video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2101
|
videos/HRA_part2/2101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A handsome, young male actor sprints through a bustling train station, wearing a dark blue coat, khaki pants, and brown shoes, his face a mask of urgency and determination. The vibrant, crowded setting provides a dynamic backdrop, filled with diverse individuals going about their day. His intense gaze and focused posture convey a sense of high stakes, while the surrounding architecture and the moving crowd add depth and realism to the scene. The camera captures his swift movement from multiple angles, highlighting his purposeful stride and the energy emanating from him as he weaves through the throngs of travelers.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, feet, and arms are distorted in the video."
}
] |
seed44_1199
|
videos/HRA_part1/1199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a brown wide-brimmed hat, green shirt, and khaki pants, tends to a lush garden, surrounded by vibrant flowers and verdant plants. She kneels on a green kneeling pad, carefully planting a sapling into the rich soil. Next, she waters the plants with a silver watering can, her actions gentle and nurturing. Then, she pauses to admire her work, a trowel in her hand, a satisfied smile on her face, with the garden in full bloom behind her. Lastly, she sits on a wooden bench, pen in hand, notebook open, capturing her thoughts inspired by the beauty of nature, the garden's colors and textures providing a stunning backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2865
|
videos/HRA_part2/2865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bespectacled teacher in a yellow polo shirt and khaki shorts kneels beside a small pool, assisting a ferret in its first swimming lesson. The ferret, wearing a tiny life jacket, paddles energetically with its feet, its nose just above the waterline. The teacher gently supports the ferret from behind, offering encouragement and ensuring safety. The scene is set in a brightly lit room with large windows, casting a warm glow over the educational and nurturing moment shared between the teacher and the adventurous ferret.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's movements in the video are basically normal, with slight coordination issues."
}
] |
seed44_1458
|
videos/HRA_part1/1458.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a red bandana, denim overalls, and a white T-shirt energetically scrubs a muddy car with a sponge, creating soapy suds. The car, a vintage yellow convertible, sits in a driveway under a clear blue sky, with green foliage and trees in the background. She sprays the car with a hose, rinsing away the suds to reveal the shiny surface underneath. Then, she wipes down the car's exterior with a clean cloth, her smile reflecting satisfaction in her work. Finally, she polishes the car's chrome details with a microfiber towel, the gleaming vehicle now immaculate against the backdrop of a suburban neighborhood.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand generation in the video is problematic."
}
] |
seed46_2952
|
videos/HRA_part2/2952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a brown leather jacket and dark pants, kneels on a wooden floor, engaged in a crawling motion, as he observes a live hare sitting on a white table nearby. The scene is set indoors, with a large window in the background, allowing natural light to illuminate the room. The director's intent gaze and careful movement convey a sense of focus and determination as he studies the animal, which remains calm and still, seemingly unfazed by the presence of the human.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3219
|
videos/HRA_part2/3219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a classic gray suit with a blue tie, speaks earnestly into a microphone at a podium, set against a backdrop of a rich wood-paneled room. His hands gesticulate passionately as he addresses an unseen audience, conveying a sense of urgency and importance. The room is illuminated by soft, ambient lighting, highlighting the serious nature of the discussion. Close-ups capture the intensity in his eyes and the determination etched on his face, emphasizing the gravity of his words in this legal setting.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer can be clearly seen gesturing with both hands while speaking into the microphone; the movements are basically normal but there is slight awkwardness."
}
] |
seed42_1406
|
videos/HRA_part0/1406.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate writer, donning a dark green blazer over a white shirt, is depicted against a backdrop of space exploration imagery, including astronauts and planets. Initially, she stands pensively, holding a book with both hands, her gaze directed downward. Then, she looks up, her expression shifting to one of determination, as if contemplating the vastness of space. Next, she is shown dancing energetically, her right arm raised, embodying the joy and freedom of movement. Finally, she strikes a confident pose, her left hand resting on her hip, her eyes gazing into the distance, encapsulating the spirit of adventure and creativity in the realm of space exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2870
|
videos/HRA_part1/2870.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director wearing a beige jacket walks through a set resembling a forest, carrying a clapboard marked 'Quantum Leap.' He stops to observe a CGI-generated rhinoceros walking past him, its movements synchronized with the director's pace. The rhinoceros, rendered with high detail, appears to interact naturally with the forest environment, while the director watches intently, his expression conveying a mix of professionalism and wonder.]"
},
{
"from": "gpt",
"value": "Normal. The rhino's movements in the video are not smooth."
}
] |
seed46_2419
|
videos/HRA_part2/2419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, clad in a brown leather jacket, blue shirt, and jeans, stands against a background of lush vegetation and distant mountains. His eyes are fixed on a graceful gazelle as it bounds across the terrain. The gazelle, exhibiting a display of speed and agility, leaps over shrubbery in the foreground, its movement captured in slow motion. The director, now holding a megaphone, directs the action, his gaze following the gazelle's path through the wilderness. Finally, the gazelle continues its run, moving away from the director and into the vast landscape, embodying freedom and beauty in motion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1873
|
videos/HRA_part0/1873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling cityscape dominated by skyscrapers, a young female cashier, dressed in a black apron over a white shirt and black pants, stands behind a checkout counter in a modern, glass-walled convenience store. She gently caresses the edge of the counter with her right hand, her eyes softly closed, as if cherishing a moment of peace amidst the urban rush. The city's towering buildings loom outside the large windows behind her, contrasting with her intimate gesture.]"
},
{
"from": "gpt",
"value": "Normal. The hand of the female cashier in the video is generated incorrectly."
}
] |
seed46_2867
|
videos/HRA_part2/2867.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic worker, clad in a high-tech silver spacesuit and helmet, walks across the expansive surface of an enormous solar sail, which glimmers under the vivid light of a distant star. The sail, a vast expanse of shimmering material, stretches out behind the figure, capturing the celestial radiance. The worker, equipped with a portable tool kit attached to the suit, is seen moving purposefully along the sail's surface, conducting maintenance or inspection tasks in the vastness of space. The background is filled with the dark void of space, dotted with distant stars, emphasizing the isolation and grandeur of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2784
|
videos/HRA_part0/2784.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a traditional white uniform with a tall hat, finds himself in an extraordinary situation, crawling on his hands and knees across a lush, green field. Beside him, a friendly hippopotamus ambles along, mirroring the chef's movements in a comical display of camaraderie. The chef's attire, complete with a pristine white apron and polished shoes, contrasts humorously with the unconventional crawling action, while the hippopotamus, with its massive frame and gentle demeanor, adds a surreal element to the scene. Both crawl under a low-hanging branch of a tree, adding a touch of whimsy to the unexpected pairing.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1662
|
videos/HRA_part1/1662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park, a woman wearing a yellow jacket and khaki pants runs along a winding path surrounded by lush greenery. As she moves, her attention is drawn to an adorable hedgehog scurrying across the trail, its tiny feet moving swiftly beneath its spiky exterior. The hedgehog pauses for a moment, looking up at the woman with curious eyes before continuing on its way, blending into the underbrush. The woman, smiling at the encounter, resumes her run, passing by various enclosures housing majestic animals, all set against the backdrop of a sunny day in the sprawling park.]"
},
{
"from": "gpt",
"value": "Bad. The woman's face, hands, and feet in the video are generated abnormally, and there are issues with the hedgehog's head and feet."
}
] |
seed42_2314
|
videos/HRA_part0/2314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, clad in a brown jacket and wide-brimmed hat, traverses the icy terrain of a vast glacier, crawling on all fours to navigate the challenging landscape. Against a backdrop of towering ice formations, he crawls over the frosty surface, his form contrasting starkly with the pristine white expanse. The farmer's methodical movements and determined expression convey his resilience and connection to the harsh yet awe-inspiring environment. Throughout the scene, he continues to crawl across the glacier, his actions emphasizing the human spirit's perseverance in the face of nature's grandeur.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2192
|
videos/HRA_part1/2192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a gray T-shirt, blue jeans, and brown shoes, organizes his garage with determination. He begins by sorting through boxes, revealing a cluttered space filled with various items, including bicycles, tools, and old books. As he works, he meticulously arranges the contents, creating order from chaos. The garage walls, adorned with shelves and pegboards, display an array of neatly organized objects, showcasing the writer's commitment to tidiness. Throughout the process, the natural light filtering through the garage windows highlights his efforts, emphasizing the transformation of the space.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, the hand is twisted, the face is distorted, the leg is twisted, and the object in the hand is twisted."
}
] |
seed44_2546
|
videos/HRA_part1/2546.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short, dark hair and a neatly trimmed beard stands on a wooden chair, set atop a checkered floor, inside a rustic barn illuminated by soft, warm lighting. Dressed in a plaid shirt, blue jeans, and a brown vest, he reaches up to change a light bulb, his face reflecting concentration. The barn's wooden structure, adorned with tools and equipment, provides a backdrop for this everyday task, highlighting the farmer's practical skills and the cozy, well-lit interior of the barn.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's hand generation in the video has issues."
}
] |
seed46_1649
|
videos/HRA_part2/1649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bright, modern kitchen with white cabinets and countertops, two young children, a boy and a girl, both wearing red aprons over their clothes and chef hats, are attentively stirring ingredients in separate pans on a large, stainless steel gas stove. The boy, with short brown hair, focuses on his task with a serious expression, while the girl, with long blonde hair tied in pigtails, smiles as she stirs. The camera captures the sizzling sound of the food cooking, emphasizing the lively atmosphere. The room is filled with natural light from a window above the sink, illuminating the children as they cook, with a row of hanging pots and pans visible in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed42_2970
|
videos/HRA_part0/2970.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a red apron over her gray sweater and black jeans, stands at a register, looking surprised. Behind her, a full-sized moose runs across the store, its antlers adorned with Christmas lights, adding a surreal touch to the supermarket setting. The moose dashes between the aisles filled with groceries, creating a chaotic yet amusing atmosphere. The cashier watches the unexpected visitor with a mix of shock and amusement, as customers look on in disbelief, capturing the bizarre event on their smartphones. The moose's presence disrupts the mundane routine of the store, turning it into an unforgettable experience for everyone present.]"
},
{
"from": "gpt",
"value": "Bad. The moose can be clearly seen crossing the store in the video, but the movements are not very continuous and smooth, there is a lack of coordination."
}
] |
seed42_183
|
videos/HRA_part0/183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seamless blend of concepts, a majestic jaguar, adorned with Saturn's rings as a necklace, gracefully extends its paw in a caressing gesture toward the camera, creating an intimate connection. The jaguar wears a collar resembling Saturn's rings, adding a cosmic touch to its regal appearance. Its piercing eyes meet the viewer's gaze, while it gently touches the lens with its paw, as if extending a tender greeting. Against a dark, mysterious background, the jaguar's powerful form and the celestial rings combine to create a captivating and surreal scene.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2166
|
videos/HRA_part2/2166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned janitor, clad in a gray jumpsuit with a yellow utility vest over it, diligently wipes down a pristine, metallic surface within a bustling space station habitat. The vibrant blue and white Earth can be seen through a large window in the background, providing a stunning contrast to the industrial interior. As he works, the man pushes a cleaning cart filled with various supplies, emphasizing his commitment to maintaining the cleanliness of the space station. Nearby, two fellow crew members, wearing matching gray jumpsuits with red accents, are engaged in a conversation, adding to the lively atmosphere of the space habitat. Throughout the scene, the janitor continues his task with a focused determination, highlighting the importance of his role in the maintenance of the space station.]"
},
{
"from": "gpt",
"value": "Normal. The person's head, face, arms, and hands are distorted in the video."
}
] |
seed42_252
|
videos/HRA_part0/252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 extraordinary scene unfolds where a young elephant, covered in dust and dirt, crawls through a lush vineyard at sunset. Its trunk occasionally touches the soil, and it wears a simple rope around its neck. The elephant is surrounded by rows of green grapevines, with a wooden fence and a small, distant house set against a purple sky. The camera captures the animal from various angles, emphasizing its unique behavior in an unexpected environment, all bathed in the warm glow of twilight.]"
},
{
"from": "gpt",
"value": "Normal. The baby elephant's trunk touching the ground action is normal, but the walking motion is discontinuous, with sudden changes in the front limbs."
}
] |
seed42_1177
|
videos/HRA_part0/1177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a yellow safety vest and blue jeans, playfully swings a baseball bat near a serene swimming pool, backlit by the golden hour sunlight. He pauses mid-swing, the bat held aloft, with the shimmering water and lush greenery framing the scene. The worker then leans on the bat, gazing pensively at the inviting pool, the warm glow of the setting sun casting long shadows across the tranquil water. Finally, he takes a powerful swing, the motion frozen in time, with the idyllic pool setting and the vibrant colors of nature providing a vivid contrast to his robust action.]"
},
{
"from": "gpt",
"value": "Bad. The action of the construction worker swinging a baseball bat in the video is very uncoordinated."
}
] |
seed42_329
|
videos/HRA_part0/329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A fluffy, yellow chick with a small, red beak is seen crawling across a surface covered in hay, its tiny feet moving steadily as it explores its surroundings. The chick pauses momentarily, looking around with bright eyes, before continuing its crawl. The camera captures the chick from various angles, highlighting its downy feathers and the texture of the hay beneath it. Throughout the video, the chick remains the central focus, its curious movements and adorable appearance captivating the viewer's attention.]"
},
{
"from": "gpt",
"value": "Normal. The crawling motion can be seen, but the movements are not continuous and there are abrupt changes."
}
] |
seed46_215
|
videos/HRA_part2/215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a helmet, gently caresses a tiny, spiky hedgehog with a gloved hand, their eyes tenderly locked in a heartwarming connection. The scene is set against a backdrop of a partially extinguished fire, with billowing smoke and the remnants of flames, highlighting the contrast between the rough exterior of the firefighter and the delicate nature of the animal. The hedgehog, seemingly unharmed, nestles into the palm of the firefighter's hand, creating a poignant moment of compassion amidst the chaos.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog in the video is basically normal, but there is some uncoordinated movement."
}
] |
seed46_3125
|
videos/HRA_part2/3125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young writer, holding a green notebook, dances energetically on a busy street in Tokyo, her movements conveying a sense of freedom and joy. She wears a gray turtleneck sweater, a brown leather jacket, and a maroon beret, her style blending seamlessly with the urban environment. As she dances, the bustling city life continues around her, with people walking, cars passing, and neon signs illuminating the scene. Her expressive face, framed by her beret, reflects pure delight, and her body language conveys the story of a creative soul finding inspiration in the vibrant heart of Tokyo.]"
},
{
"from": "gpt",
"value": "Bad. The writer in the video is generally distorted."
}
] |
seed44_2871
|
videos/HRA_part1/2871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an upscale restaurant, a waiter, dressed in a black suit with a white shirt, black tie, and a pocket square, gently caresses a small, live vole on a pristine white tablecloth. The scene is set against a backdrop of expensive cutlery, crystal glasses, and fine china. The waiter's facial expression conveys a sense of care and tenderness, while the vole appears calm and unafraid. The room is softly lit, casting warm shadows on the walls adorned with elegant paintings and tapestries. This unusual interaction unfolds in slow motion, capturing every detail of the waiter's delicate touch and the vole's relaxed demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The server's fingers are deformed in the video, the hamster is generated abnormally, and the cutlery is disproportionate."
}
] |
seed42_3000
|
videos/HRA_part0/3000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, balding with a neatly trimmed beard, sits pensively on a vintage brown leather couch, wearing a blue checked shirt, dark pants, and brown shoes. Suddenly, he holds his chest and coughs intensely, his eyes squeezed shut, indicating discomfort. The scene is set in a warmly lit room with wooden walls, showcasing a rustic environment. As the coughing fit subsides, he looks concerned, placing his hand back on his chest, suggesting a moment of reflection on his health, all while maintaining the same attire and setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2288
|
videos/HRA_part0/2288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a black jacket and khaki pants, is seen in a close-up shot, wiping his brow with a white handkerchief. Behind him, a herd of antelopes can be observed grazing in a vast, grassy savanna, creating a juxtaposition between the director's world and the natural habitat of the antelopes. The director's weathered face and focused gaze suggest a moment of intense concentration during a film shoot, while the antelopes continue their serene existence in the background, unaware of the human drama unfolding nearby.]"
},
{
"from": "gpt",
"value": "Bad. The director's arm was not generated in the video, and the antelope was generated deformed."
}
] |
seed46_1168
|
videos/HRA_part2/1168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant park, a majestic leopard, its golden eyes alert, crouches near the edge of a pristine swimming pool, surrounded by vibrant greenery and towering palm trees. The big cat, with its distinctive rosette patterns on a tawny coat, gazes intently at the clear water, contemplating a playful leap. Moments later, it leaps gracefully into the pool, its powerful body slicing through the water in a fluid motion. Emerging from the pool, the leopard shakes off droplets, revealing its muscular physique, as it strides confidently across the park, leaving behind a trail of shimmering water on the sun-drenched pavement.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's movements are not smooth."
}
] |
seed42_1601
|
videos/HRA_part0/1601.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sand dollar lies on a bed of pristine white sand, its intricate pattern clearly visible against the stark background. Sunlight filters through crystal-clear water, casting a warm glow on the delicate creature. The sand dollar, positioned at a slight angle, reveals its stunning symmetry and fine details. Surrounding it, the sandy bottom is undisturbed, save for a few tiny grains caught in the gentle current, highlighting the serenity of the underwater scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2477
|
videos/HRA_part2/2477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer wearing a high-visibility jacket walks along the edge of a bustling harbor, the sunlight glinting off the water and reflecting onto his safety glasses. He carries a clipboard in one hand, attentively observing the large ships and cranes at work. The harbor is alive with activity, from the loading and unloading of cargo to the movement of tugboats guiding massive vessels. In the distance, the silhouette of a city skyline adds a touch of urbanity to the industrial scene. The engineer stops occasionally to jot down notes, his expertise evident in his confident demeanor and the precision with which he performs his duties.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1927
|
videos/HRA_part0/1927.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a casual green shirt and khaki pants, finds inspiration while leaping energetically onto a large rock in a lush forest setting, as if escaping the ordinary to explore the unknown. Nearby, an awe-inspiring mammoth, seemingly from another time, stands majestically under a canopy of ancient trees, its massive frame and textured skin adding an element of prehistoric wonder to the scene. The juxtaposition of the writer's leap and the mammoth's presence creates a surreal and captivating narrative, blending human creativity with the grandeur of nature's past.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1174
|
videos/HRA_part2/1174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a dark green shirt and khaki pants, is seen wiping a wet floor with a mop, leaving behind a clean, glistening surface. Beside him, a small, fluffy white dog, possibly a Bichon Frise, looks up with curious brown eyes. The janitor pauses, resting the mop against a wall covered with inspirational posters and a fire extinguisher, before bending down to interact with the dog, who eagerly responds with a wagging tail and playful energy, creating a heartwarming moment in an otherwise mundane setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1685
|
videos/HRA_part2/1685.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 individuals, a man and a woman, are engaged in washing a car in a driveway, with lush green grass and a tree visible in the background. The man, wearing a white t-shirt and dark shorts, is seen using a hose to rinse the vehicle, while the woman, clad in a pink tank top and denim shorts, scrubs the car's side with a sponge. Both are focused on their task, with the man holding the hose and the woman applying soap to the car's exterior. They work together harmoniously, the man rinsing and the woman scrubbing, against a backdrop of a sunny day and a neatly kept suburban home.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness. The woman's movements are more uncoordinated."
}
] |
seed46_2127
|
videos/HRA_part2/2127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wild dingo, characterized by its sandy coat, alert ears, and bushy tail, walks purposefully across a rocky terrain, surrounded by arid scrubland and distant, hazy mountains, evoking a sense of freedom and survival in the Australian wilderness. The dingo moves with a steady gait, its eyes scanning the environment, showcasing its natural instincts and resilience in a harsh landscape.]"
},
{
"from": "gpt",
"value": "Bad. The wild dog's walking movements in the video are not smooth and coordinated."
}
] |
seed44_2979
|
videos/HRA_part1/2979.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a gray suit with a white shirt underneath, stands in an industrial mine setting, gently caressing the rough texture of a mining wall. The scene is lit dramatically, highlighting the contrast between the lawyer's polished appearance and the gritty environment. The lawyer's face expresses a mix of determination and contemplation, while the mine's machinery and tools are visible in the background, emphasizing the unusual context of this legal interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1429
|
videos/HRA_part0/1429.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white button-down shirt, black pants, and a black apron, walks down a busy city street. He gently caresses the side of a food truck, which is brightly lit and surrounded by eager customers. The scene is set during the golden hour, with the warm sunlight casting a glow on the bustling urban environment. The waiter's tender touch on the food truck contrasts with the lively atmosphere of the city, creating a unique and captivating moment.]"
},
{
"from": "gpt",
"value": "Normal. The waiter's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1806
|
videos/HRA_part0/1806.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit enclosure, a majestic black panther sits calmly, its piercing eyes gazing intently. It gently caresses a log with its massive paw, adorned with thick, black fur and sharp claws. The panther's regal demeanor is underscored by its relaxed posture and the tender interaction with the wooden surface, set against a backdrop of lush vegetation and a water source, creating a serene atmosphere in the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1066
|
videos/HRA_part1/1066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinctive black markings, is perched on a concrete ledge. It has a full, round body and is situated in an urban environment, as indicated by the presence of a streetlight and a partial view of a building's facade with windows. The bird faces right, its head turned slightly toward the viewer, revealing one bright, alert eye. Its beak is open, perhaps mid-call, and its feet grasp the edge of the ledge firmly. The scene is set against a backdrop of a clear, blue sky, offering a simple yet effective contrast to the textured details of the pigeon.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2119
|
videos/HRA_part1/2119.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space 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 firefighters' movements in the video are basically normal, but there is slight disharmony."
}
] |
seed44_2085
|
videos/HRA_part1/2085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, donning a brown coat, scurries across a lush, green meadow under a partly cloudy sky. It dashes over the grass with its front paws lifted, revealing a clear view of its full body. Moments later, it continues its run, tail held high, near a wooden fence. The scene shifts to the beaver running alongside a tranquil stream, with trees in the background, showcasing its natural habitat. Lastly, it sprints with determination, its distinctive flat tail visible as it moves through its verdant environment.]"
},
{
"from": "gpt",
"value": "Normal. The beaver in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_2963
|
videos/HRA_part1/2963.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, wearing a classic black vest, white shirt, and black tie, serves a bobcat perched on a bar stool at an outdoor poolside bar. The bobcat, looking surprisingly at ease, has its paw on a cocktail glass. In the background, a group of people enjoys a day at the pool, with some swimming leisurely, creating a surreal yet serene atmosphere under the clear blue sky. The waiter, maintaining his professional demeanor, interacts with the wild guest, adding an unexpected twist to a typical day by the pool.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_3104
|
videos/HRA_part1/3104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stadium, under the luminous glow of neon lights, a diverse group of people and ibex, wearing athletic gear adorned with high-tech logos, participate in an intergalactic sports event. They run on a track that floats above the ground, surrounded by holographic spectators cheering them on. The ibex, equipped with advanced exoskeletons, leap gracefully alongside human athletes, their determination mirrored in their eyes. The atmosphere is charged with excitement as they race towards the finish line, the unity between species highlighted by their shared passion for competition in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2419
|
videos/HRA_part1/2419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, clad in a brown leather jacket, blue shirt, and jeans, stands against a background of lush vegetation and distant mountains. His eyes are fixed on a graceful gazelle as it bounds across the terrain. The gazelle, exhibiting a display of speed and agility, leaps over shrubbery in the foreground, its movement captured in slow motion. The director, now holding a megaphone, directs the action, his gaze following the gazelle's path through the wilderness. Finally, the gazelle continues its run, moving away from the director and into the vast landscape, embodying freedom and beauty in motion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1501
|
videos/HRA_part2/1501.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a tan belt holding a radio and handcuffs, diligently repairs a damaged wooden fence in a suburban neighborhood. The fence, marred by graffiti and broken planks, is set against a clear blue sky. The officer, wearing a hat and sunglasses, demonstrates community involvement by hammering a new plank into place, emphasizing public service beyond traditional law enforcement duties.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_277
|
videos/HRA_part2/277.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 panda, with its distinctive black and white fur, sits in a lush bamboo forest. It holds a piece of bamboo in its paw, bringing it to its mouth as if tasting the fresh shoot. Suddenly, the panda wipes its mouth with its paw, a natural gesture after eating, leaving a trail of moisture on its furry face. The panda continues to munch on the bamboo, occasionally pausing to wipe its mouth again, all against the serene backdrop of the bamboo forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_190
|
videos/HRA_part0/190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic jaguar, marked by its distinctive black spots on tawny fur, walks purposefully across a lush, green savanna landscape under the dappled shade of scattered trees. Its powerful muscles ripple beneath its coat as it strides with feline grace, the camera capturing every detail in high definition. The surroundings are alive with the sounds of nature, from chirping birds to the distant call of other wildlife, creating an immersive environment that highlights the beauty and power of this wild cat in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The jaguar's walking movements in the video are not very smooth and coordinated."
}
] |
seed44_1523
|
videos/HRA_part1/1523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a gray suit, white shirt, and red tie, is seen in a wide office space, mopping the floor with a green mop and bucket. The office features a large window, a desk with a computer, and a bookshelf filled with law books, creating a professional atmosphere. The lawyer, with short brown hair and glasses, demonstrates an unexpected side as he diligently cleans the floor, highlighting the versatility and hardworking nature of legal professionals.]"
},
{
"from": "gpt",
"value": "Normal. The mop in the character's hand is not green."
}
] |
seed44_3052
|
videos/HRA_part1/3052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling art gallery filled with contemporary paintings and sculptures, a distinguished film director, wearing a gray suit with a blue shirt and tie, passionately discusses a project with two colleagues. Suddenly, he breaks into an impromptu dance, spinning and moving with joyful abandon. The gallery space, illuminated by spotlights highlighting the artwork, becomes his stage, with onlookers smiling and watching his spontaneous performance. Throughout, the director's animated expressions and gestures convey his enthusiasm and creativity, all captured in high-definition detail.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2009
|
videos/HRA_part2/2009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an astrophysics laboratory filled with high-tech equipment and screens displaying cosmic data, a worker, wearing a white lab coat over a gray shirt and dark pants, dances energetically. Accompanying him is a live rabbit, hopping playfully nearby, seemingly unfazed by the unusual environment. The scientist's joyful movements contrast with the serious scientific surroundings, creating a whimsical and unexpected scene. Throughout, the lab remains brightly lit and organized, with the scientist and the rabbit sharing a moment of lightheartedness amidst the serious pursuit of knowledge.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs are missing, and his face and body are deformed; the rabbit's facial features are incorrectly generated with too many ears, problematic legs, and a deformed body."
}
] |
seed42_2327
|
videos/HRA_part0/2327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pufferfish, with its distinctive round shape and small size, swims gracefully in a vibrant coral reef environment. Its body, covered in tiny, pebble-like protrusions, is a mix of yellow and white with intricate black patterns. The fish inflates to nearly twice its original size, demonstrating its defense mechanism against potential predators lurking among the colorful corals and marine life surrounding it. The water is crystal clear, allowing every detail of the pufferfish's unique appearance and behavior to be captured in stunning high definition.]"
},
{
"from": "gpt",
"value": "Bad. The pufferfish's mouth was not generated in the video, and there were issues with the fish tail generation."
}
] |
seed42_2828
|
videos/HRA_part0/2828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, donning a navy blue cap and sunglasses, runs along the sandy shore of a bustling beach resort, where vibrant umbrellas and lively beachgoers fill the background. His attire includes a navy blue shirt with badge, navy blue trousers, and black shoes. The setting is a crowded beach during daytime, with the officer's movement capturing the essence of duty amidst leisure. He sprints past colorful umbrellas and animated vacationers, highlighting the contrast between his purposeful stride and the relaxed atmosphere of the resort.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the police running on the beach, but the movements are not very continuous and there is a lack of coordination."
}
] |
seed44_229
|
videos/HRA_part1/229.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural village, two young boys, one wearing a yellow shirt and the other in a red top, both donning black trousers, are seen engaging in a traditional folk dance. They perform on a grassy area surrounded by a dirt path, a wooden fence, and a lush green forest in the background. The boys' energetic movements are captured in high detail, showcasing their joy and the essence of childhood innocence. Their dance is part of a local celebration, with the scene framed by the natural beauty of their environment, highlighting the cultural significance of their performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2407
|
videos/HRA_part2/2407.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red-tailed hawk soars gracefully through a clear blue sky, its powerful wings outstretched against the backdrop of a lush, green forest below. The hawk's piercing golden eyes scan the landscape for prey, its sharp talons ready to strike. The camera captures the intricate feather patterns on its broad wings and tail, highlighting the beauty and strength of this avian predator. As it glides effortlessly, the wind ruffles its feathers, and the sunlight reflects off its body, creating a mesmerizing display of nature's majesty.]"
},
{
"from": "gpt",
"value": "Bad. During the flapping of the wings, the wings become deformed, and at one point, a third wing appears. The claws also deform."
}
] |
seed44_2956
|
videos/HRA_part1/2956.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, clad in a white tank top, denim overalls, and brown work boots, stands in a modest kitchen with white cabinets and a checkered floor. He reaches into a modern, stainless steel dishwasher, his hands strong and calloused from farm labor. Carefully, he extracts a large, white plate, placing it onto a wooden drying rack set on the counter, where other plates and utensils already rest. The scene is intimate, highlighting the unexpected domestic task of unloading the dishwasher performed by this typically outdoorsy figure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1466
|
videos/HRA_part0/1466.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 male lawyer, clad in a dark suit and white shirt, sits in a modern office environment. He is backlit by a large window, casting a subtle shadow on his face as he leans forward, hands clasped together. His eyes are closed, and his facial expression conveys deep concentration, possibly during a moment of meditation or focused breathing exercises. The office is sparsely decorated, featuring only a desk, chair, and the window, emphasizing the man's presence and the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1795
|
videos/HRA_part0/1795.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial markings and red tail feathers perches on a branch, its intelligent eyes gazing intently into the camera. Set against a lush, green jungle backdrop, the bird's colorful plumage stands out dramatically. It turns its head, showcasing its striking features, including a curved, black beak. The parrot then opens its beak, emitting a loud squawk, its dynamic body language and vivid colors creating a captivating scene in the heart of the rainforest.]"
},
{
"from": "gpt",
"value": "Bad. The parrot's beak in the video is generated unreasonably, it's missing an eye, and the claws are not fully formed."
}
] |
seed46_249
|
videos/HRA_part2/249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal and imaginative scene, two children, a boy and a girl, are dancing in a whimsical, cartoon-like environment. The girl, with curly red hair, wears a pink dress, while the boy, sporting brown hair, dons a blue shirt. They are accompanied by a friendly, animated coyote who mirrors their dance moves. The backdrop is a scientific laboratory filled with high-tech equipment, where researchers in lab coats are studying dark matter. This unusual juxtaposition of elements creates a captivating and unique visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The color of the boy's clothes was generated incorrectly."
}
] |
seed44_1519
|
videos/HRA_part1/1519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 middle-aged doctor, wearing a white lab coat over a navy blue shirt, sits in a cozy, dimly lit pub, sipping a glass of red wine. The pub is filled with the warm glow of hanging lights and a fireplace, creating a relaxed atmosphere. The doctor, with short brown hair and a neatly trimmed beard, leans back in his chair, holding the stem of the wineglass, and gazes thoughtfully into the distance. The scene conveys a sense of calm and tranquility, with the doctor enjoying a moment of respite from his busy medical career.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's eyes in the video are generated incorrectly, fingers are not fully generated, and the wine glass is missing parts."
}
] |
seed42_1189
|
videos/HRA_part0/1189.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 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, 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": "Good. Basically correct."
}
] |
seed42_306
|
videos/HRA_part0/306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, donning a white tank top, beige shorts, and brown leather sandals, assembles a wooden table in a bright room with large windows and a view of greenery outside. He starts by carefully examining the instructions, his brows furrowed in concentration. Next, he skillfully uses a screwdriver to attach the legs to the tabletop, showcasing his handyman abilities. Then, he wipes his forehead with the back of his hand, a small smile on his lips, indicating satisfaction in his progress. Finally, he stands back to admire the finished product, hands on hips, revealing the completed table in the well-lit space, surrounded by lush vegetation visible through the window.]"
},
{
"from": "gpt",
"value": "Bad. The male actor's movements in the video are not smooth."
}
] |
seed44_1263
|
videos/HRA_part1/1263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 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": "Good. Basically correct."
}
] |
seed46_1776
|
videos/HRA_part2/1776.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing a full-body red fox mascot costume, performs an entertaining dance routine in the middle of a lively campus quad. The mascot, with its distinctive bushy tail and comical fox features, energetically moves to an unseen beat, captivating a group of seated students in the background. The mascot's exaggerated dance steps, set against the backdrop of a sunny day on campus with students enjoying the outdoors, adds to the festive atmosphere. Throughout the performance, the fox mascot continues to dance animatedly, drawing laughter and applause from the surrounding students.]"
},
{
"from": "gpt",
"value": "Bad. At one moment, the tail detaches from the body, disappearing and reappearing suddenly. The arms and legs become deformed. Faces in the background become distorted and deformed."
}
] |
seed42_2016
|
videos/HRA_part0/2016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic gorilla, adorned with a vibrant, golden crown and a silver cape, dances gracefully on a floating platform set within Neptune's ethereal atmosphere. The planet's vivid blue and green gaseous clouds swirl dramatically in the background, creating an otherworldly backdrop. The gorilla performs a series of elegant dance moves, its powerful yet gentle demeanor captivating the viewer. The platform, illuminated by a soft, celestial glow, adds to the mystical ambiance of this extraordinary interstellar dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the gorilla appear deformed. The body shows signs of twisting and deformation."
}
] |
seed44_2132
|
videos/HRA_part1/2132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hummingbird, with iridescent green feathers and a forked tail, hovers near a red feeder, its wings a blur of motion against a clear blue sky. The bird's tiny feet dangle beneath it as it feeds, and its long, thin beak dips into the feeder's port. Suddenly, it takes flight, its wings creating an audible hum, and lands on a branch, where it preens its feathers with its curved bill. Throughout, the hummingbird's rapid wing movements and vibrant plumage are showcased against the serene backdrop of nature.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's movements in the video are not smooth and coordinated."
}
] |
seed44_209
|
videos/HRA_part1/209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male musician, donning a white button-down shirt and khaki pants, meticulously dusts a vintage gramophone with a feather duster in a warmly lit, cluttered room filled with musical instruments. His attire includes a brown belt and brown shoes, adding to his polished appearance. The room is decorated with a variety of string instruments hanging from the walls, including violins and cellos, highlighting the musician's passion for music. Throughout the scene, he continues to dust various objects, showcasing his dedication to preserving his cherished belongings, all within the cozy, wood-paneled space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1877
|
videos/HRA_part1/1877.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by soft purple and blue lights, a woman with curly brown hair, styled in a bun, wears a silver sleeveless dress and silver earrings. She gently caresses a large, textured, abstract artwork, the colors of which resemble cosmic nebulas, while standing on a transparent floor that reveals city lights below. The walls are lined with similar cosmic-themed art pieces, creating an immersive environment. She leans toward the artwork, her expression showing deep appreciation, as she stands on the glowing, see-through floor, with the dazzling cityscape visible beneath her feet.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2881
|
videos/HRA_part2/2881.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in casual attire consisting of a gray hoodie, blue jeans, and white sneakers, diligently scrubs the bathroom floor with a green cleaning rag. The bathroom is modern, featuring sleek white tiles and fixtures, with a hint of daylight filtering in from a nearby window. The student's focused expression and the repetitive motion of scrubbing convey a sense of determination and responsibility. The scene is set in a clean, well-lit space, emphasizing the student's hard work and attention to detail in maintaining the cleanliness of the bathroom environment.]"
},
{
"from": "gpt",
"value": "Bad. The hands are slightly deformed."
}
] |
seed42_2162
|
videos/HRA_part0/2162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, otherworldly setting reminiscent of a space opera, a majestic camel, adorned with ornate, futuristic gear, leaps gracefully over an array of alien flora. The backdrop features a bustling spaceport with neon-lit structures and a variety of extraterrestrial beings. The camel's rider wears a sleek, armored suit with glowing accents, embodying a daring space adventurer. The scene is filled with dynamic energy as the camel bounds through the air, showcasing its agility against the backdrop of a technologically advanced society engaged in a grand performance.]"
},
{
"from": "gpt",
"value": "Normal. The camel and rider's walking in the video is basically normal, but there is slight inconsistency in the movements."
}
] |
seed44_2736
|
videos/HRA_part1/2736.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit cave, a small brown bat, with leathery wings folded against its body, walks along the rocky ground with deliberate steps. Its face, framed by long, curved ears, is keenly observant. The bat pauses momentarily, revealing its tiny feet and claws as it navigates the stone surface. The focus then shifts to the bat's head, highlighting its intricate facial features and alert eyes. Finally, the bat is seen walking away, its silhouette set against the textured cave wall, creating a captivating scene of a bat navigating its environment on foot.]"
},
{
"from": "gpt",
"value": "Bad. The bat's walking movements in the video are uncoordinated."
}
] |
seed46_111
|
videos/HRA_part2/111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gold accents and a peaked cap, runs purposefully across a grand hall within a futuristic space station. The hall is lined with flags from various nations and interspersed with abstract art pieces, all illuminated by the soft glow of recessed lighting. In the distance, a large, circular window reveals the vastness of space and the distant twinkle of stars. The officer's run suggests urgency, possibly related to security matters at the ongoing political summit, where delegates from Earth and various space colonies gather to discuss interstellar policy. The polished floor reflects the officer's movement, emphasizing the gravity of the situation in this otherwise serene and majestic setting.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video is severely lacking in limbs and has not been generated properly."
}
] |
seed44_2085
|
videos/HRA_part1/2085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, donning a brown coat, scurries across a lush, green meadow under a partly cloudy sky. It dashes over the grass with its front paws lifted, revealing a clear view of its full body. Moments later, it continues its run, tail held high, near a wooden fence. The scene shifts to the beaver running alongside a tranquil stream, with trees in the background, showcasing its natural habitat. Lastly, it sprints with determination, its distinctive flat tail visible as it moves through its verdant environment.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's legs became deformed while running, and its body underwent abnormal mutations. Its tail flew up at one point."
}
] |
seed44_2481
|
videos/HRA_part1/2481.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, 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. No obvious issues."
}
] |
seed44_1161
|
videos/HRA_part1/1161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic silver spacesuit with an American flag patch, is seen crawling across the rocky, red Martian landscape, examining the terrain closely. The scene is set under a pinkish-brown sky, with distant mountains visible on the horizon. The officer's spacesuit features NASA logos and a utility belt, and they carry a high-tech scanner, highlighting the unusual combination of law enforcement and space exploration. The camera captures this unique moment in crisp, high-definition detail, emphasizing the contrast between the traditional role of a police officer and the extraordinary setting of a distant planet.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the police officer in the video are missing, and the face is distorted."
}
] |
seed46_2684
|
videos/HRA_part2/2684.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heroic firefighter, clad in full gear and a yellow helmet, stands in a lush, green forest near a majestic waterfall, holding a gerbil gently in his hands. He carefully wipes water from the small animal's face, ensuring its safety, as the waterfall cascades powerfully in the background, creating a dramatic contrast between the tender moment and the raw force of nature.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's fingers are deformed, the eyes are generated incorrectly, the hamster's eyes are generated incorrectly, the body is deformed, and the claws are not generated."
}
] |
seed46_2585
|
videos/HRA_part2/2585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with a full beard, wearing a straw hat and a checkered shirt, stands waist-deep in a clear blue pond, smiling at the camera. Beside him, a dingo with a red coat and a black-tipped tail swims energetically, its head held high above the water. The farmer's right arm is raised, showing a relaxed and joyful posture, while the dingo continues to swim, its eyes fixed on the farmer. The scene is set against a backdrop of lush greenery and tall trees, creating a serene and picturesque environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1984
|
videos/HRA_part1/1984.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 newsroom, illuminated by soft blue and orange lights, a realistic animated rabbit, wearing a small suit and tie, sits at a sleek desk. The room is filled with high-tech equipment and screens displaying galactic maps and data. The rabbit, with a serious expression, reads from a teleprompter, delivering the latest space news. Suddenly, the scene changes to the same rabbit running energetically on a treadmill, surrounded by floating zero-gravity objects, including a pen, a book, and a coffee cup, all set against the backdrop of the Earth through a large window.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's hands and arms are deformed, and its legs are deformed when running."
}
] |
seed44_102
|
videos/HRA_part1/102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum-like setting filled with art galleries, a sleek and powerful jaguar, adorned with a golden collar, walks gracefully among the exhibits. The feline's presence captivates the attention, as it moves elegantly through the spacious hall, surrounded by classical sculptures and Renaissance paintings. Its confident stride and majestic demeanor contrast beautifully with the artistic masterpieces displayed on the walls, creating a unique juxtaposition between nature and culture. The golden collar it wears adds a touch of sophistication, making the jaguar appear almost like a living exhibit within the gallery space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2770
|
videos/HRA_part2/2770.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its curved horns and brown coat, walks steadily across a rocky terrain, with a clear blue sky and distant mountains providing a scenic backdrop. The ibex navigates the rugged landscape with ease, its hooves firmly gripping the stone surface. It pauses momentarily, its head held high, surveying its surroundings before continuing its journey, moving gracefully among the boulders and cliffs. Throughout the scene, the ibex remains the central focus, its presence commanding attention against the stark beauty of the alpine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1032
|
videos/HRA_part1/1032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a navy uniform with a badge, cap, and sunglasses, stands at the edge of a zoo's flamingo enclosure, where vibrant pink birds congregate. The scene shifts slightly to reveal a clear blue pool within the zoological park, where the officer now interacts with the public, demonstrating water safety techniques. Nearby, children and families watch, some seated on benches under the shade of lush trees, while others lean on the railing, observing the swimming demonstration with interest. Throughout, the police officer remains engaged and attentive, fostering a sense of community and safety among the zoo visitors.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are not smooth."
}
] |
seed42_1026
|
videos/HRA_part0/1026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a beige jacket, black t-shirt, and khaki pants, stands thoughtfully at a hot springs site, contemplating a unique shot. Suddenly, a rhinoceros emerges from the mist, leaping gracefully over a small pond within the springs. The director watches intently, camera in hand, ready to capture the extraordinary moment as the sun sets behind, casting a golden hue over the scene. The rhinoceros, now the central figure, jumps with surprising agility amidst the steamy waters, creating an unforgettable juxtaposition of nature and wildlife against the backdrop of the director's vision.]"
},
{
"from": "gpt",
"value": "Bad. The rhinoceros's movements become abrupt, and it eventually undergoes a transformation."
}
] |
seed46_3006
|
videos/HRA_part2/3006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green environment, a small brown mouse stands on the edge of a natural pool, surrounded by dense shrubbery and tall grass, creating an intricate network of thickets. The mouse looks intently at the water, its ears perked and body alert. Suddenly, it bravely leaps into the clear, shimmering pool, swimming with surprising agility, its tiny paws propelling it through the water. As it swims, the camera captures the ripples created by its movement, highlighting the contrast between the busy activity of the mouse and the stillness of the thickets surrounding the pool.]"
},
{
"from": "gpt",
"value": "Bad. The brown mouse in the video is generally malformed."
}
] |
seed46_250
|
videos/HRA_part2/250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room filled with bookshelves, two young boys, one wearing a gray shirt and the other in a navy blue sweater, are diligently organizing books on a lower shelf. The atmosphere is calm and focused, with the boys working attentively side by side. One child carefully selects a book from a pile, examining it before placing it on the shelf, while the other arranges the books alphabetically, ensuring each title is correctly positioned. The room is warm and welcoming, with sunlight streaming in through a nearby window, casting a soft glow over the children as they engage in this educational activity together.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_2787
|
videos/HRA_part1/2787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a vast, icy landscape, two children in vividly colored swimwear are seen joyfully interacting with the glacier's edge, where a pool of crystal-clear water has formed. The girl, wearing a pink swimsuit, playfully splashes the water with her hands, her face alight with delight. The boy, in blue swimming trunks, sits on the ice, dipping his feet into the chilly waters, his expression one of cautious excitement. The camera captures the stark contrast between the vibrant colors of their swimwear and the monochromatic scenery of ice and sky, creating a striking visual tableau. Throughout the scene, the children's interactions with the glacial environment showcase their curiosity and wonder, highlighting the unique experience of swimming beside a glacier.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2885
|
videos/HRA_part1/2885.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a gray suit, white shirt, and blue tie, walks purposefully across a futuristic asteroid mining facility. The setting is a large, circular room with a high ceiling and industrial equipment, bathed in a warm orange glow. He carries a brown leather briefcase in his right hand, displaying a confident and focused demeanor. Behind him, the dimly lit interior of the asteroid can be seen, with mining machinery and workers in protective gear visible in the distance. The lawyer's strides are firm and decisive, highlighting his determination and professionalism in this unique and challenging environment.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's facial features in the video are generated blurry, and the fingers are deformed."
}
] |
seed46_2155
|
videos/HRA_part2/2155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars gracefully through the crisp, clear sky, its powerful wings spread wide against a backdrop of fluffy white clouds and a vibrant blue horizon. The eagle's piercing golden eyes and distinctive white-feathered head stand out prominently. It effortlessly glides over a vast, pristine landscape, featuring lush green forests and shimmering lakes, with the distant silhouette of snow-capped mountains providing a breathtaking contrast. The eagle's strong, brown body and large, feathered tail complete the image of this awe-inspiring bird in flight.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1366
|
videos/HRA_part1/1366.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit consisting of a gray t-shirt and blue jeans, sits at a desk in a classroom filled with other students. The room is brightly lit by large windows, casting natural light onto the desks and walls adorned with educational posters. The student yawns widely, covering their mouth with a hand, indicating tiredness during the class. The scene captures a relatable moment of fatigue in an everyday learning environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2423
|
videos/HRA_part1/2423.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate male musician, dressed in a black leather jacket, dark jeans, and a white T-shirt, sings into a microphone against a dimly lit, blurred background, evoking a sense of depth. His eyes are closed as he belts out a powerful note, showcasing his emotional connection to the music. His left arm is raised, gripping the mic stand, while his right hand passionately strums an electric guitar, amplifying the intensity of the performance. The scene is set in a small, intimate venue, with the audience's silhouettes visible in the background, creating a captivating atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, and the hands are twisted."
}
] |
seed44_2663
|
videos/HRA_part1/2663.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 desert-dwelling lizard, specifically a Bearded Dragon, is shown swimming underwater in clear, sunlit water. Its body is fully submerged, and it moves gracefully through the water, showcasing its rarely seen aquatic locomotion. The lizard's skin ripples as it propels itself forward, and its claws can be seen extended as it navigates the aquatic environment. The water is crystal clear, allowing for a detailed view of the lizard's texture and movement, contrasting with its typical arid habitat. Sunbeams penetrate the water, illuminating the scene and highlighting the unique sight of a lizard swimming.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2749
|
videos/HRA_part2/2749.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 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 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": "Bad. The pelican's claws are twisted, wings are twisted, and the head is slightly twisted."
}
] |
seed46_2395
|
videos/HRA_part2/2395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, ancient-looking turtle with a weathered, brown shell and algae growth moves slowly across a lush, green forest floor, surrounded by vibrant foliage and ferns. Its wise, calm eyes peer from beneath heavy, wrinkled eyelids, and its textured skin and claws are well-adapted to its woodland habitat. The scene is peaceful, with dappled sunlight filtering through the dense canopy above, highlighting the intricate patterns on the turtle's shell as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Normal. The tortoise in the video walks very slowly, and its movements are not smooth."
}
] |
seed46_1774
|
videos/HRA_part2/1774.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene set within the lush environment of a tropical dry forest, a young, smiling female cashier, wearing a red apron over a white blouse and black pants, energetically jumps over a small log. She lands gracefully, holding a miniature baseball bat, as if ready for an unexpected game amidst the dense vegetation. The vibrant green foliage and dappled sunlight create a vivid contrast against her outfit, capturing the spirit of adventure and playfulness in an unconventional setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's head, arms, and legs are distorted in the video."
}
] |
seed46_2051
|
videos/HRA_part2/2051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed anthropomorphic fox, wearing a doctor's white lab coat over a crisp blue shirt and a stethoscope around its neck, is seen swimming in a clear blue pool. The fox maintains a relaxed yet focused expression, showcasing its unique ability to swim effortlessly while fully clothed. The pool is surrounded by lush greenery, creating a serene atmosphere as the sunlight filters through the leaves, casting dappled shadows on the water's surface.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2379
|
videos/HRA_part0/2379.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a gray suit, sits at a desk cluttered with law books and papers, attentively reading a document. He momentarily pauses, lifting a fork loaded with pasta to his mouth, revealing his multitasking nature. The room is illuminated by the warm glow of a table lamp, casting a soft light on the busy scene. A cup of coffee and a glass of water sit nearby, within easy reach for this hardworking legal professional as he sustains himself through his demanding workday.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted, the face is slightly distorted, and the object in the person's hand is distorted."
}
] |
seed44_224
|
videos/HRA_part1/224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint, rustic market, a young female cashier, wearing a green apron with a name tag reading \"Ibex,\" diligently wipes down the countertop with a cloth. The wooden cash register stand is adorned with a small flower pot and a framed picture, adding a personal touch to the space. Ibex works efficiently, her movements confident and practiced, as she cleans the area where customers place their items for purchase. The background features shelves stocked with various goods, giving a glimpse into the variety of products available in the store.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1445
|
videos/HRA_part2/1445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned with vibrant orange beads and feathers woven into its fur, dances gracefully in the dappled sunlight of a lush savanna. Its body moves fluidly to an unheard beat, each leap and twist a display of raw power and elegance. Surrounded by tall grass swaying gently in the breeze, the cheetah's every motion is captured in high definition, from the flex of its muscles to the gleam in its eyes, embodying the spirit of the wild in a captivating dance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2915
|
videos/HRA_part0/2915.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": "Good. Basically no problem."
}
] |
seed44_2787
|
videos/HRA_part1/2787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a vast, icy landscape, two children in vividly colored swimwear are seen joyfully interacting with the glacier's edge, where a pool of crystal-clear water has formed. The girl, wearing a pink swimsuit, playfully splashes the water with her hands, her face alight with delight. The boy, in blue swimming trunks, sits on the ice, dipping his feet into the chilly waters, his expression one of cautious excitement. The camera captures the stark contrast between the vibrant colors of their swimwear and the monochromatic scenery of ice and sky, creating a striking visual tableau. Throughout the scene, the children's interactions with the glacial environment showcase their curiosity and wonder, highlighting the unique experience of swimming beside a glacier.]"
},
{
"from": "gpt",
"value": "Bad. The video does not generate the scene of the girl slapping the water with her hands and the boy dipping his feet into the cold water."
}
] |
seed42_1765
|
videos/HRA_part0/1765.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and sporting sunglasses, stands with his arms crossed, observing the scene at a busy dock. Suddenly, a majestic deer emerges from the background, filled with lush greenery, and leaps gracefully over a small obstacle, drawing the attention of the officer and dock workers alike. The officer watches intently as the deer bounds across the wooden planks, its movements fluid and effortless, before disappearing into the foliage beyond the docks. Throughout the scene, the officer remains poised and watchful, his presence a testament to the unexpected encounters that can occur even in the midst of urban landscapes.]"
},
{
"from": "gpt",
"value": "Bad. The deer's legs appear deformed."
}
] |
seed46_322
|
videos/HRA_part2/322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 European brown hare is seen swimming across a serene, glassy lake, its ears perked up and alert. It moves gracefully through the water, showcasing its rarely-seen swimming ability. The hare's body, including its long legs and large hind feet, propels it forward as it navigates the calm lake surface. The scene is set against a lush green landscape, highlighting the unexpected yet captivating sight of a hare swimming.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.