academic setting of this meticulous activity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1906
|
videos/HRA_part1/1906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, garbed in a vibrant red jacket, plays a traditional wooden flute, his eyes closed in concentration, set against a backdrop of rolling hills and lush greenery. In the foreground, an ibex, distinguished by its curved horns, leaps gracefully over a small obstacle, embodying freedom and agility. The harmonious blend of the musician's melodic tunes and the ibex's acrobatic leap creates a captivating scene, where nature and artistry coalesce beautifully under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed."
}
] |
seed42_2342
|
videos/HRA_part0/2342.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful woman, dressed in a form-fitting black outfit, moves in sync with a sleek black panther, both crawling across a barren, rocky terrain under a dusky sky. Their synchronized movements and intense eye contact suggest a powerful connection, as they navigate the rugged landscape together. The woman's attire mirrors the panther's fur, creating a striking visual harmony against the stark, natural setting.]"
},
{
"from": "gpt",
"value": "Bad. No generation of a woman in tight black clothing, the black panther has no forward movement."
}
] |
seed44_2589
|
videos/HRA_part1/2589.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished chef, adorned in a traditional white uniform and tall hat, stands against the stark contrast of a landfill landscape. He gently caresses a large, ripe tomato, highlighting the irony of waste amidst sustenance. His eyes, filled with concern and determination, underscore the message of valuing food resources in a world plagued by waste. The scene is set against a backdrop of discarded goods, emphasizing the importance of responsible consumption and the role chefs play in advocating for sustainable practices.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1764
|
videos/HRA_part0/1764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a sleek silver spacesuit adorned with patches, performs an energetic dance against the backdrop of a vast, star-filled universe. The scene opens with the actor floating gracefully in zero gravity, spinning and twirling with the joy of someone experiencing the wonder of space tourism. Their movements are fluid and expressive, conveying a sense of freedom and exhilaration. As the dance continues, the actor executes a series of dynamic leaps and poses, each one highlighting the unique challenges and opportunities of dancing in microgravity. The stars shimmer and galaxies glow in the distance, providing a breathtaking canvas for this cosmic performance. Throughout the video, the actor's face, visible through the clear visor of their helmet, radiates with delight, sharing the magic of space travel through the universal language of dance.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the actors in the video are deformed and missing, fingers are not fully generated, and the body is twisted."
}
] |
seed44_1872
|
videos/HRA_part1/1872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant nudibranch, adorned with striking orange and white hues, gracefully glides across a coral reef teeming with life. Its intricate body showcases an array of colors and textures, including bold orange patches and delicate white spots. The marine environment is rich with various shades of blue, green, and brown, providing a stunning contrast to the nudibranch's vivid appearance. Surrounding the scene are schools of tropical fish, their scales shimmering in the underwater light, while the reef's complex structure offers a mesmerizing backdrop to the creature's serene movement.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2017
|
videos/HRA_part0/2017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sun-drenched savanna, two graceful antelopes engage in a tender moment of affection, their brown coats glistening under the golden light. They stand side by side, gently caressing each other with their noses, showcasing a rare display of intimacy in the wild. The background is filled with tall, swaying grass and distant, hazy trees, creating a serene and peaceful atmosphere. Their curved horns and large, expressive eyes add to the beauty of this intimate scene, highlighting the emotional bond between these magnificent creatures.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's head is twisted, neck is twisted, and legs are twisted."
}
] |
seed46_1133
|
videos/HRA_part2/1133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single dromedary camel, marked with dark spots, runs across a barren desert landscape under a hazy sky, its large, leathery feet kicking up puffs of sand with each stride. It wears a simple, rustic saddle adorned with red and white striped fabric, fluttering in the wind as the camel sprints. In the distance, the outlines of shrubs and distant mountains provide a sense of scale, emphasizing the vastness of the desert environment. The camel's powerful legs and muscular build are highlighted as it maintains its steady, fast pace through the sandy terrain.]"
},
{
"from": "gpt",
"value": "Bad. The dromedary in the video gallops unsmoothly, with uncoordinated movements."
}
] |
seed44_246
|
videos/HRA_part1/246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, charming finch perches on a branch, its vivid yellow plumage contrasting beautifully with the green foliage. Its beady eyes sparkle with life as it gazes around, alert and curious. Suddenly, it breaks into a melodious song, filling the air with its sweet, trilling notes. The bird then takes flight, its wings a blur of motion against the clear blue sky, before settling back on the branch, a picture of grace and tranquility in nature's embrace.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the action of birds spreading their wings and flying."
}
] |
seed42_1955
|
videos/HRA_part0/1955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 supermarket, a diverse group of people, including a young woman with long brown hair tied in a bun, wearing a black jacket over a gray shirt and black leggings, and a man in a red shirt and blue jeans, are joyfully dancing to an upbeat tune. Amidst the aisles filled with groceries, a person dressed in a comical weasel costume joins the impromptu dance party, adding to the festive atmosphere. The weasel, with its oversized head and expressive features, moves energetically among the dancers, who are all smiling and enjoying the spontaneous fun in the brightly lit store.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed44_244
|
videos/HRA_part1/244.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 jumping over obstacles in the video are not smooth and coordinated."
}
] |
seed42_2315
|
videos/HRA_part0/2315.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic lion, king of the beasts, is seen in the early morning, wiping its face with its paw in the grasslands of Africa. The lion, with a full, tawny mane, is lying down, using its right paw to wipe its face, perhaps after a recent meal or simply as a grooming habit. The grassy savanna stretches out behind it, dotted with acacia trees, providing a natural habitat for this powerful creature. The sun, still low in the sky, casts a warm glow over the scene, highlighting the lion's golden fur and the textures of the grass.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1261
|
videos/HRA_part0/1261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara swims through a clear, tranquil body of water, its ears and nose poking above the surface. It propels itself forward with powerful kicks from its webbed hind feet, showcasing its natural swimming abilities. The scene is set against a lush, green forest backdrop, highlighting the capybara's natural habitat. As it continues to swim, droplets of water scatter around it, creating a peaceful and captivating underwater perspective.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's eyes were not generated in the video."
}
] |
seed46_1768
|
videos/HRA_part2/1768.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid, close-up shot, a sleek, black king cobra emerges from the underbrush, its distinctive hood fully spread as it propels itself forward with surprising speed. Its body, covered in smooth scales, undulates gracefully over the forest floor, showcasing the powerful muscles beneath. The cobra's intense, amber eyes remain fixed ahead, conveying a sense of purpose and determination as it navigates the complex terrain with agility and precision. The lush greenery and dappled sunlight create a dynamic contrast against the snake's dark form, highlighting the primal energy of this extraordinary creature in motion.]"
},
{
"from": "gpt",
"value": "Bad. The cobra's eyes in the video were not generated."
}
] |
seed44_2037
|
videos/HRA_part1/2037.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a full uniform complete with a badge, gun, and radio, is seen in a modern kitchen with gray walls, white cabinets, and stainless steel appliances. He is intently loading dishes into a dishwasher, his focus and precision reflecting his attention to detail, typically associated with his law enforcement duties. The kitchen counters are clean and clutter-free, except for a few dishware items awaiting their turn in the dishwasher. The officer's demeanor suggests a moment of domestic routine amidst his usual high-stakes professional life.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2101
|
videos/HRA_part1/2101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome, young male actor sprints through a bustling train station, wearing a dark blue coat, khaki pants, and brown shoes, his face a mask of urgency and determination. The vibrant, crowded setting provides a dynamic backdrop, filled with diverse individuals going about their day. His intense gaze and focused posture convey a sense of high stakes, while the surrounding architecture and the moving crowd add depth and realism to the scene. The camera captures his swift movement from multiple angles, highlighting his purposeful stride and the energy emanating from him as he weaves through the throngs of travelers.]"
},
{
"from": "gpt",
"value": "Bad. The actor's running motion in the video can be clearly seen, but the movements are not very continuous and there is a lack of coordination."
}
] |
seed44_1838
|
videos/HRA_part1/1838.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 somber space funeral setting, a lone janitor, dressed in a black suit and tie, leaps gracefully over a floating row of mops and brooms that are held aloft by unseen forces, against the backdrop of a distant, glowing nebula. His face is marked with determination, and his movements are fluid and controlled, as if dancing among the stars. The funeral attendees, dressed in various mourning attire, watch him in awe, their expressions a mix of grief and admiration. The scene is both surreal and poignant, capturing the unique juxtaposition of everyday duties and extraordinary circumstances in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2868
|
videos/HRA_part1/2868.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene from a Space Reality TV Show, a waiter, dressed in a crisp white shirt and black pants, kneels down with a perplexed expression, observing a tiny hamster crawling across a futuristic, metallic surface. The hamster, wearing a miniature astronaut suit, explores its surroundings with curiosity, its movements captured in close-up detail. The waiter, now sitting cross-legged, watches the hamster with growing amusement, as the tiny astronaut continues its journey across the space station's gleaming floor, the vastness of space visible through large windows in the background.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the waiter and the finger generation are uncoordinated, and the hamster's paws are generated with distortion."
}
] |
seed44_1878
|
videos/HRA_part1/1878.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, possibly named Ray, stands in a sunlit room, wearing a stylish gray suit, white shirt, and patterned tie. He is seen from different angles, first with his back to the window, then with his profile illuminated by the sunlight, and finally facing forward, his confident expression captured in high definition. Throughout the sequence, he maintains a calm demeanor, his attire and the interplay of light and shadow creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1368
|
videos/HRA_part1/1368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, reminiscent of Chris Hemsworth, is seen in a modern, minimalistic living room with large windows and plenty of natural light. He wears a navy blue t-shirt, dark jeans, and a wedding band, giving him an approachable, everyman appeal. The actor is intently focused on assembling a piece of flat-pack furniture, such as an IKEA dresser, using a screwdriver and following the instruction manual. The scene conveys a sense of relatability and domesticity, as the celebrity navigates the familiar challenge of putting together home furnishings.]"
},
{
"from": "gpt",
"value": "Normal. Hand deformity appears."
}
] |
seed44_1737
|
videos/HRA_part1/1737.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, wearing a brown jacket and khaki pants, sits on a wooden chair in a spacious, empty room with high ceilings and large windows, stitching a button onto his garment with a look of intense concentration. The button, which matches the color of his jacket, is being sewn back on with a strong thread, as the man holds the fabric taut with his free hand. The room is bathed in soft, natural light, casting gentle shadows across the floor and highlighting the dust motes that dance in the air. The janitor's face is set in a serious expression, his brow furrowed in determination as he carefully guides the needle through the fabric, ensuring the button is securely fastened. Behind him, a row of neatly arranged brooms and cleaning supplies stand against the wall, a testament to his hard work and dedication to keeping the space clean and orderly.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's actions of sewing buttons with a needle and thread in the video are basically normal, slightly uncoordinated."
}
] |
seed46_1935
|
videos/HRA_part2/1935.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of a large, sleek bass fish fills the screen, its body glistening with vibrant green and brown hues, accented by striking black spots. The fish's powerful form is emphasized as it swims within its natural freshwater habitat, surrounded by lush aquatic plants and a rocky bottom. The water's rippling surface occasionally comes into view, hinting at the bass's movements just beneath. The scene is captured in high definition, highlighting the intricate details of the fish's scales, fins, and eyes, offering a captivating glimpse into the underwater world of this formidable predator.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1760
|
videos/HRA_part1/1760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by soft purple lights and adorned with cosmic artwork, a young, bald writer wearing a black turtleneck and jeans sits pensively at a sleek, metallic desk. He wipes away a smudge on the pristine, reflective surface, revealing a holographic interface beneath. Around him, floating canvases display vibrant, otherworldly landscapes, while the artist himself seems lost in thought, perhaps contemplating his next masterpiece among the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2295
|
videos/HRA_part0/2295.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant 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": "Good. Basically correct."
}
] |
seed46_2033
|
videos/HRA_part2/2033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, spiky hedgehog clad in a miniature astronaut suit embarks on an extraordinary adventure across a fantastical landscape. The scene opens with the hedgehog standing bravely at the edge of a small, smoking volcano, its eyes fixed on the distant horizon where other volcanoes loom large against the twilight sky. Suddenly, it springs into action, leaping high into the air with surprising agility, defying gravity for a brief moment before landing softly back onto the volcanic terrain. The hedgehog continues its daring journey, bounding from one dramatic setting to another, showcasing its courage and determination against the backdrop of these awe-inspiring natural wonders.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and undergo sudden changes."
}
] |
seed44_1019
|
videos/HRA_part1/1019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly contrasting scene, a middle-aged, bespectacled teacher wearing a gray jacket, blue shirt, and khaki pants runs alongside a majestic, wild panther, both moving at full speed across a lush green field under a bright blue sky. The teacher, with short brown hair and a look of intense focus, matches strides with the powerful feline, its sleek black fur rippling in the wind as it sprints effortlessly beside him. The unlikely pair cuts through the vibrant grassland, the teacher's clothing billowing slightly from the momentum, creating an extraordinary and dynamic image of an educator and a panther in motion together.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated, and the legs of the characters and animals appear and disappear."
}
] |
seed46_1040
|
videos/HRA_part2/1040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic scene set against the backdrop of a bustling harbor, a snake charmer dressed in traditional attire, complete with a red turban and colorful vest, plays an enchanting melody on his pungi. The cobra, coiled and alert, rises from its basket, swaying hypnotically to the music under the golden glow of the setting sun. The charmer's skilled hands guide the snake into a mesmerizing dance, captivating the audience gathered around the harbor, where boats gently rock in the water and seagulls circle overhead. The cobra's movements, synchronized with the charmer's music, create a powerful display of control and grace against the maritime setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted and deformed, and the snake's body is divided into several segments."
}
] |
seed44_147
|
videos/HRA_part1/147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the dense rainforest underbrush, a tiny vole emerges, its soft, brown fur glistening with moisture. It pauses, nose twitching, against the textured bark of a towering tree, as if caressing the ancient, moss-covered surface. Sunlight filters through the lush canopy overhead, casting dappled shadows on the rich soil below. The vole, sensing safety, continues its gentle exploration, its small paws leaving faint impressions on the damp earth, all set against the vibrant backdrop of the rainforest's greenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2718
|
videos/HRA_part2/2718.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [At a busy city bus stop, two cheerful children wearing swimsuits and holding floaties wait alongside their mother, who wears a yellow dress. The scene is vibrant, with the bus stop shelter adorned with colorful graffiti and the city skyline visible in the background. Suddenly, a double-decker bus approaches, its exterior painted with a striking zebra pattern. As the bus pulls up, the children look up in awe, their excitement palpable as they prepare to board for what seems like an adventurous day ahead.]"
},
{
"from": "gpt",
"value": "Bad. Overall, it does not conform to real-life scenarios; the facial features, hands, and feet of the characters in the video are generated blurry."
}
] |
seed42_3017
|
videos/HRA_part0/3017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 high-tech kitchen illuminated by neon lights, a chef dressed in a white apron and cap, wearing a gas mask, carefully handles a container of antimatter, its energy subtly pulsing within a secure, futuristic device. The chef, displaying remarkable courage, begins to run through the sleek, metallic corridors of a vast space station, the antimatter safely secured in a specialized briefcase designed to withstand extreme conditions. With each stride, the urgency of the situation becomes palpable, the chef's determination evident in the focused gaze beneath the mask, as they navigate the complex towards an unknown destination.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1726
|
videos/HRA_part2/1726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a gray suit, white shirt, and patterned tie, rearranges furniture in an office setting. He lifts a wooden chair with leather seating, moving it across the room with ease. The scene is set in a corner office, featuring a large window with a cityscape view, a desk adorned with legal documents, and a bookshelf filled with law books. The lawyer's actions are deliberate, indicating a need for change or reorganization in his workspace. Despite the professional environment, the act of rearranging furniture adds a personal touch to the narrative.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_3021
|
videos/HRA_part0/3021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown shirt, beige vest, and dark pants, is seen on his hands and knees in a grassy yard, playfully crawling alongside a small, light brown dog. Both the man and the dog exhibit joyful expressions, with the dog wagging its tail enthusiastically. The man's shirt is untucked, revealing his playful side as he engages in this delightful interaction with his canine companion on a sunny day.]"
},
{
"from": "gpt",
"value": "Normal. The man's face is distorted, his hands are distorted, his arms are distorted, and the dog's face is distorted."
}
] |
seed46_193
|
videos/HRA_part2/193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, donning a crisp white shirt, black vest, and tie, is seen in an upscale restaurant, standing on a chair to check a smoke detector. The room is modern and stylish, with wooden floors, a white ceiling, and large windows. The waiter, displaying a conscientious attitude towards safety, carefully inspects the device. The scene conveys a sense of professionalism and attention to detail, as the waiter ensures the restaurant is equipped with functional safety equipment. The establishment is empty except for the waiter, emphasizing the routine nature of the task. The waiter's attire and the restaurant's decor suggest a high-end dining environment, where safety measures are taken seriously.]"
},
{
"from": "gpt",
"value": "Normal. The server's hands and arms appear deformed."
}
] |
seed44_2681
|
videos/HRA_part1/2681.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer with short brown hair, wearing safety glasses, a gray shirt, and khaki pants, stands in a large industrial space filled with machinery. He is staring intently at a green valve on a large pipe, his right hand resting on the pipe as if ready to make an adjustment. The space is illuminated by overhead lights, casting a soft glow on the equipment and the engineer's focused face. Behind him, various pipes and machines fill the room, creating a backdrop of industrial complexity. His gaze is unwavering, conveying a sense of determination and expertise in his work environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2082
|
videos/HRA_part0/2082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chef, wearing a traditional white uniform and a tall hat, finds himself in an unexpected encounter with a bobcat. They stand on a dirt path winding through a dense forest, the sunlight filtering through the trees casting dappled shadows on the ground. The chef, holding a basket presumably filled with fresh ingredients, looks surprised yet calm as he meets the gaze of the wild feline. The bobcat, equally intrigued, pauses in its walking, standing tall on the path, its ears perked and tail swishing gently, as if acknowledging the chef's presence in its natural habitat. The two share a moment of mutual respect and curiosity before continuing on their respective paths, the chef moving forward with purpose and the bobcat melting back into the underbrush, both figures disappearing into the lush greenery of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The chef's face is blurry and distorted, and the cat's legs are deformed, with its body undergoing sudden and abnormal changes during movements."
}
] |
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 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 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": "Normal. The person in the video does not move."
}
] |
seed42_1892
|
videos/HRA_part0/1892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier, donning a red apron with a name tag, works diligently behind a cluttered grocery store checkout counter. She is in the process of changing the batteries in a barcode scanner, handling the device with care and precision. The scene is set in a bustling supermarket, with customers waiting patiently in line, and the cashier's actions are framed by shelves stocked with various products. As she replaces the batteries, her focused expression conveys her commitment to ensuring the scanner functions smoothly, maintaining the efficiency of the checkout process.]"
},
{
"from": "gpt",
"value": "Normal. The female cashier's hand and the barcode scanner in the video generate anomalies."
}
] |
seed42_1709
|
videos/HRA_part0/1709.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the heart of a dense boreal forest, dappled sunlight filters through the canopy, illuminating the mossy ground. A curious capuchin monkey, clad in a red vest for visibility, explores this unfamiliar habitat. It cautiously descends from the treetops, venturing onto the forest floor, where it encounters an array of flora and fauna. The monkey walks among tall conifers, its eyes scanning the underbrush for interesting insects and plants, offering a unique perspective on life beneath the towering trees. Throughout the journey, the capuchin's red vest contrasts vividly with the lush greenery, making it a standout figure in the woodland scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_278
|
videos/HRA_part2/278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clear, close-up underwater shot, a tiny ghost shrimp, nearly transparent with faint grayish-blue hues, scuttles along the sandy bottom of a freshwater environment. Its delicate, see-through body reveals its intricate internal structure, while its antennae and legs move rapidly as it navigates its habitat. Surrounded by small stones and plant roots, the shrimp pauses momentarily before continuing its journey, showcasing its unique ability to blend into the aquatic surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The ghost shrimp in the video generated with deformities, claws were partially missing, and eyes did not generate."
}
] |
seed42_3099
|
videos/HRA_part0/3099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savannah dotted with distant acacia trees, a large herd of African cape buffaloes gathers. The scene opens with a panoramic view of the herd, then zooms in on two buffaloes standing face-to-face, seemingly engaged in a dance-like interaction. The dominant male, with massive horns and a thick mane, takes a step forward, while the other male responds with a matching step, creating a rhythmic pattern. They continue this 'dance', mirroring each other's movements against the serene backdrop of the savannah, the clear blue sky, and the distant horizon, evoking a sense of primal connection and ritual within the herd.]"
},
{
"from": "gpt",
"value": "Normal. The right antelope's horns are slightly deformed."
}
] |
seed42_2000
|
videos/HRA_part0/2000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished man with salt-and-pepper hair and a neatly trimmed beard speaks passionately, gesturing with his hands to emphasize his points. Dressed in a navy suit with a crisp white shirt and a red tie, he commands attention against a backdrop of city lights and a blurred crowd. His animated expressions and dynamic body language convey the intensity of his conversation, drawing the viewer into the engaging dialogue taking place in this urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are not fully generated, and his facial features are slightly distorted."
}
] |
seed44_1142
|
videos/HRA_part1/1142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 gaunt writer, clad in a brown leather jacket, gray t-shirt, and dark jeans, crawls through a desert landscape, reminiscent of a jackal, with a vintage typewriter strapped to his back. The scene opens with him crawling on sandy terrain, his face reflecting determination and resolve. Next, he continues his arduous journey, his clothes and skin stained with dirt, showcasing his unwavering commitment to his craft. The camera then captures him from above, emphasizing his small figure against the vast, barren environment. Lastly, he pauses to rest, the camera focusing on his weathered hands as they gently touch the typewriter, symbolizing his dedication and the intimate connection between the writer and his instrument.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1102
|
videos/HRA_part2/1102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a black jacket over a gray shirt and dark pants, is engaged in an intense scene where he skillfully catches a falling glass bottle with his right hand, displaying remarkable agility and precision. His focused gaze and the dynamic motion of the catch are highlighted against a dimly lit, gritty urban setting, adding to the dramatic effect of the moment. The scene is shot in high definition, capturing every detail of the actor's expression and the fluidity of his movements as he successfully intercepts the bottle mid-air.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3008
|
videos/HRA_part1/3008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blue jeans, is seen energetically dancing in a surreal scene set in the middle of a vast prairie. Surrounding him are several large bison, who calmly observe the director's enthusiastic dance moves under the open sky. The director, displaying an unexpected sense of whimsy, continues to dance amidst the majestic animals, creating a unique juxtaposition between human creativity and the untamed beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The director's dance moves in the video are not smooth."
}
] |
seed44_1574
|
videos/HRA_part1/1574.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 detailed close-up, a badger with piercing eyes and sharp teeth runs through a grassy landscape, its fur textured and realistic. Behind it, the silhouette of a large power plant with cooling towers can be seen, emitting steam into the dusky sky. The badger continues its sprint across the terrain, its body language conveying determination and strength, all set against the backdrop of the industrial power plant under the twilight sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1911
|
videos/HRA_part2/1911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, presumably a writer, sits cross-legged on a lush, grassy surface, wearing a blue denim jacket and dark pants. He gently caresses a small, brown bear, who reciprocates with a loving nuzzle. The bear, adorned with a red bow tie, displays affection towards the man, who smiles warmly. Both are surrounded by a serene, verdant landscape, with the man's writing materials, including a notebook and pen, visible nearby. The scene conveys a tender moment between the writer and the bear, set against a peaceful outdoor backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The human hands and arms show deformation and mutation, as well as the bear's legs."
}
] |
seed44_2243
|
videos/HRA_part1/2243.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic musician, clad in a vibrant yellow raincoat and matching hat, stands under a powerful waterfall in a lush, green forest, playing a harmonica with intense focus. The water cascades over mossy rocks, creating a natural stage for the performer. Suddenly, the musician leaps into the air, harmonica still in mouth, capturing a moment of pure joy and freedom amidst the thundering water and verdant surroundings. The scene is framed by towering trees and ferns, emphasizing the connection between music, nature, and human spirit.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_1396
|
videos/HRA_part1/1396.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a red tracksuit, emulates a monkey with playful antics, running energetically across a vibrant green field under a clear blue sky. The student's facial expression, complete with wide eyes and an open mouth, mirrors the monkey's characteristic features, enhancing the mimicry. Accompanied by a group of friends, who cheer and laugh in the background, the scene captures a moment of carefree fun and youthful exuberance. The student's attire, which includes a red jacket and matching pants, stands out against the lush greenery, while the clear blue sky provides a perfect backdrop for the lively scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1377
|
videos/HRA_part1/1377.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with a striking resemblance to Taylor Swift, known for her blonde hair and red lips, is seen in a series of scenes. First, she stands confidently against a backdrop of a gray wall, wearing a black leather jacket, a gray top, and black pants. Her stance suggests strength and determination. In the next scene, she walks away from the camera, showcasing her outfit and a casual, relaxed demeanor. Then, she is captured in a moment of laughter, leaning back, her smile wide and genuine, conveying a sense of joy and freedom. Lastly, she is seen mid-stride, walking purposefully towards the camera, her expression serious and focused, embodying the essence of the song 'Shake It Off' by Taylor Swift.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers in the video are incomplete, her arm is missing, and her face and body are deformed."
}
] |
seed46_2253
|
videos/HRA_part2/2253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 surprising and vivid scene, a beautifully rendered CGI cheetah, marked by its distinctive black spots, sits calmly on a restaurant's hardwood floor, bathed in warm lighting. Surprised diners watch from their tables, which are set with white tablecloths and elegant place settings, as a brave individual reaches down to caress the wild cat's head. The cheetah, relaxed and unperturbed by the surroundings, accepts the gentle touch, creating an extraordinary juxtaposition of nature and civilization.]"
},
{
"from": "gpt",
"value": "Bad. The person's action of petting the cheetah in the video is uncoordinated."
}
] |
seed44_1542
|
videos/HRA_part1/1542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature, bespectacled man, presumably a writer, stands on a ladder, cleaning the rain gutters of a charming, old house. He wears a brown jacket over a checked shirt, blue jeans, and a cap, while holding a long-handled gutter scoop. The scene is set against a backdrop of lush greenery, indicating a peaceful, suburban environment. The writer's focused expression and the tools of his current task, including the ladder, scoop, and a bucket placed on the grass, suggest a dedicated approach to home maintenance. Despite the mundane activity, his attire hints at his dual identity as a creative professional and a homeowner managing everyday chores.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_3070
|
videos/HRA_part0/3070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, dressed in a brown jumpsuit and cap, is playfully crawling on his hands and knees across a stable floor, chasing after a curious horse. The horse, with a full brown mane and tail, looks back at the janitor with a sense of amusement, its hooves stepping lightly on the straw-covered ground. The stable's wooden beams and stalls provide a rustic backdrop, while the janitor's playful demeanor adds a touch of unexpected humor to the otherwise ordinary task of cleaning.]"
},
{
"from": "gpt",
"value": "Bad. The crawling motion of the character in the video is not smooth."
}
] |
seed44_1466
|
videos/HRA_part1/1466.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished male lawyer, clad in a dark suit and white shirt, sits in a modern office environment. He is backlit by a large window, casting a subtle shadow on his face as he leans forward, hands clasped together. His eyes are closed, and his facial expression conveys deep concentration, possibly during a moment of meditation or focused breathing exercises. The office is sparsely decorated, featuring only a desk, chair, and the window, emphasizing the man's presence and the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2204
|
videos/HRA_part1/2204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, complete with a suit jacket, shirt, tie, and glasses, interacts with a porcupine on the edge of a swimming pool. The lawyer gently reaches out to touch the porcupine, which remains calm and still. In another scene, the lawyer is seen swimming in the pool, while the porcupine watches from the side, both under the clear blue sky. The lawyer then sits on a pool chair, the porcupine nestled in his lap, as they both enjoy the sunny day beside the pool, surrounded by lush greenery.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2000
|
videos/HRA_part1/2000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished man with salt-and-pepper hair and a neatly trimmed beard speaks passionately, gesturing with his hands to emphasize his points. Dressed in a navy suit with a crisp white shirt and a red tie, he commands attention against a backdrop of city lights and a blurred crowd. His animated expressions and dynamic body language convey the intensity of his conversation, drawing the viewer into the engaging dialogue taking place in this urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are not fully generated, and his facial features are slightly distorted."
}
] |
seed42_1575
|
videos/HRA_part0/1575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker in a lab coat walks purposefully across a large, open laboratory space filled with complex machinery and high-tech equipment, the setting for a quantum entanglement experiment. The room is illuminated by bright overhead lights, casting a sterile glow over everything. In the background, scientists can be seen observing data on computer screens and discussing theories, their faces serious and focused. The worker carries a clipboard, pausing occasionally to check notes or adjust settings on various machines, all while surrounded by the hum of active scientific inquiry into the mysteries of quantum mechanics.]"
},
{
"from": "gpt",
"value": "Normal. The character's legs are slightly twisted, and the hands are distorted."
}
] |
seed42_1816
|
videos/HRA_part0/1816.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist wearing a blue denim jacket and black cap, holding a paintbrush in his right hand, walks alongside a large elephant with intricate, colorful patterns painted on its body. Both the artist and the elephant stroll through a lush, green landscape filled with tall trees and vibrant vegetation. The elephant carries a canvas on its back, and the artist occasionally glances at it as they walk together in harmony. They are surrounded by the natural beauty of the environment, which complements the vivid artwork on the elephant's skin.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1755
|
videos/HRA_part2/1755.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow safety vest and a hard hat, finds himself in a whimsical scenario where he's crawling on his hands and knees through a narrow, dimly lit tunnel. The setting is enhanced by the presence of a stuffed weasel toy, which has somehow joined him on this unusual journey, adding a touch of humor and unexpectedness to the scene. The engineer's serious expression contrasts with the playful atmosphere created by the stuffed animal, making for a unique and memorable visual.]"
},
{
"from": "gpt",
"value": "Normal. Legs show deformities. A weasel plushie suddenly appears and then disappears."
}
] |
seed46_1169
|
videos/HRA_part2/1169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great blue heron, with its signature blue-gray feathers and long, slender legs, stands majestically in the shallow waters of a serene lake. Its sharp, yellow eyes scan the water's surface as it patiently awaits its next meal. Suddenly, the heron strikes with lightning speed, its sharp beak piercing the water to catch a small fish. As it emerges victorious, the heron proudly displays its catch before swallowing it whole. All the while, the calm surroundings of the lake provide a peaceful backdrop, with gentle ripples on the water and the distant silhouette of trees completing the scene.]"
},
{
"from": "gpt",
"value": "Normal. The heron's beak is generated too long, and the legs are generated too thin."
}
] |
seed46_1791
|
videos/HRA_part2/1791.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 navy blue shirt and beige trousers, gently caresses a buffalo in a rural setting. The buffalo, with its shaggy brown fur and large horns, stands calmly under a clear blue sky, with lush green grass and distant trees providing a peaceful backdrop. The engineer, showing a tender side, connects with the animal, which is often a symbol of strength and resilience, in a moment of quiet intimacy amidst the natural landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1793
|
videos/HRA_part2/1793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, futuristic setting, a skilled musician, dressed in a black leather jacket, plays a gleaming silver electric guitar. Nearby, an enormous, friendly bear, adorned with a red bow tie, listens intently, its paw gently resting on the musician's shoulder in a gesture of companionship. Suddenly, a shimmering wormhole opens behind them, revealing a kaleidoscope of colors and swirling galaxies. The musician and the bear look into the wormhole, their expressions a mix of awe and curiosity, as they contemplate the mysteries of the universe together.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1838
|
videos/HRA_part1/1838.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 somber space funeral setting, a lone janitor, dressed in a black suit and tie, leaps gracefully over a floating row of mops and brooms that are held aloft by unseen forces, against the backdrop of a distant, glowing nebula. His face is marked with determination, and his movements are fluid and controlled, as if dancing among the stars. The funeral attendees, dressed in various mourning attire, watch him in awe, their expressions a mix of grief and admiration. The scene is both surreal and poignant, capturing the unique juxtaposition of everyday duties and extraordinary circumstances in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. No black suit and tie, no floating mops and brooms, and the number of attendees is incorrect."
}
] |
seed44_1609
|
videos/HRA_part1/1609.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student with a messy bun, wearing a white t-shirt and grey sweatpants, stands in a small dorm kitchen. She measures coffee grounds into a filter, her movements practiced and efficient. Next, she pours water from a bottle into the coffee maker, the light catching the droplets as they fall. Then, she pushes the start button on the machine, her face lighting up with anticipation. Lastly, she adds a splash of milk to her mug, stirring it slowly as steam rises, ready to enjoy her well-deserved break amidst the stacks of books and papers on her desk.]"
},
{
"from": "gpt",
"value": "Normal. The hand of the character in the video has generation issues."
}
] |
seed42_1496
|
videos/HRA_part0/1496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, wearing a brown shirt and denim overalls, drives a futuristic lunar buggy across a vast, barren moon landscape, dotted with craters and boulders under a starlit sky. Suddenly, the scene transitions to a serene, earthbound setting where the same farmer is seen leisurely floating on an inflatable raft, fully clothed, in the middle of a tranquil, crystal-clear lake surrounded by lush greenery. The peaceful atmosphere is punctuated by the occasional splash as the farmer gently moves through the water, enjoying a refreshing break from his daily chores.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the farmer moving on the inflatable raft in the middle of the lake with clothes on in the video are not smooth and coordinated."
}
] |
seed42_1941
|
videos/HRA_part0/1941.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_1035
|
videos/HRA_part0/1035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a standard uniform complete with badge, gun holster, and radio, is engaged in an unexpected task. He is seen from behind, bending over a small hole in the ground, which is surrounded by a ring of yellow tape. His right hand is plunged into the hole, indicating he is unclogging a drain. The location appears to be a public park, with green grass and trees in the background, and a group of people watching the unusual scene from a distance, their expressions a mix of amusement and curiosity. A yellow sign with the words \"Caution, Wet Floor\" leans against a nearby tree, adding to the surreal atmosphere of the situation.]"
},
{
"from": "gpt",
"value": "Bad. Hand deformation."
}
] |
seed42_2797
|
videos/HRA_part0/2797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying a rugged explorer, traverses a dense tropical dry forest, wiping beads of sweat from his brow. Surrounded by towering trees with gnarled roots and sparse foliage, he navigates the arid landscape, dressed in khaki cargo pants, a beige tank top, and a wide-brimmed hat. The scene is illuminated by the golden glow of late afternoon sunlight filtering through the canopy, casting dappled shadows on the ground. The explorer pauses, wiping away perspiration with a cloth, revealing a map in his hands, hinting at his quest for hidden treasures within the unforgiving yet enchanting wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, the hand is twisted, the face is distorted, and the object in the hand is also twisted."
}
] |
seed44_1882
|
videos/HRA_part1/1882.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated female nurse, clad in a white uniform and wearing her hair in a bun, attentively checks a smoke detector mounted on the ceiling in a modern hospital hallway. The space is pristine and well-lit, with pale green walls and white trim, exuding a sense of cleanliness and professionalism. The nurse, displaying her commitment to safety, uses a long, red-handled tool to test the device, ensuring it functions properly in the healthcare environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2169
|
videos/HRA_part2/2169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, fluffy gray mouse walks along the edge of a weathered wooden table, its tiny feet making delicate movements against the grainy surface. The mouse pauses momentarily, its whiskers twitching as it senses the environment, before continuing its journey. Its round ears and curious demeanor are highlighted as it explores the tabletop landscape, framed by a blurred background that suggests a rustic interior setting. Throughout the scene, the mouse's agile movements and cautious behavior are captured in detail, providing a close-up view of its natural actions.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3184
|
videos/HRA_part2/3184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green savanna setting, a gentle giraffe is being affectionately caressed by a human, both standing under a vast, open sky. The giraffe, with its distinctive spotted coat and long neck, leans into the touch, expressing comfort and trust. The human, wearing a khaki safari outfit, reaches up to stroke the giraffe's face, creating a tender moment of interspecies connection. The scene is framed by the natural beauty of the savanna, with distant trees and a clear blue sky, emphasizing the harmony between the human and the majestic animal.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe's head is twisted, and the character's hands are distorted."
}
] |
seed42_3090
|
videos/HRA_part0/3090.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 character's head and hands are distorted in the video."
}
] |
seed46_1918
|
videos/HRA_part2/1918.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 writer, donning a brown leather jacket and a gray beanie, sits at a wooden table in a rustic, dimly lit room. With a focused gaze, they caress the worn pages of a chaparral poetry book, their right hand gently touching the text as if feeling the essence of the words. The scene conveys a sense of reverence and connection to literature, with the writer's attire and the chaparral book adding depth to the narrative. The room's ambiance, characterized by wooden elements and soft lighting, enhances the intimate atmosphere as the writer's hand, adorned with a silver ring, lovingly glides over the book's pages.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3143
|
videos/HRA_part0/3143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 children, a boy and a girl, are working together to mend a broken wooden fence in a rural, grassy area. The boy, wearing a gray T-shirt and blue jeans, holds a hammer in his right hand, while his left hand grips a nail. He looks intently at the task before him. The girl, dressed in a yellow top and blue jeans, assists by holding the loose board steady. She looks up, perhaps seeking approval or guidance. Behind them, a lush green landscape stretches into the distance, with tall trees framing the horizon. The sunlight filters through the leaves, casting dappled shadows on the ground, highlighting the industriousness of the young duo as they focus on fixing the fence.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2826
|
videos/HRA_part2/2826.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a kangaroo, dressed in a chef's hat and apron, is shown playfully hopping around a vibrant, modern restaurant kitchen filled with gleaming stainless steel appliances and colorful, contemporary decor. The kangaroo then takes a break from its culinary duties to enjoy a refreshing swim in an outdoor pool, surrounded by lush greenery and bright, sunny skies, creating a surreal and delightful blend of dining and leisure. After its swim, the kangaroo returns to the restaurant, where it is greeted by patrons sitting at tables, enjoying their meals in the stylish dining area, complete with large windows offering views of the beautiful landscape outside. Finally, the kangaroo is seen back in the kitchen, preparing a dish with precision and care, as if it were a true master chef, all while maintaining its playful and endearing demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's face is distorted, its body is twisted, and its paws are deformed."
}
] |
seed44_3105
|
videos/HRA_part1/3105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature woman with graying hair, wearing a brown jacket over a peach-colored top, stands against a blurry background, gesturing with her right index finger pointed outward. Moments later, she points emphatically toward the right side of the frame, her face expressing determination. She then points upward with both hands, her eyes following the direction of her gesture, suggesting a moment of revelation or realization. Finally, she points straight ahead with her right index finger, her body language conveying authority and command, all against a softly blurred backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The woman's facial eyes in the video are slightly mismatched, and the fingers are deformed."
}
] |
seed44_2167
|
videos/HRA_part1/2167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bobcat, typically a wild and elusive creature, is shown in an extraordinary scene, gently interacting with the sandy beaches of a coastal landscape. The bobcat, with its distinctive tufted ears and short tail, is depicted in a moment of unexpected tenderness, seemingly caressing the sand with its paw, a behavior rarely captured on camera. This unique encounter unfolds against the serene backdrop of a beach, where the gentle touch of the bobcat's paw on the sand challenges our perceptions of these usually solitary and fierce predators.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2508
|
videos/HRA_part1/2508.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a brown jacket and wide-brimmed hat, walks purposefully across a vast, futuristic farm landscape, with a colossal space elevator looming in the distance, its massive cable stretching into the heavens. The farmer pauses, looking up at the awe-inspiring structure, a blend of hard work and advanced technology coexisting in this extraordinary setting. As he continues walking, the camera captures the juxtaposition of traditional farming life and the futuristic marvel towering over the horizon.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2973
|
videos/HRA_part1/2973.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet suburban neighborhood, two young boys stand side by side, wearing casual clothes; one in a gray t-shirt and denim shorts, the other in a red shirt and khaki shorts. They are positioned against a backdrop of a white-painted wooden fence, with lush green bushes visible beyond. The boy in gray has his left foot raised, while the other boy leans forward, both engaged in a playful interaction. Their stance and attire are typical of summertime leisure, capturing a candid moment of childhood camaraderie against a backdrop of a sunny day.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3177
|
videos/HRA_part1/3177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet, overcast day, a small gerbil sits atop a tombstone in an old cemetery, surrounded by rows of weathered headstones and tall, swaying grass. The gerbil, with its tiny hands clasped together, appears to be contemplating the serene surroundings. Suddenly, it starts wiping its face with both paws, an endearing gesture that adds a touch of whimsy to the somber setting. The scene is captured in high definition, allowing every detail of the gerbil's fur and the intricate carvings on the tombstones to be clearly visible.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's body and limbs show deformities when performing actions."
}
] |
seed46_2801
|
videos/HRA_part2/2801.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow vest and khaki pants, walks down a dimly lit hallway, pushing a red cleaning cart. Suddenly, a small brown mouse scurries across the floor, its movements quick and cautious. The janitor stops, observing the unexpected visitor with mild curiosity before continuing on his path, the mouse now hidden from view, leaving behind a sense of quiet solitude in the empty corridor.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner walks very unsmoothly, with uncoordinated movements and goes in the wrong direction. The brown mouse also walks very unsmoothly, with uncoordinated movements."
}
] |
seed42_1578
|
videos/HRA_part0/1578.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, adorned in a cozy gray sweater and glasses, stands in a modern kitchen with sleek appliances, ready to craft stories. They pour water into a high-tech coffee machine, its illuminated screen displaying the brewing process, setting the scene for a productive day of writing. The individual then adds coffee grounds to the machine, preparing a perfect cup of coffee to fuel their creative endeavors. Dressed in a comfortable outfit and with a laptop nearby, they embody the ideal image of a writer ready to tackle the day, all while the aroma of freshly brewed coffee fills the air.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3184
|
videos/HRA_part0/3184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green savanna setting, a gentle giraffe is being affectionately caressed by a human, both standing under a vast, open sky. The giraffe, with its distinctive spotted coat and long neck, leans into the touch, expressing comfort and trust. The human, wearing a khaki safari outfit, reaches up to stroke the giraffe's face, creating a tender moment of interspecies connection. The scene is framed by the natural beauty of the savanna, with distant trees and a clear blue sky, emphasizing the harmony between the human and the majestic animal.]"
},
{
"from": "gpt",
"value": "Normal. The giraffe's ears are generated multiple times, the mouth is generated incorrectly, the man's hand is deformed, and there are issues with the face generation."
}
] |
seed42_1421
|
videos/HRA_part0/1421.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a red checkered shirt, brown apron, and khaki pants, takes a break from cooking to rake leaves in a suburban backyard. He pauses for a moment, looking thoughtful, before continuing his task with determination. The chef, now smiling, rakes a large pile of autumn leaves into a heap, enjoying the crisp fall weather. Finally, he pauses again, this time looking pleased with his work, standing next to the sizable leaf pile, with his rake resting on his right shoulder, and a residential neighborhood visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the scene of the chef resting."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.