video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1962
|
videos/HRA_part2/1962.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two young children, a boy and a girl, both wearing red jackets, are seen walking together with a realistic, animated beaver on a wooden path in a park during daytime. The beaver, positioned between the children, is slightly ahead, leading the way as if guiding them, while the girl looks down at it with a smile. The trio continues walking on the wooden trail, surrounded by lush greenery, with the beaver still in the lead, its bushy tail swaying side-to-side, and the children following closely behind, engaged in a joyful outdoor adventure.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the girl."
}
] |
seed42_2508
|
videos/HRA_part0/2508.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, 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."
}
] |
seed42_191
|
videos/HRA_part0/191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cosmic setting, a cashier, clad in a unique space suit adorned with symbols of diplomacy, traverses the mammoth hall of an intergalactic embassy. She walks with purpose, passing through a grand archway, her eyes set on a distant goal. Behind her, a massive window reveals the breathtaking expanse of stars and galaxies, highlighting the enormity of her mission among the celestial bodies. Her every step echoes in the spacious corridor, resonating with the gravity of her role in maintaining galactic peace.]"
},
{
"from": "gpt",
"value": "Normal. The character's head, arms, and legs are distorted in the video."
}
] |
seed46_182
|
videos/HRA_part2/182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant community garden, a group of diverse individuals, including a woman with brown hair tied in a bun, wearing a gray jacket and blue jeans, and a bald man in a red T-shirt and blue jeans, work together to pull weeds from a raised flower bed. The scene is set against a backdrop of lush greenery and blooming flowers, with a wooden shed and a painted mural visible in the distance. The cooperative atmosphere is highlighted by the shared effort of the group, each member engaged in the task of maintaining the garden's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed42_1401
|
videos/HRA_part0/1401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 human-sized fox, wearing a doctor's outfit complete with a white lab coat, blue shirt, and stethoscope around its neck, walks purposefully down a hospital corridor. The fox's facial features are clearly visible, with a furrowed brow conveying concern and determination. The hospital hallway is brightly lit, with white walls and linoleum flooring, and the fox strides confidently, passing by various medical equipment and posters hanging on the walls. Despite being a fox, it carries itself with the poise and professionalism expected of a medical professional.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_282
|
videos/HRA_part0/282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 person dressed in a panda costume runs playfully through the narrow, cobblestone streets of a quaint town, surrounded by colorful, closely-packed buildings. The panda mascot dashes past outdoor cafes, small shops with hanging signs, and historical architecture, blending elements of fantasy and reality. Locals and tourists alike look on in amusement, some taking photos, as the panda sprints by, adding a touch of unexpected joy to the picturesque town. The mascot's movements are energetic and lively, contributing to the overall sense of fun and adventure in this unique setting.]"
},
{
"from": "gpt",
"value": "Normal. The panda mascot's hand and arm are twisted in the video."
}
] |
seed46_1597
|
videos/HRA_part2/1597.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a yellow vest and gloves, stands at the edge of a vast landfill, the sprawling site of discarded waste stretching into the horizon under an overcast sky. The artist begins wiping the surface of a found object, revealing layers of rust and texture beneath the dirt, as trash and debris are scattered across the landfill in the background. Moments later, the artist continues wiping the object, now partially cleaned, revealing its industrial form against the bleak landscape of waste. Finally, the artist holds the fully wiped object, a reclaimed piece of art, against the stark backdrop of the landfill, the clouds hinting at a dramatic sky overhead.]"
},
{
"from": "gpt",
"value": "Normal. The face and hands of the character in the video have generation issues."
}
] |
seed44_1456
|
videos/HRA_part1/1456.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, recognizable by his distinct facial hair and dressed in hiking gear which includes a gray jacket, backpack, and cap, pauses on a rocky trail. The scenic mountain landscape behind him, featuring lush greenery and distant peaks, provides a stunning contrast to his utilitarian appearance. Initially, he looks down at his feet, seemingly contemplating his next step. Then, he turns his head slightly, his gaze following the path ahead. Next, he stops to observe the breathtaking view, his expression reflecting a sense of peace and appreciation for nature. Finally, he smiles widely, perhaps recalling a fond memory, before continuing his journey, embodying the unexpected image of a janitor enjoying a hike in the great outdoors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2575
|
videos/HRA_part2/2575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young children, a boy and a girl, are energetically shoveling snow in their front yard, surrounded by a wooden fence. The boy wears a brown jacket, gray pants, and a matching hat and mittens, while the girl is dressed in a purple jacket, jeans, and a pink hat and mittens. Both are using small red shovels to clear a path through the fresh, fluffy snow, their faces showing determination and joy. The scene is set against a backdrop of a suburban house, with windows reflecting the bright, sunny day, and a green minivan parked in the driveway, partially covered in snow. The atmosphere is one of cheerful family activity on a crisp, wintry day.]"
},
{
"from": "gpt",
"value": "Bad. The snow shoveling action is discontinuous, there is a sudden change."
}
] |
seed42_13
|
videos/HRA_part0/13.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, solitary moose is depicted swimming in a clear, glassy lake surrounded by lush vegetation, with its head and antlers visible above the water's surface. The majestic creature gracefully propels itself forward, its body partially submerged, showcasing its surprisingly strong swimming abilities. In the distance, dramatic cliffs rise from the water's edge, their rugged surfaces covered in dense greenery, providing a stunning contrast against the calm waters. The scene is completed by the inclusion of a second moose, also swimming, creating a captivating visual of these powerful animals in their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The video failed to generate another moose, and there is an issue with the antlers of the moose in the video."
}
] |
seed42_1717
|
videos/HRA_part0/1717.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and utility belt, stands in a dimly lit alleyway, his face partially obscured by shadow. He takes a deep breath, his chest expanding beneath his bulletproof vest, as he prepares for action. The focus is on his breathing, a testament to his calm under pressure, with the urban environment providing a gritty backdrop. His hand rests on his holstered weapon, and his eyes scan the surroundings, alert and watchful, as he draws another measured breath.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2481
|
videos/HRA_part0/2481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, with curly brown hair and wearing a gray shirt, speaks directly to the camera with a smile, holding a small, unframed artwork in his hands. The focus is on his face and upper body, with the studio environment blurred in the background, including a large window and a partially visible sculpture. Throughout the clip, he maintains eye contact with the viewer, gesturing with his free hand as he passionately discusses his work. The atmosphere is warm and inviting, enhanced by the soft lighting that illuminates the artist and the artwork.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2411
|
videos/HRA_part2/2411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, grassy plains under a wide, clear blue sky, two small children, a boy and a girl, both wearing vibrant yellow raincoats and red boots, walk alongside a majestic bison. The bison, with its shaggy brown fur and large, powerful body, moves gracefully across the landscape, leading the children on an adventurous journey. The siblings follow closely, their expressions a mix of awe and delight, as they explore the wilderness together with their unlikely companion. The scene is peaceful, with the gentle swaying of tall grass and the distant silhouette of mountains framing the horizon.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the brother and sister, and the head of the buffalo in the video have generation issues."
}
] |
seed46_1855
|
videos/HRA_part2/1855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bespectacled female doctor in a white lab coat, adorned with colorful pins, dances energetically in a spacious, well-lit room. Her attire includes a vibrant red blouse and stylish glasses, adding to her lively appearance. In her arms, she cradles a relaxed, curious ferret, which seems unperturbed by the dancing. The pair moves in sync, the doctor's joyful expression and the ferret's inquisitive gaze capturing the essence of an unexpected yet delightful moment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand appears deformed. A third hand appears during the process."
}
] |
seed44_1999
|
videos/HRA_part1/1999.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Amid the bustling activity of a harbor filled with boats and people, two young boys perform a daring leap from a wooden dock into the shimmering water below, their joyful expressions and the spray of water capturing the thrill of their summer adventure. Dressed in casual shorts and t-shirts, they are silhouetted against the bright sky, their bodies mid-air in a moment frozen in time, encapsulating the essence of youthful freedom and the vibrant life of the harbor.]"
},
{
"from": "gpt",
"value": "Bad. The person's arms, hands, head, and legs are twisted in the video."
}
] |
seed44_2486
|
videos/HRA_part1/2486.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 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 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": "Good. Basically no problem."
}
] |
seed46_187
|
videos/HRA_part2/187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young children, a boy and a girl, stand on a wooden chair in a cozy, lived-in room, their faces illuminated by the soft glow of a lamp. The boy, wearing a striped shirt and jeans, holds a new light bulb, while the girl, dressed in a pink sweater and leggings, assists him by holding a screwdriver. The boy carefully unscrews the old light bulb from the socket, while the girl looks on attentively. They work together, their teamwork and concentration evident in their focused expressions. The room around them is filled with toys and books, highlighting the everyday setting of this domestic task.]"
},
{
"from": "gpt",
"value": "Bad. The boy's hand, the girl's hand, and the screwdriver in the hand are poorly generated; the screwdriver in the girl's hand suddenly disappears in the middle frame."
}
] |
seed44_32
|
videos/HRA_part1/32.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tailored suit, tie, and leather briefcase, finds himself in an unexpected scenario: cleaning windows. With a microfiber cloth in hand, he meticulously wipes a large, clear window pane, revealing a cityscape beyond. The scene is set in a spacious office with modern decor, where natural light illuminates the room, highlighting the lawyer's dedication to detail in an unconventional task. Despite his professional attire, he approaches the chore with the same seriousness and precision as his legal work.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's face in the video is generated blurily, and the fingers are deformed."
}
] |
seed46_1201
|
videos/HRA_part2/1201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, dressed in a silver spacesuit, floats weightlessly in orbit around Earth, cradling a vibrant red electric guitar. His helmet visor reflects the stunning view of our planet, encapsulating the vastness of space. He gently caresses the guitar, playing it in zero gravity, as the blue and green hues of Earth contrast beautifully with the darkness of space behind him. The visual conveys a sense of tranquility and isolation, with the musician appearing lost in music amid the cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_1921
|
videos/HRA_part0/1921.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over casual clothes, finds himself unexpectedly digging with a shovel in the middle of a large, empty lot overgrown with grass, as if searching for something specific. The contrast between his professional attire and the task at hand highlights the unusual nature of the situation. He pauses to wipe sweat from his brow, revealing a look of intense determination. In another scene, he continues to dig with the same shovel, now more dirt-stained, while the afternoon sun casts a warm glow over the desolate lot, emphasizing the solitary and strenuous nature of his endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The middle-aged doctor's arm and hand are deformed, and the shovel in his hand is also distorted."
}
] |
seed42_2115
|
videos/HRA_part0/2115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, donning a brown leather jacket, a gray t-shirt, and jeans, stands against a dark background, holding a megaphone and gesturing with his other hand. Moments later, a wolf, possibly a Timber Wolf, is seen running in a dense forest, its powerful legs propelling it forward with grace and speed. The wolf's fur is a mix of grays and browns, blending seamlessly with the underbrush. The scene transitions to show the wolf's perspective, capturing the blur of trees and foliage as it dashes through the woodland, highlighting its agility and strength in motion.]"
},
{
"from": "gpt",
"value": "Bad. The director's gesture movements in the video are not very smooth and appear uncoordinated; the wolf's running movements are also discontinuous and uncoordinated."
}
] |
seed42_1232
|
videos/HRA_part0/1232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a well-dressed doctor, wearing a suit and tie, spectacles, and a stethoscope around his neck, playfully floats on a yellow inflatable raft in a clear blue swimming pool. In the background, a mammoth, standing at the edge of the pool, looks on curiously, its massive body shaded by the trees overhead. The doctor's attire remains perfectly neat despite the water, and the mammoth's presence adds an element of surrealism to the otherwise ordinary setting of a backyard pool surrounded by lush greenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2568
|
videos/HRA_part2/2568.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, clad in a red jacket and black pants, races through a city park surrounded by towering skyscrapers, lush greenery, and a clear blue sky. The panda, sporting sunglasses and a determined look, sprints past urban landmarks, including a towering glass building and a bridge. In another scene, the panda leaps over a log, its athletic prowess on full display against the cityscape backdrop. Finally, it continues its run, moving right to left across the screen, with the vibrant city as its dynamic setting.]"
},
{
"from": "gpt",
"value": "Bad. The panda's running motion in the video is not continuous, with abrupt changes."
}
] |
seed42_314
|
videos/HRA_part0/314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a blue shirt and khaki pants, sprints down a sleek, metallic corridor within a futuristic space station that functions as a medical facility. High-tech equipment lines the walls, and large, illuminated screens display complex data and patient vitals. The farmer's weathered face, marked by years of working under the sun, contrasts with the advanced technology surrounding him. As he runs, his boots echo against the pristine floor, highlighting the urgency of his mission within this orbiting sanctuary of healing.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's limbs and body are generated twisted in the video."
}
] |
seed46_1111
|
videos/HRA_part2/1111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal scene, a giraffe, standing tall with its spotted coat and long neck elegantly bent, is seen swimming in a clear, turquoise lake. Its legs paddle gracefully beneath the water's surface, creating gentle ripples that extend outward. The background features lush greenery and a serene sky, with the sun casting a warm glow on the tranquil landscape, highlighting the unique sight of this majestic creature effortlessly moving through the water.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe in the video has a twisted body, twisted legs, and head; its movements are not smooth."
}
] |
seed46_248
|
videos/HRA_part2/248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a majestic buffalo, with its shaggy brown fur and powerful stature, stands beneath the vibrant lights of an amusement park, visible through the trees. A carousel featuring colorful, whimsical animals spins in the background, adding to the surreal scene. Suddenly, the focus is on a young boy, perhaps five years old, wiping his hands on his jeans after enjoying a snack. Dressed in a red t-shirt and denim, he looks up with a smile, the Ferris wheel towering above him, encapsulating the essence of childhood joy and the unexpected combination of nature and entertainment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2617
|
videos/HRA_part1/2617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, clad in a dark gray jacket, white shirt, and black tie, is shown in a bathroom, intently focused on unclogging a drain. The bathroom features a white sink with chrome fixtures, a mirror above it, and a window in the background. The musician, with his graying hair and serious demeanor, uses a metal wire hanger as a makeshift tool to clear the clogged drain, demonstrating his problem-solving skills in an unexpected domestic task. The scene captures the juxtaposition of his refined appearance and the mundane chore, highlighting his versatility beyond his musical talents.]"
},
{
"from": "gpt",
"value": "Bad. The character's face in the video is slightly distorted, the hands are distorted, and the object in hand is distorted."
}
] |
seed42_2231
|
videos/HRA_part0/2231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical depiction, a janitor, dressed in a reflective silver suit, gently caresses the ethereal auroras of Uranus. The celestial event unfolds with vibrant green and purple hues swirling across the planet's atmosphere, creating an otherworldly spectacle. The janitor, equipped with a futuristic cleaning tool, appears to interact with the auroral lights, as if nurturing the beauty of the cosmic phenomenon. This surreal scene merges the mundane profession of a janitor with the majestic wonder of space, set against the backdrop of Uranus's mesmerizing auroras.]"
},
{
"from": "gpt",
"value": "Bad. The finger generation of the cleaner in the video has issues."
}
] |
seed42_3161
|
videos/HRA_part0/3161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 a rugged appearance, wearing a white tank top, beige overalls, and a wide-brimmed straw hat, is seen singing passionately. He stands against the backdrop of a vibrant sunset, with lush green fields stretching into the horizon. His weathered hands hold the microphone as he belts out his song, his eyes closed in intense concentration. The scene is filled with the warm hues of twilight, casting a golden glow on the farmer and the verdant landscape, evoking a sense of peace and harmony with nature.]"
},
{
"from": "gpt",
"value": "Good. The man's singing and movements in the video are basically normal."
}
] |
seed42_2037
|
videos/HRA_part0/2037.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_314
|
videos/HRA_part1/314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a blue shirt and khaki pants, sprints down a sleek, metallic corridor within a futuristic space station that functions as a medical facility. High-tech equipment lines the walls, and large, illuminated screens display complex data and patient vitals. The farmer's weathered face, marked by years of working under the sun, contrasts with the advanced technology surrounding him. As he runs, his boots echo against the pristine floor, highlighting the urgency of his mission within this orbiting sanctuary of healing.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's limbs in the video are distorted and incomplete, and the face is deformed."
}
] |
seed46_1006
|
videos/HRA_part2/1006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 police officer, clad in a navy uniform with a badge, cap, and sunglasses, interacts with a large brown teddy bear outside a row of shops, which include a bakery, a bookstore, and a clothing store, each with colorful awnings and signs. The officer gently lifts the stuffed animal, which is nearly as big as him, into the air. Nearby, a group of children watch in awe, sitting cross-legged on the sidewalk, their faces alight with wonder and joy. The officer then crawls on his hands and knees next to the bear, playfully engaging with the delighted kids, creating a heartwarming moment of connection between law enforcement and the community, all against the backdrop of a bustling street lined with charming stores.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous."
}
] |
seed44_1733
|
videos/HRA_part1/1733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent cheetah, known for its prowess on land, surprisingly takes to water, swimming in a large, lush, natural pool surrounded by verdant vegetation. The big cat, identifiable by its distinctive spots, demonstrates its adaptability as it navigates the water, its muscular body moving gracefully beneath the surface. The setting sun casts a warm glow over the scene, highlighting the cheetah's wet fur and the droplets of water displaced by its powerful strokes. This rare sight captures the animal's unexpected aquatic abilities in a serene, wild environment.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's face is distorted in the video."
}
] |
seed46_1861
|
videos/HRA_part2/1861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, wearing a crisp white shirt, black vest, and tie, stands in a cozy, warmly-lit room with wooden floors. He gently caresses a fluffy, white cat sitting on a table covered with a red checkered cloth. Beside him, a glass bottle and a wine glass are visible. The cat, adorned with a pink ribbon, looks content as it receives affection from the attentive waiter, whose demeanor suggests a tender, caring personality.]"
},
{
"from": "gpt",
"value": "Normal. The server's action of petting the cat in the video is not very smooth, and there is a sudden change in the server's hand during the process."
}
] |
seed46_2710
|
videos/HRA_part2/2710.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, resembling Colin Farrell, is seen walking through a dense forest with tall trees, wearing a brown jacket, jeans, and boots. Suddenly, the scene changes to reveal a prehistoric setting, where the actor now finds himself casually strolling beside a woolly mammoth. Both the actor and the mammoth continue their leisurely walk together, with the mammoth's massive frame towering over the actor, who appears unfazed by the extraordinary situation. They meander through the ancient landscape, surrounded by lush vegetation and underbrush, creating a surreal juxtaposition of eras and species.]"
},
{
"from": "gpt",
"value": "Normal. The character and mammoth movements in the video are slightly unsmooth."
}
] |
seed44_2367
|
videos/HRA_part1/2367.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, known for his mastery of the banjo, takes a break from his art to sweep his wooden porch on a sunny day. Dressed casually in a gray shirt and khaki pants, he methodically sweeps with a broom made of natural fibers, revealing the clean, weathered wood beneath. The porch, adorned with potted plants and a rustic rocking chair, overlooks a lush garden filled with vibrant flowers and greenery. In the background, a vintage acoustic guitar leans against the wall, hinting at the musician's passion for music, while the peaceful, suburban neighborhood provides a serene setting for this ordinary yet captivating task.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_2266
|
videos/HRA_part0/2266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 medical facility, an engineer, wearing a gray shirt with a NASA logo, gently caresses a high-tech medical device, displaying tenderness and care. The room is illuminated by the soft glow of screens and equipment, highlighting the advanced technology surrounding him. Against the backdrop of sleek, metallic surfaces and complex machinery, the engineer's tender gesture toward the device, which resembles a combination of a robotic arm and diagnostic tool, conveys a sense of emotional connection and the importance of human touch even in a highly technical environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2749
|
videos/HRA_part1/2749.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown pelican with a large, distinctive orange pouch flies low over the surface of a calm bay, its wings spread wide against the vivid blue sky. It gracefully swoops down, diving into the water to catch fish, its body momentarily submerged before it resurfaces, triumphant. The pelican then floats on the water, preening its feathers with a meticulous beak, showcasing its survival skills in the serene coastal environment. Against the backdrop of a clear sky and calm waters, the pelican's flight and feeding habits are highlighted, emphasizing its unique features and behaviors in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The pelican's movements in the video are slightly unsmooth, and the wing-spreading action is uncoordinated."
}
] |
seed42_2974
|
videos/HRA_part0/2974.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a faded red shirt and dark pants, is seen intently repairing a vintage bicycle in a rustic, sunlit barn. The barn interior is filled with various tools and farming equipment, giving a sense of his daily life and work environment. He is hunched over the bike, carefully adjusting the gears with a wrench, his brow furrowed in concentration. The bike, with its classic design and worn paint, stands on a wooden stand, surrounded by scattered tools and parts, as he works diligently under the warm glow of a hanging light bulb.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's hands undergo a deformity mutation while repairing the bicycle, and the tool in his hand also deforms."
}
] |
seed44_2977
|
videos/HRA_part1/2977.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned worker, donning a brown jacket and blue jeans, leads a strong, brown horse by a red halter, walking together in unison on a dirt path. The pair moves at a steady pace, the man guiding the horse with care and respect. The horse, with its muscular build and glossy coat, follows obediently, the two sharing a bond reflective of their partnership. The setting is a rural landscape, with distant hills and trees providing a serene backdrop to their peaceful walk.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1233
|
videos/HRA_part2/1233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 penguin, distinguished by its black and white plumage, waddles comically on a snowy shore, pausing to preen its feathers with its sharp beak. Against a backdrop of icy mountains and a serene, cloud-dotted sky, it stands upright, displaying its characteristic tuxedo-like appearance. The bird then takes a leap into the frigid waters, where it swims gracefully, propelled by its flippers, before re-emerging onto the ice, shaking off droplets, and continuing its journey across the frosty landscape under the soft glow of the Antarctic sun.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the penguin jumping into the water as mentioned in the caption."
}
] |
seed42_2060
|
videos/HRA_part0/2060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a stunning array of coral formations takes center stage. Hard corals in various shades of brown and orange create a textured landscape, while neon green and blue soft corals sway gently in the current. Brightly colored fish, such as yellow tangs and red snappers, dart in and out of the coral structures. The water above is crystal clear, allowing sunlight to filter down and illuminate the rich colors of the coral reef. In the distance, the silhouette of a large sea turtle can be seen gliding through the water, adding to the serene atmosphere of this underwater paradise.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2337
|
videos/HRA_part1/2337.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a crisp, white lab coat stands within a futuristic, neon-lit control room, his face reflecting determination as he gazes intently at a holographic interface displaying complex schematics. Suddenly, the scene changes to reveal the same engineer navigating through a parallel universe, where technology and nature intertwine in unexpected ways. He wipes away a layer of mist from a transparent panel, revealing an intricate circuit design beneath, symbolizing the merging of worlds and the power of innovation. The engineer's focused expression and the vivid, otherworldly landscapes around him emphasize the limitless possibilities of exploration and discovery.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are missing, and his face is deformed."
}
] |
seed42_2756
|
videos/HRA_part0/2756.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly moose stands in a hospital room, wearing a stethoscope around its neck, implying it plays the role of a doctor. The moose, with a caring expression, wipes the face of a seated patient, a child wearing a yellow shirt, using a soft cloth. The room is filled with natural light, highlighting the gentle interaction between the moose and the child, who looks up at the moose with trust and gratitude. Behind them, medical equipment and a hospital bed are visible, blending the elements of a healthcare setting with the unexpected presence of the animal.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_267
|
videos/HRA_part2/267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green orchard, a hardworking farmer pauses from his labor, wiping sweat from his brow, while in the foreground, a mongoose is seen playfully exploring its surroundings. The farmer, dressed in a straw hat, denim overalls, and a plaid shirt, leans against a wooden fence, offering a warm smile. Nearby, the mongoose, with its slender body and bushy tail, darts between tree trunks, seemingly unbothered by the human presence. In the distance, a shimmering swimming pool, surrounded by a wooden deck and sun loungers, provides a refreshing contrast to the vibrant orchard setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2673
|
videos/HRA_part0/2673.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casual attire, leaps into the air against the backdrop of a vibrant village scene. The village is set amidst lush greenery, with colorful houses lining the cobblestone streets. The student, wearing a yellow t-shirt and denim shorts, is captured mid-jump, their arms spread wide in exhilaration. The scene is filled with natural beauty, from the verdant foliage to the clear blue sky above. As the student jumps, they seem to embody the spirit of youth and adventure, their face alight with joy and energy. Behind them, the village bustles with life, with locals going about their daily routines and children playing nearby. The overall effect is one of vitality and happiness, capturing a fleeting moment of pure delight in a picturesque village setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3013
|
videos/HRA_part0/3013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged chef, wearing a white apron over a black shirt and gray pants, is seen scrubbing the bathroom floor with a green cleaning brush. The room is illuminated by overhead lights, and the chef's serious expression conveys the importance of cleanliness. In another angle, the chef, still in his chef's uniform, is shown on his knees, focused on scrubbing the bathroom tiles with determination. The video emphasizes the chef's commitment to hygiene, even in non-food-related areas, as he meticulously cleans the bathroom floor with a green cleaning brush under the bright lights.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_3121
|
videos/HRA_part0/3121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense forest setting, a middle-aged man dressed in a green jacket and gray pants is seen wiping a wooden signpost with a cloth. The signpost, which bears the name of the forest trail, is set against a backdrop of lush greenery and tall trees. The man, likely a park ranger or caretaker, focuses intently on his task, ensuring the sign is clean and legible for visitors. The scene captures a moment of maintenance in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2728
|
videos/HRA_part1/2728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 artistic individual, donning a black beret and a red and black striped shirt, dances whimsically in a studio filled with vibrant paintings and art supplies. In their right hand, they hold a ferret that matches their playful energy, engaging in a synchronized dance that reflects their unique bond. The ferret, wrapped around their wrist like a furry bracelet, seems to enjoy the movement, adding a touch of eccentricity to the scene. The artist's left hand gestures expressively, complementing their dance moves, while the chaotic yet colorful environment around them enhances the creative atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1210
|
videos/HRA_part2/1210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing a yellow rubber glove on their left hand and a look of determination, scrubs the white tiles of a bathroom shower stall with a green scrub brush. The bathroom has a modern design with stainless steel fixtures. The student, dressed in blue jeans, a gray t-shirt, and sneakers, leans into their task with focused energy. In another angle, the student continues scrubbing the tiles, now revealed to be in a dorm room bathroom, with a shower curtain featuring a geometric pattern in the background. The student's dedication to cleaning is evident in their posture and the intensity of their scrubbing motion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2269
|
videos/HRA_part2/2269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, smiling cashier, wearing a brown apron over a gray shirt and black pants, meticulously dusts antique wooden furniture inside a vintage shop, highlighted by warm, golden sunlight streaming through the windows. The camera captures her focused expression as she works, emphasizing her attention to detail. Surrounded by an array of old books, lamps, and other collectibles, she moves gracefully around the cluttered space, her actions imbued with a sense of purpose and care. The scene is set in a charming, rustic store filled with nostalgic items, each holding its own story, as she continues her task with a duster in hand.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2374
|
videos/HRA_part0/2374.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinctively attired in a crisp white shirt, black vest, and black trousers, diligently cleans the expansive windows of an upscale restaurant. Surrounded by lush greenery, he expertly maneuvers a squeegee across the glass, ensuring crystal-clear transparency. With focused determination, he tackles the task at hand, his movements methodical and efficient. The vibrant outdoor foliage contrasts sharply with the clean, modern lines of the building, highlighting the meticulous attention to detail in maintaining the restaurant's pristine appearance.]"
},
{
"from": "gpt",
"value": "Bad. The scraper in the server's hand is deformed, and the server's hand and arm have also undergone distortion and mutation."
}
] |
seed42_2209
|
videos/HRA_part0/2209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a well-dressed doctor, wearing a white coat and a stethoscope around his neck, finds himself in a vibrant restaurant filled with lively music. Surprisingly, he is accompanied by a monkey dressed in miniature clothing, sitting on a chair beside him. As the captivating beat takes over, the doctor and the monkey begin to dance together, their movements synchronized in a comical yet endearing manner. The other patrons, seemingly unfazed, continue dining, providing a backdrop of casual elegance to this unusual dance spectacle.]"
},
{
"from": "gpt",
"value": "Normal. The monkey in the video is not wearing miniature clothes."
}
] |
seed46_1316
|
videos/HRA_part2/1316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a sandy beach, two smiling children, a boy and a girl, gently caress a small green lizard that rests on a patch of dry sand, surrounded by lush vegetation. The boy, wearing a blue t-shirt and blue swimming trunks, and the girl, clad in a pink dress, sit cross-legged as they tenderly pet the lizard. The scene is filled with warmth and sunlight, casting shadows of the children and the lizard onto the sandy ground. Moments later, the lizard scurries away into the foliage, and the children watch it go, their faces a mix of fascination and delight, embodying the innocence and wonder of childhood discovery.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2807
|
videos/HRA_part2/2807.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, an antelope, distinctively marked with white underbelly and brown coat, is shown crawling on its belly across the grassland, a behavior rarely observed. The scene opens with the antelope lying down, then it proceeds to crawl, its horns visible, as it moves slowly through the tall grass. Throughout the sequence, the antelope remains low to the ground, its body almost parallel to the earth, showcasing this unusual behavior in great detail against the backdrop of the African savanna.]"
},
{
"from": "gpt",
"value": "Normal. The antelope in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_1582
|
videos/HRA_part2/1582.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brightly lit, modern kitchen, a middle-aged chef with short brown hair, wearing a clean white apron over a black shirt, looks startled upon encountering an alien. The extraterrestrial being, with large eyes and a small body, hovers near the kitchen counter filled with various cooking tools and ingredients. The scene shifts to the chef running hurriedly down a long corridor, passing by stainless steel appliances and cabinets, while casting a fearful glance back at the unexpected visitor. The chase continues as the chef dashes through the bustling kitchen, dodging staff and equipment, with the alien following closely behind, creating a sense of urgency and chaos.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1314
|
videos/HRA_part2/1314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-dusted wilderness, two majestic bison stand side by side, their large, sturdy bodies nearly touching. One bison gently nudges the other with its snout in a tender caress, their breath visible in the crisp air. Their shaggy coats ripple slightly in the wind, and their eyes meet, conveying a deep bond. The scene is peaceful and intimate, set against a backdrop of distant mountains and a clear blue sky, highlighting the gentle nature of these powerful creatures.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3123
|
videos/HRA_part1/3123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dimly lit warehouse complex, a renowned film director, wearing a black leather jacket, gray shirt, and jeans, kneels among stacks of wooden crates. With a handheld camera, he captures footage of a giant panda cub crawling across the dusty floor, its fluffy black and white fur contrasting with the industrial setting. The panda moves slowly, exploring its surroundings with curiosity, while the director films intently, capturing every detail of this unusual encounter in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, the hands are twisted, the panda's body is distorted, the claws are twisted, and the legs are distorted."
}
] |
seed44_1528
|
videos/HRA_part1/1528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hermit crab, adorned with a vibrant red and orange color palette, emerges from its seashell home on a sandy beach. The crab, showcasing its intricate, spiraled shell, scuttles across the sand, leaving a trail of tiny footprints. It pauses to explore its surroundings, its eyes on long stalks scanning the environment. Nearby, a group of similar hermit crabs gather, creating a social scene among the rocks and driftwood, all set against the backdrop of a serene, sunlit beach.]"
},
{
"from": "gpt",
"value": "Normal. The hermit crab in the video has too many legs and no eyes generated."
}
] |
seed42_1693
|
videos/HRA_part0/1693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful red fox, standing on its hind legs in a grassy meadow under a twilight sky, wears a green bow tie and a brown top hat, adding a whimsical touch to the scene. It dances energetically, with the focus on its expressive face, showing pure joy and playfulness. The fox continues to dance, now surrounded by a group of admiring woodland creatures, including rabbits, squirrels, and birds, all watching in delight from the edge of a dense forest. The fox performs a final dance move, leaping into the air with its front paws raised, against the backdrop of the setting sun, casting a warm golden glow over the entire meadow.]"
},
{
"from": "gpt",
"value": "Bad. The red fox is deformed, with several extra legs."
}
] |
seed44_1084
|
videos/HRA_part1/1084.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and a brown belt, is on his knees next to a brown horse, which lies on its side on a grassy surface, possibly injured or receiving care. The officer's hands are gently placed on the horse's neck, showing concern and compassion, while the animal's eyes are closed, indicating it might be resting or in a state of distress. The scene is set against a backdrop of green fields and trees, with no other people or horses visible, emphasizing the intimate connection between the officer and the horse.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1789
|
videos/HRA_part2/1789.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 agile antelope leaps majestically across the sun-drenched savanna, its powerful legs propelling it high above the golden grasses. The animal, distinguished by its brown fur and impressive horns, is captured mid-jump, with all four feet off the ground, highlighting its remarkable athleticism. In the background, a vast landscape stretches out under a clear blue sky, dotted with distant trees, emphasizing the vastness of the environment. The scene is one of raw nature, with the antelope's leap frozen in time, showcasing the beauty and grace of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The antelope in the video runs very unsmoothly, with uncoordinated movements."
}
] |
seed46_1805
|
videos/HRA_part2/1805.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly capybara wearing a stethoscope and a lab coat, akin to a doctor, energetically jumps in slow motion against a vibrant green meadow background, capturing the joy and playfulness of the moment. The capybara's enthusiastic leap is highlighted by its joyful facial expression and the picturesque setting, blending elements of fantasy and nature.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the capybara's jumping movements, but they are not very smooth and continuous."
}
] |
seed44_1261
|
videos/HRA_part1/1261.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."
}
] |
seed44_1600
|
videos/HRA_part1/1600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hare runs through the city at night, its fur glowing under the streetlights, navigating urban obstacles like a seasoned athlete. It bounds across a busy intersection, dodging between yellow cabs and pedestrians, its powerful legs propelling it forward with graceful ease. The hare then leaps over a low brick wall, lands on the cobblestone sidewalk, and continues its journey, its silhouette framed by the neon signs of city storefronts. Finally, it pauses beneath a towering skyscraper, its large ears perked up, listening to the sounds of the city before continuing its mysterious nocturnal run.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's movements in the video are not smooth."
}
] |
seed42_120
|
videos/HRA_part0/120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a brown jacket and khaki pants, stands in a savanna environment, engaged in gently wiping the face of a seated cheetah. The big cat is calm, displaying trust, as it sits on a sandy ground strewn with rocks and twigs. The director's caring action is evident as they tenderly clean the cheetah's face using a soft cloth, all while surrounded by the natural habitat of tall grass and distant trees.]"
},
{
"from": "gpt",
"value": "Bad. The director's movements in the video are not smooth and coordinated."
}
] |
seed44_2915
|
videos/HRA_part1/2915.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent cheetah, embodying grace and power, rests on a dry, grassy savanna, its body curved in a relaxed position. It turns its head, using its paw to wipe its face, showcasing a natural, intimate grooming moment. The cheetah's distinctive black spots stand out against its tan fur, while its piercing eyes and pronounced facial features add depth to the scene. This close-up shot captures the animal's wild beauty and the serene environment surrounding it, with distant trees adding a sense of place to the composition.]"
},
{
"from": "gpt",
"value": "Normal. The cheetah's head and paws in the video were generated abnormally."
}
] |
seed42_1263
|
videos/HRA_part0/1263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A nervous-looking cashier, a young man with glasses and a name tag, stands behind a checkout counter. He wears a red apron over a white collared shirt, and his fingers shake slightly as he handles a stack of cash. The scene is set in a dimly lit grocery store aisle, with products visible on shelves in the background. The man's apprehensive demeanor is evident in his furrowed brow and tense posture, as he carefully counts the money with quivering hands, the camera capturing every detail in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are distorted, the face is distorted, and the coin in the hand is distorted."
}
] |
seed46_2664
|
videos/HRA_part2/2664.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a brown jacket over a white shirt and khaki pants, walks through a temperate deciduous forest during autumn. The trees are predominantly bare, with scattered leaves covering the ground. The forest floor is carpeted with a thick layer of dry, brown leaves, creating a crunching sound underfoot. The doctor occasionally stops to observe his surroundings, showcasing his appreciation for nature. Throughout the scene, the forest remains dense and the trees tall, with occasional glimpses of sunlight filtering through the canopy, highlighting the serenity of the environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor can be clearly seen moving in the video, with basically normal movements, but there is some lack of coordination."
}
] |
seed42_2328
|
videos/HRA_part0/2328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly colored ibis, with its signature red curved bill and long legs, stands regally in a shallow body of water. Its plumage, a stunning mix of white, brown, and chestnut, catches the light beautifully. The bird's eye, sharp and observant, scans the surroundings for potential prey. The serene setting, featuring lush greenery and a calm water surface, enhances the serene atmosphere, making it a perfect habitat for this elegant creature.]"
},
{
"from": "gpt",
"value": "Normal. The video has an issue with the generation of the ibis's beak."
}
] |
seed46_1250
|
videos/HRA_part2/1250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit tailor shop, a friendly cashier, dressed in a maroon collared shirt and khaki pants, assists a customer. The cashier, with neatly trimmed facial hair, sits at a sewing machine, carefully hemming a pair of gray pants, demonstrating expertise and precision. The scene highlights the skilled craftsmanship and personal service provided in the store, with the cashier's focused expression and the sewing machine's rhythmic sound adding to the atmosphere. The customer, standing nearby, watches attentively, expressing satisfaction and trust in the cashier's abilities.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1595
|
videos/HRA_part1/1595.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, complete with a receding hairline, glasses, and a gray beard, is depicted in a series of vignettes scrubbing various surfaces in a bathroom. In the first frame, he vigorously cleans the bathtub, wearing a black turtleneck sweater, khaki pants, and black shoes, his attire contrasting with the task at hand. Next, he is seen on his knees, scrubbing the floor tiles with the same intensity, his clothing now slightly disheveled. Then, he appears focused on cleaning the toilet bowl, his attire unchanged, showcasing his determination to tackle household chores. Lastly, he is shown wiping down the sink countertop, his attire still formal despite the domestic activity, highlighting the juxtaposition of his professional persona with the mundane task of bathroom cleaning.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3198
|
videos/HRA_part1/3198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone firefighter, clad in a specialized Neptune atmospheric suit, complete with a helmet and breathing apparatus, runs across a rugged, alien landscape bathed in eerie, ethereal light. The environment is dominated by hues of blue and green, evoking the mysterious atmosphere of Neptune. Wisps of cloud-like formations swirl in the distance, adding to the otherworldly ambiance. The firefighter's suit, equipped with advanced technology to withstand the harsh conditions, glimmers under the faint illumination, highlighting the bravery and determination required to perform such a daunting task in an extraterrestrial setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1468
|
videos/HRA_part1/1468.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, smiling teacher stands in a classroom filled with sunlight, wearing a stylish outfit consisting of a striped top, dark jeans, and brown boots. Her warm smile radiates positivity as she looks down at a small child, who is sitting on a chair and wearing a gray jacket and gray pants. The child returns her smile, creating a heartwarming scene of connection and joy in the educational setting. The teacher's attire, the classroom environment, and the presence of the child all contribute to a sense of happiness and engagement in learning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2771
|
videos/HRA_part1/2771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary director, dressed in a classic pinstripe suit, stands in a vast, dimly lit studio, skillfully orchestrating a surreal scene. Nearby, a Robot astronaut, adorned in a sleek silver spacesuit with gleaming gold accents, follows the director's guidance as it begins to dance. The robot's movements are fluid and precise, a captivating fusion of technology and artistry, set against the backdrop of cinematic equipment and the director's watchful gaze, creating a mesmerizing spectacle where reality meets imagination.]"
},
{
"from": "gpt",
"value": "Bad. The robot's movements are not smooth, and the actions are uncoordinated."
}
] |
seed46_2046
|
videos/HRA_part2/2046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, wearing a dark green jacket over a gray shirt, tends to laundry in a busy laundromat. Surrounded by rows of washing machines and dryers, he checks the status of a load in a washer, occasionally glancing at the patrons around him. He then moves to a dryer, where he retrieves a bundle of freshly laundered linens, carefully folding them with practiced hands. Amidst the hum of machinery and the scent of detergent, the janitor continues his duties, maintaining order in the bustling environment. Throughout the scene, he remains focused and diligent, his actions highlighting the routine yet essential task of laundry care in a public space.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's actions of folding clothes in the video are not continuous, there are abrupt changes."
}
] |
seed46_1081
|
videos/HRA_part2/1081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil orchard setting, lush greenery surrounds a badger as it curiously explores its environment. The badger, with its distinctive black and white striped face, sniffs the air, then gently caresses the bark of an old apple tree with its paw. The camera captures the badger's actions in detail, focusing on the texture of the tree bark and the animal's fur. The scene is peaceful, with the soft sounds of nature providing a soothing soundtrack to the badger's gentle interaction with its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1189
|
videos/HRA_part1/1189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit room, two young girls sit on a large, colorful rug, engrossed in crocheting a vibrant patchwork blanket. One girl, with short brown hair, wears a yellow T-shirt and blue jeans, focusing intently on her work. Beside her, a girl with long blonde hair, dressed in a pink dress, stitches away with determination. The room is filled with an array of yarn balls in various colors, scattered around them, and a white wooden table stands nearby, holding a cup of crayons and a half-finished coloring book, hinting at other creative activities. The atmosphere is warm and nurturing, with the girls' concentration and the colorful surroundings creating a scene of creativity and companionship.]"
},
{
"from": "gpt",
"value": "Normal. The girl's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2310
|
videos/HRA_part2/2310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, possibly a writer, wearing a brown jacket, blue shirt, and khaki pants, stands pensively on a rocky cliff overlooking a vast, stormy sea. He wipes his face with his right hand, perhaps reflecting a moment of emotional intensity or physical exertion, as he contemplates the dramatic landscape before him. The rugged terrain and turbulent waters provide a striking contrast to his thoughtful demeanor, emphasizing the solitude and grandeur of his surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are deformed, and his face is not fully generated."
}
] |
seed46_159
|
videos/HRA_part2/159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, male gorilla stands in a lush, green forest, engaging in a series of comical dance moves. He begins by swaying side to side, his massive body moving in time with an unseen rhythm. Suddenly, he breaks into a playful jig, his arms flailing wildly as he hops from foot to foot. The gorilla then attempts a spin, his wide grin revealing a mouthful of sharp teeth. Throughout the performance, the gorilla remains in the same spot, his dance a delightful contrast to the stillness of the surrounding environment. Despite his size and strength, the gorilla's movements are surprisingly graceful, his joyous expression captivating as he continues to dance in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Normal. The gorilla's movements are not smooth."
}
] |
seed44_2908
|
videos/HRA_part1/2908.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a black puffer jacket, dark jeans, and black boots, stands on a vibrant movie set. He momentarily closes his eyes, blinking, before opening them wide again to maintain focus. As he blinks once more, the overhead lights reflect off his glasses, hinting at the intense concentration required for his role. Despite the bustling activity around him, he remains centered, pausing briefly to blink, his attire and the lively set creating a contrast between the calm director and the dynamic filmmaking environment.]"
},
{
"from": "gpt",
"value": "Normal. The director's fingers are deformed in the video, and the eyes look unnatural."
}
] |
seed46_1538
|
videos/HRA_part2/1538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and unexpected scene, a dedicated teacher, wearing a vibrant yellow swimsuit and cap, instructs a curious jackal pup, who dons a miniature life jacket, in the art of swimming. They are in a serene, clear blue pool surrounded by lush greenery, creating a harmonious blend of nature and learning. The teacher gently supports the jackal pup, both displaying expressions of concentration and determination as they navigate the water together, embodying an unconventional yet touching teaching moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1123
|
videos/HRA_part1/1123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badge, sits attentively on a stone bench in a small, enclosed garden. He rests his hands on his thighs, wearing black gloves, and looks directly at the camera with a serious expression. Behind him, lush greenery and blooming flowers frame the serene setting, offering a peaceful contrast to his authoritative presence. The officer's attire includes a navy cap, and he holds a black baton in his right hand, symbolizing his role in maintaining law and order. Despite the tranquility of the garden, his alert posture and watchful gaze convey readiness and vigilance.]"
},
{
"from": "gpt",
"value": "Normal. The proportions of the police officer's hands are not well rendered."
}
] |
seed44_2154
|
videos/HRA_part1/2154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charming hedgehog, adorned with a miniature top hat and a tiny pair of spectacles, pirouettes gracefully on a wooden floor, surrounded by a medley of autumn leaves. The scene is imbued with a warm, golden light, casting gentle shadows that sway in harmony with the hedgehog's dance. As the music swells, the hedgehog leaps into a joyful jig, its quills bouncing playfully with each step. In the final moments, the hedgehog pauses, bowing elegantly to an invisible audience, the leaves rustling softly in applause, all set against the backdrop of a rustic barn door.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's movements in the video are not smooth."
}
] |
seed42_2934
|
videos/HRA_part0/2934.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a dark suit and carrying a leather briefcase, walks with purpose across a dimly lit, gritty urban environment. Simultaneously, a CGI weasel, also dressed in a miniature lawyer's outfit complete with a bow tie and a tiny briefcase, scurries alongside the human lawyer. Both characters navigate through the cityscape, which features brick walls, fire escapes, and a sense of the urban jungle. The juxtaposition of the human lawyer and the anthropomorphized weasel lawyer adds a layer of whimsy and metaphor to the scene, suggesting themes of cunning and legal maneuvering.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the lawyer walking, with basically normal movements, but there is slight uncoordination."
}
] |
seed46_2216
|
videos/HRA_part2/2216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer wearing a dark green jacket, blue jeans, and brown boots stands in a lush, green meadow dotted with dandelions. He looks down with a slight smile as he spots a small vole. The vole, with its distinctive round ears and brown fur, leaps from one dandelion tuft to another in the foreground, creating a playful contrast against the serene farm landscape. The farmer watches the vole's antics with amusement, his stance relaxed and his hands resting on his hips, as the rural setting provides a peaceful backdrop to this unexpected interaction.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2318
|
videos/HRA_part2/2318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman stands tall and poised, her blonde hair in a sleek bun, wearing a fitted black blazer over a white collared shirt, black trousers, and black heels. She is positioned in front of a large window with a city skyline visible in the background, her gaze directed towards the urban landscape. The scene is bathed in the warm glow of the setting sun, casting a golden hue over the woman and the cityscape, highlighting her silhouette and the texture of her attire. The contrast between the structured clothing and the fluidity of her stance conveys a sense of power and elegance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1400
|
videos/HRA_part1/1400.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 European badger, with its distinct black and white striped face and grey fur, is seen in a natural woodland setting. It stands on its hind legs, using its front paws to wipe its face meticulously, cleaning itself in the early morning light. The action is repeated several times, emphasizing the creature's grooming habits, all while surrounded by lush green foliage and undergrowth, giving a sense of the animal's natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The hands of the European badger in the video were not fully generated."
}
] |
seed42_1514
|
videos/HRA_part0/1514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, windswept grassland under a partly cloudy sky, a janitor wearing a yellow vest, blue jeans, and a white shirt is seen wiping a transparent, rectangular window that floats in front of him. The serene landscape stretches to the horizon, dotted with distant trees, while the janitor diligently cleans the window with a cloth, revealing the pristine clarity of the glass. The peaceful scene is punctuated by the gentle sway of the tall grass and the solitude of the janitor's task, emphasizing the unexpected context of maintenance in the midst of nature.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are very unsmooth and uncoordinated."
}
] |
seed46_1952
|
videos/HRA_part2/1952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 young female cashier with a name tag, wearing a yellow shirt and black pants, is playfully jumping over a small, live hamster on the floor of a convenience store, capturing a lighthearted moment during her shift. The hamster, seen from above, scurries across the checkered floor, adding to the unexpected and amusing interaction. The cashier, still mid-jump, is framed by shelves of beverages and snacks, creating a surreal yet charming atmosphere in the store aisle. The scene is set under the bright lights of the shop, highlighting the unusual encounter between the employee and the tiny rodent.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the hamster's actions are also not fluid."
}
] |
seed44_2026
|
videos/HRA_part1/2026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent cheetah, the world's fastest land animal, is shown in a lush, green savanna environment. The big cat is engaged in a self-cleaning ritual, using its paw to wipe across its face in a natural grooming behavior. The cheetah's iconic spotted coat is visible as it sits on the grassy ground, performing this common yet intimate act. The scene captures the cheetah's solitary nature and the importance of hygiene in its daily life, all set against a backdrop of vibrant vegetation and clear skies.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2027
|
videos/HRA_part0/2027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green swamp environment teeming with life, two young children, a boy and a girl, are seen energetically running and exploring. The boy wears a red t-shirt and khaki shorts, while the girl dons a yellow dress, both dressed appropriately for the outdoors. They splash through shallow water, their faces lit up with joy and wonder, surrounded by tall cattails and lily pads. A wooden bridge can be glimpsed in the background, adding to the sense of adventure in this vibrant natural setting.]"
},
{
"from": "gpt",
"value": "Bad. No wooden bridge was generated."
}
] |
seed44_1620
|
videos/HRA_part1/1620.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, wearing a yellow safety vest and blue jeans, sits on the ground in a rural landscape, gently caressing a small, brown hare. The worker, with a brown beard and wearing a dark cap, looks intently at the camera, while holding the hare near his chest. The scene is set against a backdrop of green grass and trees, creating a harmonious connection between the worker and the natural environment. The hare, seemingly unafraid, rests calmly in the worker's hands, highlighting a tender moment of interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Normal. The character's action of petting the wild rabbit in the video is basically normal, with slight awkwardness."
}
] |
seed44_2742
|
videos/HRA_part1/2742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, temperate rainforest, a janitor, dressed in a yellow vest and dark green pants, leaps over a fallen log with surprising agility. Surrounded by towering trees and dense foliage, he lands gracefully on the mossy ground, his movements deft and sure. As he continues his unlikely journey, bounding from one natural obstacle to another, the vibrant greens of the forest serve as a striking contrast to his utilitarian attire. Throughout this unexpected scene, the janitor's expression is one of focused determination, his form mid-jump captured against the backdrop of the rainforest's rich biodiversity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2483
|
videos/HRA_part0/2483.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spotted hyena, mid-jump, leaps across a grassy savanna landscape, its powerful hind legs fully extended beneath it, capturing the essence of its agility and strength. The hyena's spotted coat is vivid against the green vegetation, and its mouth is open, revealing sharp teeth, as it focuses on an unseen target ahead. The scene is set during the golden hour, with warm sunlight casting a glow over the hyena and the surrounding environment, highlighting the texture of the grass and the depth of the landscape.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the spotted hyena in the video are missing."
}
] |
seed46_1439
|
videos/HRA_part2/1439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 juxtaposition, a small brown rat wearing swimming goggles and a red swim cap is seen floating in a pool, its limbs outstretched in a relaxed position. Behind it, the stunning rings of Saturn are visible, appearing as a backdrop in the night sky. The water is clear, reflecting the stars above, and the rat seems content in its unusual aquatic environment, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The rat's face is distorted, and the paws are twisted."
}
] |
seed46_2994
|
videos/HRA_part2/2994.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene, two children, a boy and a girl, both dressed in khaki safari outfits, walk alongside a gentle rhinoceros in a lush, grassy savannah setting. The children, appearing fearless and joyful, interact closely with the rhino, which is adorned with natural vegetation, indicating its habitat. The trio moves harmoniously together, with the children occasionally touching the rhino, highlighting a unique bond between humans and wildlife. The scene is set against a backdrop of distant trees and clear skies, emphasizing the beauty and tranquility of their shared environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1520
|
videos/HRA_part0/1520.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, live chicken stands in the center of a dirt farmyard, surrounded by various farm equipment and buildings in the background. The chicken, with its brown and white feathers, yellow legs, and red comb, scratches the ground with its right foot, searching for food. It then pauses, head held high, seemingly alert to its surroundings. The camera captures a close-up of the chicken's face, highlighting its curious expression and detailed features. Finally, it shows the chicken from a distance, walking away from the camera, offering a full view of its body and movements within the rustic farm setting.]"
},
{
"from": "gpt",
"value": "Normal. The chicken's claws and face in the video are not fully generated."
}
] |
seed42_2119
|
videos/HRA_part0/2119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, a firefighter clad in a specialized silver suit and equipped with an advanced helmet wipes down a high-tech control panel with a cloth, ensuring cleanliness in zero gravity. The background showcases intricate machinery and complex equipment typical of a space exploration module, with the firefighter's actions highlighting the routine maintenance tasks necessary for maintaining operational integrity in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's fingers were not fully generated, and there is a part of the arm missing."
}
] |
seed44_2622
|
videos/HRA_part1/2622.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male chef with a neatly trimmed beard, wearing a brown jacket over his white kitchen uniform, expertly flips a crepe in a large pan over a high flame, demonstrating his culinary skills in a professional kitchen. The kitchen is modern and well-lit, with stainless steel appliances and countertops. The chef's focused expression and the sizzling sound of the cooking crepe fill the space, capturing the essence of his craft. Moments later, he carefully folds the perfectly cooked crepe, showcasing his precision and expertise in the art of cooking.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.