video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_138
|
videos/HRA_part2/138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant tropical dry forest, a talented female musician, dressed in a flowy yellow sundress, sits atop a fallen tree trunk, surrounded by lush greenery and vibrant wildflowers. She gently caresses her acoustic guitar, playing a soulful melody that resonates throughout the forest. Sunbeams filter through the canopy overhead, casting dappled light onto the forest floor, as birds chirp in the background, adding to the serene atmosphere. The musician's eyes are closed in concentration, her fingers gracefully moving across the strings, creating a harmonious symphony in the midst of nature's splendor.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2022
|
videos/HRA_part2/2022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a brown plaid shirt and blue jeans, stands in the shallow end of a clear blue swimming pool, looking curiously at a squirrel perched on the edge. The squirrel, standing upright on its hind legs, holds a nut in its paws and peers intently into the water. Sunlight filters through the leaves of nearby trees, casting dappled shadows on the pool's surface and the green grass surrounding it. The farmer, with a straw hat tilted back on his head, seems to share a moment of mutual interest with the bushy-tailed creature, both pausing in their day's activities.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's body and limbs undergo deformative mutations when it performs actions."
}
] |
seed46_2418
|
videos/HRA_part2/2418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a focused doctor, dressed in a white lab coat, leans over a table, examining a specimen. On the floor below, a tiny mouse scurries across the wooden surface, navigating the shadows beneath the furniture. The scene alternates between the doctor's intense study and the mouse's cautious movements, highlighting the stark contrast between the clinical environment and the unexpected presence of the small creature.]"
},
{
"from": "gpt",
"value": "Bad. The mouse in the video was generated abnormally, with twisted and deformed limbs, and the scene suddenly changed in the middle frame."
}
] |
seed44_3017
|
videos/HRA_part1/3017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a high-tech kitchen illuminated by neon lights, a chef dressed in a white apron and cap, wearing a gas mask, carefully handles a container of antimatter, its energy subtly pulsing within a secure, futuristic device. The chef, displaying remarkable courage, begins to run through the sleek, metallic corridors of a vast space station, the antimatter safely secured in a specialized briefcase designed to withstand extreme conditions. With each stride, the urgency of the situation becomes palpable, the chef's determination evident in the focused gaze beneath the mask, as they navigate the complex towards an unknown destination.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2152
|
videos/HRA_part1/2152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a small monkey wearing a red bow tie and a golden ring on its tail is leaping from one floating bookshelf to another in a vast space library. The shelves, filled with ancient books bound in brown leather, are suspended in zero gravity, illuminated by a warm, golden light. The monkey swings its arms in excitement as it jumps, revealing a joyful, playful spirit in the cosmic setting, surrounded by stars and galaxies. The library's architecture is grand, with arches and columns made of what appears to be stardust, adding to the surreal and magical atmosphere of this extraordinary space.]"
},
{
"from": "gpt",
"value": "Bad. The little monkey in the video has a twisted body, head, feet, legs, and claws."
}
] |
seed46_181
|
videos/HRA_part2/181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A visionary director, wearing a brown jacket, sits on a chair, intently operating a camera, capturing footage of a rhinoceros in a barren desert landscape, with a massive white hole explosion occurring in the distance. The rhinoceros, filmed in extreme close-up, slowly crawls across the sandy terrain, its textured skin and concentrated gaze highlighting its determination. The director, now seen from behind, continues to film the rhinoceros as it traverses the challenging environment, with the white hole explosion's brilliant light illuminating the scene, creating a surreal and captivating contrast between the earthbound creature and the cosmic event.]"
},
{
"from": "gpt",
"value": "Normal. The rhino's movements are not smooth."
}
] |
seed42_2861
|
videos/HRA_part0/2861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional-looking male chef, donning a white chef's jacket and black pants, stands in a bustling kitchen environment, pulling a large, fully loaded dish from a high-end, commercial-grade oven. The oven is integrated into a sleek, stainless steel kitchen setup. The chef exhibits a focused expression, displaying his expertise and confidence. The dish, brimming with an exquisite culinary creation, is positioned at the center of the frame, highlighting its appeal against the busy kitchen backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The chef's hand in the video is deformed."
}
] |
seed44_1086
|
videos/HRA_part1/1086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of an ibis's face, its piercing yellow eye set against a backdrop of dark feathers, commands attention. The bird's distinctive curved bill, a striking contrast to its plumage, adds character. Its textured feathers, a mix of brown and black, envelop the head, while the yellow iris and bill tip pop against the dark plumage. The ibis's head tilts slightly, revealing a patch of bare red skin, and its textured feathers frame the captivating facial features, capturing the essence of this unique bird species.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2905
|
videos/HRA_part1/2905.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, recognizable by its black ears and eye patches, crawls on all fours across a lush, green forest floor, its fur a striking contrast against the vibrant vegetation. It moves slowly, carefully placing each paw, showcasing its strength and agility. The panda's attention is drawn to something in the distance, its ears perked, adding a layer of curiosity to its demeanor. Surrounded by bamboo plants, a staple in its diet, the panda continues its crawl, encapsulating the essence of its natural habitat in every deliberate motion.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
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 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 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": "Good. No obvious problems."
}
] |
seed46_1787
|
videos/HRA_part2/1787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a brown vest and khaki trousers, races through lush, green vineyards, his expression one of determination. He is followed closely by a prehistoric mammoth, its massive body and shaggy fur moving surprisingly swiftly through the rows of grapevines. The sun, low in the sky, casts long shadows across the fertile landscape, highlighting the unusual pair as they navigate the terraced fields. In the background, a rustic barn and rolling hills provide a classic countryside setting, contrasting with the extraordinary sight of the farmer and the mammoth in motion.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1153
|
videos/HRA_part0/1153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male worker, wearing a brown shirt and green shorts, attentively wipes an Asian elephant's face using a small cloth. The elephant, with its trunk slightly raised, stands calmly next to a wooden structure within a spacious enclosure, possibly at a wildlife sanctuary. The man continues to clean the animal's eye area, showing care and familiarity, while the elephant remains still, indicating a trusting relationship between the two. Throughout, the worker focuses on his task, gently tending to the creature's needs in a peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The elephant's movements in the video are unsmooth."
}
] |
seed42_2939
|
videos/HRA_part0/2939.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 bobcat, with distinctive ear tufts and a short tail, leaps over a checkout counter in slow motion, its muscles tensing and releasing with each bound. The cash register, with its glowing display and scattered coins, provides context to the setting. The cashier, wearing a red apron and a surprised expression, watches the wild cat jump, creating an unexpected and captivating moment. The bobcat's leap is captured in mid-air, highlighting its agility and grace, against the backdrop of a typical supermarket checkout area.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the mountain cat's body twisted, head twisted, claws twisted, and legs twisted."
}
] |
seed46_1437
|
videos/HRA_part2/1437.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning rainbow trout, exhibiting vibrant hues of pink, silver, and green, gracefully swims in a clear, freshwater stream, surrounded by smooth stones and lush vegetation. The water gently cascades over rocks, creating a serene environment for the fish. Sunlight filters through the surface, highlighting the trout's shimmering scales and fins as it navigates the current with effortless ease. The trout occasionally opens its mouth, filtering oxygen from the water, demonstrating its natural survival skills in the pristine aquatic habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2210
|
videos/HRA_part1/2210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, adorned in a spacesuit and helmet, stands on the lunar surface, illuminated by the Earth's glow, holding a leash attached to a lion. The lion, also wearing a miniature spacesuit and helmet, jumps playfully in the low gravity environment. Both figures cast long shadows against the moon's dusty terrain, with the Earth shining brightly in the dark, star-studded sky. This surreal scene combines elements of space exploration, wildlife, and human ingenuity in a single captivating frame.]"
},
{
"from": "gpt",
"value": "Bad. The lion's movements in the video are not smooth."
}
] |
seed44_1503
|
videos/HRA_part1/1503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate doctor, wearing a white lab coat, blue shirt, and khaki pants, gently caresses a small, brown squirrel nestled in her hands. The scene is set in a cozy, well-lit room with wooden floors, where the doctor, sporting a ponytail, glasses, and a warm smile, tenderly holds the squirrel. The focus is on the interaction between the caring medical professional and the tiny creature, emphasizing the nurturing bond formed in this peaceful environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1307
|
videos/HRA_part0/1307.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef wearing a classic white uniform and toque walks alongside a bobcat on a leash in a lush, green park. The chef, holding a large bunch of fresh herbs, interacts casually with the curious bobcat, which wears a matching chef's hat, adding a touch of humor. The two stroll past a row of vibrant red tulips, drawing attention with their unusual companionship. The chef, maintaining a professional demeanor, occasionally glances at the bobcat, ensuring its comfort during their walk. The setting, a well-manicured garden with neatly trimmed hedges, provides a picturesque backdrop for this unlikely duo.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the chef and the lynx walking, with movements that are mostly normal, though slightly uncoordinated."
}
] |
seed46_1398
|
videos/HRA_part2/1398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with curly brown hair tied back in a ponytail and wearing a red apron over a casual outfit stands in a modern kitchen, illuminated by bright overhead lights. She focuses intently on slicing a red bell pepper on a white cutting board, her silver ring catching the light. Next, she stirs a sizzling pan of vegetables on a stainless steel stove, steam rising from the pan. Then, she adds a pinch of salt and a sprinkle of fresh herbs to the dish, enhancing its aroma. Finally, she smiles as she plates the finished meal, garnishing it with a sprig of parsley, ready to serve a delicious dinner.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate scenes of the woman adding salt and herbs to the dish, or plates the finished meal and garnishes it with a sprig of parsley."
}
] |
seed46_1094
|
videos/HRA_part2/1094.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space worker, clad in a high-tech, neon-accented spacesuit, traverses a vast, ethereal galactic nebula, the swirling cosmic clouds of reds and purples forming a breathtaking backdrop. The figure moves with purpose, the lights from their suit casting dramatic shadows against the interstellar gas and dust. A closer shot reveals the worker's faceplate, reflecting the mesmerizing nebula, highlighting their isolated journey among the stars. As they walk, the nebula's colors swirl around them, creating a stunning visual of a human amidst the grandeur of the universe.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2365
|
videos/HRA_part2/2365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, adorned in hues of green, orange, and blue, swims gracefully among the coral reefs, its beak-like mouth distinctive against the colorful underwater landscape. It forages for food, nibbling on algae-covered rocks, showcasing its unique feeding behavior. The fish's body, covered in a protective layer of mucus, shimmers as it moves through the crystal-clear waters, surrounded by other marine life. Against the backdrop of the reef, the parrotfish's colors stand out, making it a captivating subject in the aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2181
|
videos/HRA_part2/2181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Caspian tern soars gracefully through the air, its large size and robust build evident as it navigates the skies above a serene coastal landscape. With a striking orange-red bill that is thick and strong, this bird exemplifies power and agility. Its plumage is predominantly white, with a faint tinge of grey on the back, and its wings display black tips that contrast beautifully with the rest of its feathers. As it glides over the water, the tern's keen eyes search for prey, showcasing its hunting prowess against the backdrop of a calm sea and a clear blue sky.]"
},
{
"from": "gpt",
"value": "Normal. The terns flying in the video are basically normal, but there is slight disharmony in their movements."
}
] |
seed44_1313
|
videos/HRA_part1/1313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene unfolds on a bustling Shanghai street, where a creative writer, dressed in a brown jacket and khaki pants, kneels on the pavement, engrossed in scribbling notes. Beside them, an unexpected giraffe, adorned with a red bow tie, also kneels, observing the writer with curiosity. The vibrant urban landscape, filled with pedestrians and vehicles, serves as a lively backdrop, contrasting the unusual duo's focused yet peculiar crawling position on the crowded sidewalk.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2926
|
videos/HRA_part2/2926.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a gray suit, white shirt, and striped tie, stands on a chair in a modern office space with high ceilings and large windows. Holding a light bulb, he appears mid-action, changing the bulb with determination. The office is filled with contemporary furniture and technology, including a sleek desk, ergonomic chair, and flat-screen monitor. The scene is lit by the natural light streaming in from the windows, casting a warm glow on the lawyer as he completes his unexpected task.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer can be clearly seen changing the light bulb in the video, with actions that are not continuous and smooth, showing a lack of coordination."
}
] |
seed44_133
|
videos/HRA_part1/133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone gray wolf, standing in a lush, green meadow dotted with vibrant wildflowers, shakes its body vigorously to rid itself of water, its fur rippling and droplets flying in slow motion against the serene landscape. The wolf, with piercing yellow eyes, then looks directly at the camera, its powerful presence commanding attention against the backdrop of nature's beauty. After shaking, it stands still, water dripping from its thick fur, with the sun casting a warm glow on the scene, highlighting the wolf's resilience and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The wolf's body is twisted, its face is distorted, and its legs are deformed."
}
] |
seed44_2733
|
videos/HRA_part1/2733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two individuals sit side by side on wooden stools, engrossed in the meticulous task of hemming pants. One person, wearing a plaid shirt, focuses intently on the fabric spread across their lap, while the other, donning a gray sweater, holds a pair of scissors, ready to trim the excess material. Both use a sewing machine placed on a rustic wooden table, the sound of the needle punctuating the air as they work diligently. The scene is filled with tools of the trade, including spools of thread, a tape measure, and pins, all set against the backdrop of a warm, welcoming space adorned with shelves of craft supplies.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2551
|
videos/HRA_part2/2551.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, dressed in a flowing white robe with gold trim, stands in a vast, dimly lit space chamber, holding a fluffy rabbit gently against her chest. The chamber is filled with rows of benches, each occupied by similarly dressed figures, all facing an altar adorned with candles and space-themed decorations. The student caresses the rabbit lovingly, her face expressing deep reverence and peace, as the soft light from the candles illuminates the scene, casting a warm glow on everyone present. The rabbit, seemingly aware of its significant role, remains calm and still, adding a sense of serenity to the unique religious ceremony taking place among the stars.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not move."
}
] |
seed46_2681
|
videos/HRA_part2/2681.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer with short brown hair, wearing safety glasses, a gray shirt, and khaki pants, stands in a large industrial space filled with machinery. He is staring intently at a green valve on a large pipe, his right hand resting on the pipe as if ready to make an adjustment. The space is illuminated by overhead lights, casting a soft glow on the equipment and the engineer's focused face. Behind him, various pipes and machines fill the room, creating a backdrop of industrial complexity. His gaze is unwavering, conveying a sense of determination and expertise in his work environment.]"
},
{
"from": "gpt",
"value": "Normal. The caption mentions that the engineer's right hand is resting on the pipe, but in the video, it is the left hand that is resting on the pipe."
}
] |
seed42_18
|
videos/HRA_part0/18.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 North American porcupine, identified by its dark brown fur and quills, is seen jumping with surprising agility from branch to branch in a dense forest. The scene captures the porcupine's unique climbing skills as it leaps from one limb to another, highlighting its ability to navigate its arboreal habitat. The video focuses on the porcupine's movements, emphasizing the contrast between its slow, deliberate gait when on solid ground and its sudden bursts of energy as it propels itself through the air. The forest surroundings provide a natural setting, with sunlight filtering through the canopy to illuminate the porcupine's quills during its jumps.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the porcupine jumping from one branch to another as mentioned in the caption."
}
] |
seed42_2471
|
videos/HRA_part0/2471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a distinguished doctor, clad in a lab coat and stethoscope, runs alongside a prehistoric mammoth through an industrial landscape dotted with colossal power plants. Their breaths form visible clouds in the crisp air, as they navigate the terrain under an overcast sky. The mammoth's massive frame and the doctor's determined gaze create an unlikely alliance, their journey unfolding against the backdrop of towering smokestacks and power lines, blending elements of fantasy and reality in a captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the doctor and the prehistoric mammoth running, but the running movements are not continuous and smooth, showing some inconsistencies."
}
] |
seed44_1462
|
videos/HRA_part1/1462.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a light brown jacket, kneels in a modest living room to feed three domesticated cats. The room features a small, cluttered table, a beige couch, and a brown coffee table. The officer demonstrates kindness and care, pouring food into a green bowl as the cats eagerly surround him. Moments later, he gently pets one of the cats, showcasing a softer side of law enforcement, with the cats nestled around the bowl and the comforting interior of the home providing a backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The cat's limbs and the police officer's hand are missing in the video, the cat's body is distorted, the arms are twisted, the paws are twisted, the face is distorted, and the people and objects are distorted."
}
] |
seed42_2530
|
videos/HRA_part0/2530.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary black rhinoceros, distinguished by its squared-off lips and grayish-brown skin, wipes itself vigorously against a tree trunk in the midst of dense savanna vegetation. The action is captured in high definition, showcasing the rhino's determination and the textural contrast between its rough hide and the tree bark. The scene unfolds against a backdrop of lush greenery, highlighting the animal's natural habitat. Moments later, the rhino continues rubbing against the tree, emphasizing its commitment to the self-cleaning ritual, with the verdant foliage and distant trees framing the action in a captivating wildlife moment.]"
},
{
"from": "gpt",
"value": "Normal. The rhino's horn was not generated, there were issues with the nose and mouth generation, problems with the toe generation, and the trees were generated abnormally."
}
] |
seed46_2119
|
videos/HRA_part2/2119.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": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1789
|
videos/HRA_part1/1789.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 agile antelope leaps majestically across the sun-drenched savanna, its powerful legs propelling it high above the golden grasses. The animal, distinguished by its brown fur and impressive horns, is captured mid-jump, with all four feet off the ground, highlighting its remarkable athleticism. In the background, a vast landscape stretches out under a clear blue sky, dotted with distant trees, emphasizing the vastness of the environment. The scene is one of raw nature, with the antelope's leap frozen in time, showcasing the beauty and grace of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2773
|
videos/HRA_part2/2773.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female teacher, clad in a gray blazer, white blouse, and dark pants, walks purposefully across a bustling university campus, animatedly discussing the recent discovery of a habitable exoplanet. She gestures enthusiastically, engaging with her students who walk alongside her, their faces alight with curiosity and excitement. The backdrop shifts subtly from the interior of a modern lecture hall, filled with attentive students, to the outdoor campus, where the teacher continues her captivating lesson under the open sky, emphasizing the significance of the exoplanet find. Throughout the scene, the teacher's energy and dedication to teaching are evident, inspiring her students to explore the wonders of the universe.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher's face generation is abnormal, and both the female teacher and the student's fingers are deformed."
}
] |
seed44_2070
|
videos/HRA_part1/2070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, iridescent green and purple, hovers near a red feeder, its wings a blur of motion against a clear blue sky, set against the backdrop of a lush garden filled with various flowers and greenery. The tiny bird's red beak is extended toward the feeder, while its body remains remarkably still despite the rapid wing beats. Its vibrant feathers catch the sunlight, creating a shimmering effect as it feeds, encapsulating the beauty and agility of nature in this serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1511
|
videos/HRA_part2/1511.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, standing in a lush green meadow under a vast blue sky, begins by shaking its bushy tail, sending droplets flying in a slow-motion spray. It then proceeds to wipe its face with a paw, leaving water droplets clinging to the fur around its eyes and nose. The fox's alert ears and curious gaze are highlighted as it pauses mid-wipe, showcasing the intimate grooming moment in stunning detail against the serene natural backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The fox's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1182
|
videos/HRA_part0/1182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large herd of African buffalo, distinguished by their massive curved horns and sturdy builds, gallop across a sunlit savanna, stirring up clouds of dust in their wake. The lead buffalo, a dominant male, charges ahead with determination, followed closely by the rest of the herd. They run through tall grass, which sways in the breeze, creating a dramatic contrast against the clear blue sky. The action is captured in high definition, focusing on the power and grace of these magnificent animals as they thunder across the landscape.]"
},
{
"from": "gpt",
"value": "Normal. The buffalo's head and claws in the video have issues."
}
] |
seed44_2252
|
videos/HRA_part1/2252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 green sweater and brown trousers, kneels on a lush, grassy field as they observe a graceful gazelle. The writer, with a notebook in hand, carefully documents the gazelle's movements from a crawling position, capturing the serene atmosphere under a clear blue sky. The scene highlights the writer's dedication to their craft, as they immerse themselves in nature to gather inspiration, while the gazelle, unaware of the observer, continues its elegant grazing nearby.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1888
|
videos/HRA_part1/1888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, empty warehouse with high ceilings and large, open spaces, four young children, two boys and two girls, are gleefully jumping and laughing as they play a game of tag. The boys wear matching blue striped shirts and khaki pants, while the girls are dressed in pink floral dresses and white leggings. The warehouse's concrete floors and metal beams provide an industrial yet spacious setting for their energetic play. The children's joyous expressions and animated movements capture the essence of carefree childhood fun in an unconventional environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1588
|
videos/HRA_part1/1588.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savannah, two zebras engage in a tender moment, their striped bodies gently touching as they caress each other. One zebra, with its mane flowing in the breeze, nuzzles the face of another, their bond evident in the softness of their interaction. The scene is framed by distant acacia trees and a clear blue sky, emphasizing the intimacy shared between these majestic creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1942
|
videos/HRA_part2/1942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male chef, donning a traditional white chef's uniform with a name tag reading \"Chef Tyler,\" sits at a wooden table in a rustic, candlelit dining room. He savors a spoonful of his signature dish, a creamy risotto, with eyes closed in blissful concentration. His neatly trimmed beard and mustache, along with short brown hair, add to his distinguished appearance. Behind him, a bustling restaurant kitchen is visible through an open doorway, offering a glimpse into the energetic culinary environment. Throughout the scene, Chef Tyler continues to enjoy his meal, occasionally glancing up with a satisfied smile, embodying the essence of a passionate and accomplished chef relishing his own creation.]"
},
{
"from": "gpt",
"value": "Bad. The chef's fingers in the video are not fully generated, and there are issues with the generation of the spoon, the chef's eyes, and the mouth during eating."
}
] |
seed44_301
|
videos/HRA_part1/301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 marlin breaches the sparkling turquoise ocean, its sleek indigo body glistening in the sunlight. The fish soars through the air, its elongated rostrum pointed skyward, before plunging back into the sea with a splash. Surrounded by the vastness of the ocean, the marlin's powerful leap is captured against a backdrop of rolling waves and a cloud-dappled sky, showcasing the beauty and grace of this magnificent marine creature.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the marlin jumping out of the water and re-entering it with basically normal movements, but there is some lack of coordination."
}
] |
seed44_227
|
videos/HRA_part1/227.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, middle-aged farmer with a short beard, dressed in a green flannel shirt, brown vest, brown trousers, and brown boots, hikes across a lush, green pasture. The vibrant colors of his clothing contrast beautifully with the verdant landscape. In the first scene, he pauses to look up at the sky, which is partly cloudy, indicating a pleasant day. Then, he continues hiking, walking uphill towards a dense forest in the distance, the rolling hills providing a stunning backdrop. Next, he stops to observe a group of sheep grazing nearby, his presence conveying a sense of peace and harmony with nature. Lastly, he is seen walking along a narrow path bordered by tall grass, his figure becoming smaller as he moves further away, encapsulating the spirit of adventure and connection to the land.]"
},
{
"from": "gpt",
"value": "Bad. The man's head, hands, and feet in the video are distorted, and the character's body suddenly flips from front to back in the middle frames."
}
] |
seed44_258
|
videos/HRA_part1/258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate female veterinarian, wearing a white lab coat and blue scrubs, gently feeds a small dog from a spoon, her caring nature evident in her warm smile. The clinic room is clean and modern, with stainless steel equipment and a large window providing natural light. Behind her, a poster about pet nutrition hangs on the pale green wall. On a nearby table, various pet food samples are neatly arranged, emphasizing the importance of proper animal care. Throughout the scene, the vet's loving interaction with the dog highlights her dedication to animal welfare.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's hand shows a deformity, and the spoon in her hand also becomes bent."
}
] |
seed44_2904
|
videos/HRA_part1/2904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bull moose, antlers wide and impressive, runs through a lush, green meadow under a clear blue sky, with a distant mountain range visible on the horizon. Its powerful legs propel it forward in a graceful gallop, kicking up small clouds of dust from the dry earth beneath its hooves. The moose's coat is a deep brown, nearly black, and its large body ripples with muscles as it bounds across the landscape, the embodiment of wild strength and freedom. In the background, tall trees frame the edges of the clearing, their leaves whispering softly in the breeze, while birds take flight, startled by the majestic creature's sudden movement.]"
},
{
"from": "gpt",
"value": "Normal. The moose's running motion in the video is not smooth and coordinated."
}
] |
seed42_2706
|
videos/HRA_part0/2706.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, donning a gray t-shirt beneath a clean white apron, expertly wields a large spoon and spatula as he stirs a sizzling pan on a commercial stove in a bustling kitchen. Amidst the steamy atmosphere, his focused eyes and neatly trimmed facial hair convey his dedication to culinary artistry. With a vibrant red bandana tied around his neck, he exhibits a unique flair while preparing a gourmet dish. The scene captures the essence of hard work and passion in the culinary world, as the chef's movements are fluid and purposeful, encapsulating the heart of the kitchen environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1059
|
videos/HRA_part0/1059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artistic individual, adorned in a red jacket, blue jeans, and a white t-shirt, explores the vibrant streets of Tokyo, holding a sketchbook and pencil. The bustling cityscape surrounds him, featuring neon signs, crowded sidewalks, and eclectic architecture. Suddenly, the scene shifts to a serene indoor swimming pool, where the same artist is seen diving into the water, the reflection of the pool lights creating a mesmerizing pattern on the ceiling. The artist swims with grace and determination, their red swim cap standing out against the blue water, encapsulating a moment of tranquility amidst the urban chaos.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2513
|
videos/HRA_part0/2513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a distinguished lawyer, clad in a classic black suit and white shirt, gently caresses the metallic surface of a Mars rover model placed on a wooden table. The room is dimly lit, casting dramatic shadows across the scene. The lawyer's face reflects a mix of fascination and professional poise, while the rover, adorned with intricate details and wheels designed for extraterrestrial terrain, stands as a symbol of human innovation and exploration. This intimate interaction between the legal world and space technology creates a thought-provoking narrative about the convergence of seemingly unrelated fields.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed and mutated."
}
] |
seed44_1352
|
videos/HRA_part1/1352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, resembling a young Russell Crowe, sits in a dimly lit room, deeply engrossed in sketching. He wears a white shirt with rolled-up sleeves, revealing a watch on his right wrist, and a black blazer draped casually over his shoulders. The room is adorned with various artworks, adding to the creative atmosphere. The actor's intense focus is evident as he draws, his face reflecting deep concentration. The camera captures his every move in stunning detail, from the way his fingers grip the pencil to the intensity in his eyes, all set against the backdrop of an art-filled room.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands in the video are distorted, with the pencil suddenly disappearing in the middle frames."
}
] |
seed42_2959
|
videos/HRA_part0/2959.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished with salt-and-pepper hair and a trimmed beard, stands in a dimly lit, cluttered bathroom. Dressed casually in a gray t-shirt, dark jeans, and a black jacket, he focuses intently on unclogging a blocked sink drain. His right hand grips a metal tool, while his left hand steadies the sink's rim. The scene captures his determination, with the bathroom's sparse details - a white toilet, a beige wall, and a small window - adding context to his solitary task. The director's serious demeanor and the bathroom's functional design emphasize the mundane yet necessary act of home maintenance.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands appear deformed."
}
] |
seed42_2642
|
videos/HRA_part0/2642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small hamster, with its distinctively furry cheeks and nose, energetically runs inside a clear plastic exercise ball. It scampers across a room filled with everyday objects like furniture and potted plants, providing a unique perspective on a typical living space. The hamster's movement is fluid and rapid, highlighting its determination and playful nature as it explores its surroundings within the safety of the transparent sphere.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's walking in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed46_1976
|
videos/HRA_part2/1976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, spotted leopard leaps across a mossy log in a dense, lush forest, its powerful muscles rippling under golden fur flecked with black rosettes. Towering trees with emerald canopies surround the scene, dappled sunlight filtering through the leaves, casting an ethereal glow. The big cat lands gracefully on the forest floor, strewn with ferns and fallen leaves, before bounding away into the undergrowth, demonstrating the apex predator's agility and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's legs show deformities, and its body has become distorted and elongated."
}
] |
seed46_1601
|
videos/HRA_part2/1601.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 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 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. No obvious problems."
}
] |
seed42_3084
|
videos/HRA_part0/3084.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform and black pants, stands outdoors in a garden, holding a shovel. He is surrounded by various plants, including leafy greens, carrots, and herbs like rosemary, thyme, and sage. The chef has short brown hair and a neatly trimmed beard, and he is digging into the rich soil with determination, perhaps searching for fresh ingredients for his culinary creations. The scene is set against a backdrop of wooden crates and greenery, with a hint of sunlight filtering through the trees, casting dappled shadows on the chef and his gardening endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands appear deformed, and the shovel in his hand has also become distorted."
}
] |
seed44_1606
|
videos/HRA_part1/1606.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 high-tech facility with glowing blue accents, a muscular firefighter, wearing a full-body protective suit and helmet, stands against a backdrop of advanced machinery. He holds an antimatter containment device, a sleek silver sphere with intricate detailing, which emits a faint blue glow, signifying its active state. The setting shifts subtly to reveal the firefighter engaging in a lively dance, maintaining a firm grip on the containment device, now resting on his hip. The dance moves fluidly from a standing position into a crouched stance, with the firefighter's hands moving dynamically, all while keeping the device secure. Throughout the sequence, the futuristic setting, characterized by clean lines and blue accents, remains visible, adding a dramatic touch to the dancing firefighter's performance.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and deformed hands."
}
] |
seed42_128
|
videos/HRA_part0/128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its greenish-blue body with orange highlights and yellow fins, swims gracefully among the coral reefs. Its intricate scales resemble armor, providing a unique texture. It explores its underwater world, surrounded by various corals of purple, red, and orange, creating a stunning contrast against the blue water. The fish's beak-like mouth, a characteristic feature, is clearly visible as it feeds on algae-covered rocks, demonstrating its natural behavior in its marine habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1418
|
videos/HRA_part1/1418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a yellow reflective vest, blue latex gloves, and a badge, runs with purpose toward a cluster of factories in the background. The factories feature large smokestacks, metal siding, and concrete exteriors, set against a cloudy gray sky. The officer's intense gaze and focused posture convey urgency as they sprint across a desolate industrial landscape, the factories' imposing structures looming ominously behind.]"
},
{
"from": "gpt",
"value": "Normal. The finger generation of the police in the video is defective."
}
] |
seed42_2395
|
videos/HRA_part0/2395.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, 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": "Bad. The video shows too many limbs of the turtle, and the eyes are not fully generated."
}
] |
seed42_1867
|
videos/HRA_part0/1867.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, wearing a khaki safari outfit complete with a vest, pants, and hat, walks alongside a capybara on a leash. They are strolling on a concrete path that winds through a lush, green landscape filled with trees and shrubs. The capybara, the world's largest rodent, is shown in profile, moving at a relaxed pace beside the human. The setting is a serene, outdoor environment, possibly within a zoo or wildlife sanctuary, where the two amble together in a scene that highlights the unique bond between the caretaker and the animal.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, the hand is twisted, the leg is twisted, and the capybara's leg is twisted."
}
] |
seed42_206
|
videos/HRA_part0/206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, distinguished by its black and white striped face and brown fur, scurries through a network of intricately dug tunnels in a dimly lit sett. The animal, with its stocky build and sharp claws, moves swiftly and purposefully, navigating the narrow passages with ease. As it runs, the texture of the tunnel walls, composed of earth and roots, becomes apparent, providing a natural contrast to the badger's movement. Throughout the sequence, the focus remains on the badger's journey within the tunnel system, emphasizing its agility and familiarity with its subterranean habitat.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the European badger in the video are missing, and the facial generation is deformed."
}
] |
seed42_2340
|
videos/HRA_part0/2340.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a casual outfit of a gray t-shirt and khaki pants, takes a break from his usual duties to fix a leaky faucet. He is shown kneeling before a bathroom sink, tools in hand, with a look of determination on his face. The scene is set in a small restroom, with beige walls and a window casting natural light onto the countertop. As he works, the camera captures his focused expression and the intricate details of the plumbing, highlighting the contrast between his customer service role and his unexpected handyman task.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_2576
|
videos/HRA_part2/2576.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a casual outfit of a gray hoodie and blue jeans, diligently cleans a large window in a modern building, surrounded by other windows. The natural light from outside illuminates the space, casting a warm glow on the young cleaner. The scene is set in a minimalist room with white walls and hardwood floors, adding to the clean aesthetic. The student, with a focused look on their face, uses a squeegee and a bucket of soapy water to ensure every inch of the glass is spotless, reflecting their commitment to the task at hand.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video cleans the glass very unsmoothly, with uncoordinated movements."
}
] |
seed46_170
|
videos/HRA_part2/170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a black beanie and glasses, sits at a modern desk, engrossed in typing on a sleek laptop. The scene is set in a cozy room with a brick wall and a wooden shelf filled with books, plants, and a clock. Morning sunlight softly illuminates the space, casting a warm glow on the writer's face. A cup of coffee sits nearby, a trusted companion during the creative process. The writer occasionally glances at notes spread across the desk, incorporating ideas into the digital manuscript, capturing the essence of dedication and inspiration in the art of writing.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are missing, and the books on the bookshelf are not fully placed."
}
] |
seed42_1400
|
videos/HRA_part0/1400.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 badger, with its distinct black and white striped face and grey fur, is seen in a natural woodland setting. It stands on its hind legs, using its front paws to wipe its face meticulously, cleaning itself in the early morning light. The action is repeated several times, emphasizing the creature's grooming habits, all while surrounded by lush green foliage and undergrowth, giving a sense of the animal's natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1388
|
videos/HRA_part0/1388.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sunlit indoor environment, three young children sit on a large, comfortable sofa, each gently caressing a small rabbit. One child, dressed in a blue jacket, has short blond hair and a joyful smile, cradling a white rabbit with care. Another child, wearing a yellow shirt, has brown hair and a peaceful expression, softly petting a brown rabbit. The third child, clad in a red hoodie, has curly dark hair and a serene look, tenderly stroking a gray rabbit. The room is filled with a sense of calm and happiness, as the children enjoy the company of the adorable bunnies.]"
},
{
"from": "gpt",
"value": "Normal. The child's clothes in the video are inconsistent with the text."
}
] |
seed46_2474
|
videos/HRA_part2/2474.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a black outfit with a leather jacket, walks down a dimly lit street at night, a guitar case in hand, as a lizard scurries across the cobblestones beside him. The scene is set under the glow of a single streetlamp, casting long shadows and highlighting the textured walls of the surrounding buildings. The musician, with tousled dark hair and a determined look, strides purposefully forward, while the agile lizard, with its distinctive green and brown scales, moves swiftly alongside, both seemingly on a mysterious journey through the urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The lizard in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed46_2359
|
videos/HRA_part2/2359.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, clad in a vibrant pink uniform and wearing a traditional cap, joyfully dances alongside a large, gentle elephant in a lush, green outdoor setting. The pair moves in perfect harmony, their spirits uplifted by the warm sunlight filtering through the leaves overhead. The nurse's face is aglow with happiness, her eyes closed in blissful abandon, while the elephant sways gracefully, its trunk raised in a playful salute to their shared moment of pure delight.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_12
|
videos/HRA_part1/12.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gun holster, leaps into the air in the middle of a vast, temperate grassland. The landscape is dominated by knee-high green grasses and a few scattered oak trees, with the horizon stretching far into the distance. The officer's feet leave the ground, capturing a moment of action and energy, as the rolling hills and clear blue sky provide a serene contrast to the dynamic scene. The officer's movements are sharp and decisive, embodying the spirit of law enforcement in the open, wild environment of the grasslands.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_289
|
videos/HRA_part1/289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, gently caresses another meerkat lying on the ground, creating a tender and intimate moment. The first meerkat, with brown spots and alert eyes, uses its front paws to softly touch and comfort the other, which responds with closed eyes, indicating relaxation and trust. The scene takes place under the shade of a small bush in the savanna, with the soft, warm sunlight illuminating the interaction, highlighting the bond between these social animals.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2409
|
videos/HRA_part1/2409.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vibrant coral reef ecosystem, a pair of butterfly fish, characterized by their distinctive black stripes and oval-shaped bodies, gracefully swim among the colorful corals and anemones. One fish displays a striking yellow hue with bold black markings, while the other exhibits a more subdued brown and white pattern. They navigate the intricate underwater landscape, their movements synchronized, as they explore the nooks and crannies of the reef in search of food. The scene is illuminated by the filtered sunlight that penetrates the clear blue water, casting dappled light on the fish and their surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1368
|
videos/HRA_part0/1368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, reminiscent of Chris Hemsworth, is seen in a modern, minimalistic living room with large windows and plenty of natural light. He wears a navy blue t-shirt, dark jeans, and a wedding band, giving him an approachable, everyman appeal. The actor is intently focused on assembling a piece of flat-pack furniture, such as an IKEA dresser, using a screwdriver and following the instruction manual. The scene conveys a sense of relatability and domesticity, as the celebrity navigates the familiar challenge of putting together home furnishings.]"
},
{
"from": "gpt",
"value": "Normal. Hand deformity appears."
}
] |
seed46_2330
|
videos/HRA_part2/2330.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating underwater scene, a large, ghostly jellyfish with a brownish hue and intricate patterns floats serenely, its trailing tentacles creating mesmerizing movements against a dark blue background. Another jellyfish appears, smaller and more transparent, with delicate bell-shaped bodies and fine, trailing tendrils that seem to glow softly in the mysterious depths. The camera focuses on a stunning, semi-transparent jellyfish with a large bell and long, flowing tentacles that appear to sparkle, evoking a sense of enchantment and wonder in the deep blue sea. Lastly, a beautiful, clear jellyfish with a large bell and fine, trailing tendrils is captured in a captivating close-up, its body illuminated by a soft glow as it gently pulsates through the water, showcasing the mesmerizing beauty of these ethereal creatures.]"
},
{
"from": "gpt",
"value": "Normal. The jellyfish's movements in the video are basically normal, with slight inconsistency."
}
] |
seed46_233
|
videos/HRA_part2/233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a plaid shirt, denim overalls, and a worn baseball cap, stands in a modern kitchen. He methodically unloads a sleek, stainless steel dishwasher, handling each plate and utensil with unexpected gentleness. The contrast between his calloused hands and the shiny, clean dishes highlights the unusual domestic task for someone more accustomed to farm chores. The kitchen is spacious and well-lit, featuring granite countertops and contemporary appliances, offering a glimpse into the farmer's home life beyond the fields.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_1567
|
videos/HRA_part1/1567.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, verdant garden filled with vibrant flowers and greenery, two young children, a boy and a girl, are happily engaged in gardening activities under a clear blue sky. The boy, wearing a red shirt and khaki shorts, attentively waters plants with a small watering can, while the girl, clad in a pink dress and white shoes, diligently digs soil using a tiny shovel. They both wear wide-brimmed hats to shield them from the sun. Nearby, a wooden bench sits beside a stone walkway, and a white picket fence surrounds the garden, completing the idyllic scene of youthful enthusiasm and nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, and the face is deformed."
}
] |
seed42_2465
|
videos/HRA_part0/2465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious brown monkey, with its fur ruffled by the breeze, is seen playfully paddling in a tranquil body of water, surrounded by lush green foliage. It uses its arms to splash about, moving gracefully through the clear blue water, with trees and plants in the background framing the scene. The monkey's expressive face shows delight as it swims, its limbs working rhythmically beneath the surface, and droplets of water scatter around it, capturing the joy of this unexpected aquatic adventure.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1508
|
videos/HRA_part0/1508.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint beachside store, a young cashier, wearing a red apron over a white t-shirt and blue jeans, interacts with customers against a backdrop of ocean views through the window. Moments later, the focus is on the cashier, who is attentively counting change for a customer, with the sound of the ocean subtly heard in the background. Then, the cashier is shown organizing items on the counter, the ocean's calming presence visible outside. Lastly, the scene captures the cashier's hands as they handle transactions, the ocean view providing a serene backdrop throughout the interactions. Note: The term 'crawling' was not included as it does not fit naturally into the scene without causing confusion or requiring a scene transition, which is against the guidelines.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted, and the arm is twisted."
}
] |
seed46_1259
|
videos/HRA_part2/1259.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a museum hall with marble floors, an antelope taxidermy mount is displayed under a spotlight, its majestic form captured mid-leap. A diligent custodian wearing a green apron wipes the glass display case, ensuring the exhibit is pristine. The antelope, with its striking coat and alert posture, seems to leap over a miniature landscape within the display. The custodian, in a green uniform, carefully cleans the case, her reflection visible alongside the antelope's image. Throughout, the museum's grandeur is evident, with high ceilings, ornate moldings, and other exhibits surrounding the featured antelope.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, and the face is deformed."
}
] |
seed44_2798
|
videos/HRA_part1/2798.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, typically terrestrial, is shown swimming in a serene lake under a cloudy sky, creating a rare and captivating scene. Its body, adapted for digging, moves surprisingly gracefully through the water, showcasing its unexpected aquatic abilities. The badger's head, with distinctive black and white stripes, breaks the water surface as it propels itself forward with powerful strokes, leaving ripples across the calm lake. Surrounding trees and foliage frame the peaceful setting, highlighting the unusual yet mesmerizing sight of this normally land-dwelling creature taking to the water.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3030
|
videos/HRA_part1/3030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 human-like jackal, dressed in a red apron and name tag, stands behind a checkout counter. The background features a vibrant, turquoise water surface, suggesting a swimming pool or body of water. The jackal, with its distinctive canine features and upright posture, interacts with customers, handling items scanned over a register. The setting is illuminated by bright, warm lighting, casting a glow on the turquoise water, which stretches out behind the cashier area, merging the indoor and outdoor environments in an unexpected juxtaposition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2603
|
videos/HRA_part1/2603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, smoke-filled environment, a firefighter wearing full gear, including a helmet and breathing apparatus, crawls through a confined space. The setting is a high-tech facility, indicated by the presence of an antimatter containment unit, which is a large, cylindrical container with intricate machinery and glowing blue lights, seen in the background. The firefighter's movements are slow and deliberate, emphasizing the hazardous conditions and the need for caution. Despite the challenging circumstances, the firefighter's determination is evident, as they navigate the narrow passage with a flashlight in hand, illuminating the path ahead. The overall scene conveys a sense of urgency and danger, with the firefighter's mission being critical to the safety of the facility and its personnel.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1659
|
videos/HRA_part0/1659.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and cap, walks through a bustling space casino, neon lights casting an otherworldly glow on the patrons. Among them, a meerkat stands upright, wearing a tiny tuxedo, its eyes wide with wonder as it navigates the futuristic gaming tables, slot machines, and alien creatures. The officer, maintaining a watchful eye, ensures order in this eclectic mix of species and activities, all set against the backdrop of a grand, space-themed casino.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's whiskers in the video are not fully generated, there are issues with the eyes, and some fingers are missing."
}
] |
seed44_1004
|
videos/HRA_part1/1004.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 muscular firefighter, dressed in full gear and a yellow reflective jacket, interacts with a graceful gazelle in a surreal, dreamlike scenario. They stand together in a shallow, clear blue swimming pool, surrounded by lush green foliage. The firefighter gently touches the gazelle's head, while the animal remains calm and curious. Both share the water, creating an unexpected yet harmonious connection between human, wildlife, and nature, all set against a backdrop of vibrant greenery and clear blue skies.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are a bit stiff."
}
] |
seed42_1386
|
videos/HRA_part0/1386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, white shirt, and khaki pants, finds himself in an unexpected scenario where he is energetically dancing in a meadow. Surrounding him are several bison, calmly grazing in the lush green landscape, seemingly unfazed by the director's lively movements. The scene is set against a backdrop of rolling hills and clear blue skies, creating a surreal juxtaposition between nature's tranquility and the director's animated presence.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the person show signs of deformity and mutation, and the face has also become distorted."
}
] |
seed44_1446
|
videos/HRA_part1/1446.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bee-eater perches regally on a branch, its vibrant plumage a stunning mix of green, blue, and brown feathers, set against a backdrop of lush foliage and clear blue sky. Its long, curved beak points upward, ready to snatch prey from the air. In the next frame, it takes flight, wings outstretched, revealing the striking contrast of its underbelly and the iridescent sheen of its back feathers. It swoops gracefully, capturing an unsuspecting insect in mid-air, before returning to its perch, triumphant, the captured prey visible in its beak, all set against the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video walks very unsmoothly, and the movements are not coordinated."
}
] |
seed44_270
|
videos/HRA_part1/270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A musician, wearing a red bandana, black leather jacket, and dark jeans, walks through an abandoned mine with caution. He carries a vintage guitar case, adding to his rugged, artistic persona. The mine, filled with debris and old machinery, provides a stark, industrial backdrop. The musician's confident stride and the detailed textures of the mine walls and floor convey a sense of exploration and mystery. As he moves deeper into the mine, the dim lighting highlights his silhouette, creating a dramatic effect. Throughout the video, the focus remains on the musician's journey, emphasizing his presence and the unique setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and head are distorted in the video."
}
] |
seed44_2950
|
videos/HRA_part1/2950.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny warbler perches on a thin branch, its vibrant yellow-green plumage contrasting beautifully against the lush green foliage of the forest. The bird, no bigger than a sparrow, displays its distinctive black facial markings and streaks, enhancing its charm. It tilts its head curiously, revealing its sharp, pointed beak, perfectly adapted for probing into bark crevices and catching insects. The warbler then flutters its wings, preparing to leap onto another branch, showcasing its agility and grace in the dappled sunlight filtering through the leaves above.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_237
|
videos/HRA_part1/237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly lush subtropical moist forest, a young, athletic female cashier, donning a green vest and khaki shorts, is depicted running with intense focus, her eyes fixed ahead. Suddenly, a cobra slithers across her path, its hood dramatically spread. Unfazed, she leaps gracefully over the snake, her action capturing a powerful moment of survival instinct. As she continues her run, the dense vegetation and towering trees of the subtropical environment envelop her, highlighting her determination and agility amidst the wild setting.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs are missing in the video, her face has generation issues, and the snake's body is deformed."
}
] |
seed42_2755
|
videos/HRA_part0/2755.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a dark green jacket, beige pants, and brown shoes, walks across a grassy field under a clear blue sky, carrying an easel and a canvas. The focus shifts to reveal a majestic antelope standing in the distance, its silhouette framed by the golden hour sunlight. The artist stops, observing the antelope intently, before setting up the easel and beginning to sketch the graceful creature against the backdrop of a serene landscape. The artist's hands move skillfully over the canvas, capturing the essence of the antelope in motion, with the rolling hills and distant mountains providing a stunning natural setting for this artistic endeavor.]"
},
{
"from": "gpt",
"value": "Bad. No artist wearing a dark green jacket, khaki pants, and brown shoes was generated, and there is no action of the artist's hands moving on the canvas."
}
] |
seed44_2211
|
videos/HRA_part1/2211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, prehistoric landscape filled with vibrant greenery and ancient flora, a colossal woolly mammoth tenderly caresses another smaller mammoth with its trunk, showcasing a rare, intimate moment between these majestic creatures. The larger mammoth, adorned with thick, shaggy fur and imposing tusks, gently touches the younger one, whose eyes reflect curiosity and trust. The backdrop features a dense forest, with sunlight filtering through the canopy, casting dappled shadows on the ground, highlighting the tenderness and connection shared between the two mammoths.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's movements in the video are not smooth."
}
] |
seed44_2646
|
videos/HRA_part1/2646.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a costumed character resembling a janitor, complete with a green jumpsuit, gray mustache, and brown hair, performs an energetic jump. This quirky figure, embodying both the roles of maintenance worker and woodland creature, is set against a neutral backdrop. The playful scene is enhanced by the addition of an animated beaver, which appears to mimic the janitor's jumping action, creating a comical and engaging visual narrative. Both characters are depicted in vibrant colors, with the beaver sporting realistic features and the janitor maintaining his distinct uniform and facial details.]"
},
{
"from": "gpt",
"value": "Bad. The facial features and fingers of the cleaner in the video have generation issues."
}
] |
seed44_1024
|
videos/HRA_part1/1024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds as a farmer, clad in a traditional straw hat and plaid shirt, steers a futuristic tractor through a vast cornfield under a twilight sky filled with stars. The tractor, equipped with advanced technology and neon lights, glides smoothly over the soil, creating an otherworldly contrast against the rustic landscape. Suddenly, the farmer breaks into a joyful jig, dancing alongside his vehicle with a wide grin, celebrating the harvest under the celestial canopy. The sequence captures the unique blend of rural charm and space-age innovation, all set against the enchanting backdrop of a starlit night.]"
},
{
"from": "gpt",
"value": "Bad. The farmer in the video is not driving the tractor."
}
] |
seed44_2178
|
videos/HRA_part1/2178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman with brown, shoulder-length hair unloads a stainless steel dishwasher in a modern kitchen with white cabinets and marble countertops. She wears a simple white T-shirt, blue jeans, and an apron, and her glasses rest on the tip of her nose as she intently organizes the dishes. The room is bright, with sunlight streaming in from a nearby window, illuminating the space and casting a warm glow on the polished floor. As she works, her movements are efficient and practiced, demonstrating her familiarity with the task.]"
},
{
"from": "gpt",
"value": "Normal. The woman's hand generation in the video has issues."
}
] |
seed44_1328
|
videos/HRA_part1/1328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Neptune's ethereal atmosphere, human figures, clad in futuristic, silver, metallic swimsuits and equipped with advanced breathing apparatus, swim gracefully through the gaseous clouds. Their movements are fluid and balletic, almost as if they are performing an underwater dance in the sky. The humans, both male and female, exhibit expressions of wonder and awe as they navigate the alien environment. They perform synchronized swimming routines, moving in perfect harmony with each other and the surrounding gas giant atmosphere. The scene is illuminated by a distant sun, casting a soft, dreamlike glow on the figures as they glide through the thick, swirling clouds of Neptune.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video has uncoordinated movements."
}
] |
seed44_1836
|
videos/HRA_part1/1836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a writer sits at a large wooden desk, adorned with a typewriter, a glass of whiskey, and a half-smoked cigar. Dressed in a brown leather jacket, black shirt, and jeans, he appears rugged and disheveled. Behind him, an open window reveals the gritty urban landscape of a city at night. Suddenly, the scene shifts to a close-up of a rhinoceros, its gray skin wrinkled and textured. The animal is being gently wiped down by a caregiver, who uses a cloth to clean its face, highlighting the creature's large size and docile nature. The juxtaposition of the writer and the rhinoceros creates a surreal and thought-provoking image.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand appears deformed. The towel disappears and reappears."
}
] |
seed46_1558
|
videos/HRA_part2/1558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, athletic female nurse with short brown hair, wearing a navy scrubs top and gray pants, stretches her body against a white wall. She performs various stretches, including touching her toes and raising her arms overhead, highlighting her flexibility and physical fitness. The room is brightly lit, with a large window and a whiteboard in the background, providing a clinical yet dynamic setting for her routine. Throughout the sequence, she maintains a focused expression, showcasing her dedication to maintaining her physical health in a medical environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are very unsmooth and uncoordinated."
}
] |
seed44_2373
|
videos/HRA_part1/2373.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying the role of an artificial intelligence pilot, performs an energetic dance within a high-tech command center. Dressed in a sleek silver metallic jumpsuit with LED lines, he moves to an unseen beat, surrounded by holographic interfaces and screens displaying futuristic data. The room is bathed in cool blue and purple lights, enhancing the sci-fi atmosphere. His expressive face, complete with augmented reality glasses, shows pure joy and freedom as he seamlessly integrates dance into his AI pilot character, creating a captivating fusion of technology and artistry.]"
},
{
"from": "gpt",
"value": "Bad. The actor's dancing in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_1464
|
videos/HRA_part1/1464.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the vast, golden expanse of the temperate grasslands, a lone dingo, its sandy fur blending with the surroundings, stands alert. It shakes off water droplets, its ears pricked forward, before wiping its face with a paw in a natural grooming gesture. The dingo then continues its vigilant stance, scanning the horizon under a clear blue sky, the wind gently swaying the tall grass around it. This intimate moment captures the creature's resilience and adaptability in its native habitat, the rolling plains stretching to the horizon under a wide, cloudless sky.]"
},
{
"from": "gpt",
"value": "Normal. The dingo in the video has uncoordinated movements."
}
] |
seed42_2041
|
videos/HRA_part0/2041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is showcased on a wooden cutting board, its right side facing upward, displaying a clean, unblemished surface. The fish, with a length exceeding two feet, is set against a background of green herbs, lemon wedges, and a chef's knife, evoking a culinary preparation scene. The halibut's left eye is positioned prominently on the top side, indicating the fish's freshness, while its gills are slightly open, revealing the vibrant red color within. The overall setup, with the halibut as the central focus, is meticulously arranged to highlight the quality and size of the fish, perfect for a gourmet seafood dish.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1134
|
videos/HRA_part0/1134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, balding with graying hair, meticulously dusts furniture in a large, elegant room filled with antique wooden furnishings, including a desk, a table, and a shelf. He is dressed in a simple gray shirt and brown trousers, moving methodically around the space. He pauses to look at an item on the desk, perhaps a photo or a book, before continuing his work. The room is bathed in warm, golden light from windows not shown, highlighting the dust motes swirling in the air as he works. He finishes by straightening a framed picture on the wall, ensuring everything is perfectly aligned, demonstrating his pride in his work.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and arms undergo deformation. Hands and arms sometimes mutate and get cut off."
}
] |
seed42_2995
|
videos/HRA_part0/2995.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, with its bushy tail swaying, dances gracefully in a clearing surrounded by lush green foliage. Its movements are fluid and lively, as if performing a choreographed routine under the dappled sunlight filtering through the leaves. The fox leaps and twirls, its fur shimmering with golden highlights, embodying the spirit of the wild in a joyful, uninhibited dance. Against the backdrop of the vibrant forest, the fox's agile form and animated expressions convey a sense of freedom and playfulness in nature.]"
},
{
"from": "gpt",
"value": "Bad. The fox's limbs and head generation in the video have problems, and the body generation is distorted."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.