video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1090
|
videos/HRA_part2/1090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, finch perches on a branch, its vibrant yellow feathers contrasting beautifully against the lush green foliage. The bird's eyes sparkle with curiosity as it tilts its head, listening to the distant sounds of nature. Its beak, perfectly shaped for cracking seeds, opens slightly as it lets out a melodic chirp, filling the air with its song. The sunlight filters through the leaves, casting dappled shadows onto the finch, highlighting the intricate patterns on its wings. In the background, the outline of a wooden cabin can be seen, nestled among the trees, adding a touch of rustic charm to the serene forest scene.]"
},
{
"from": "gpt",
"value": "Bad. The claws appear deformed."
}
] |
seed44_220
|
videos/HRA_part1/220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sun-drenched subtropical shrubland, a striking red fox gently caresses the foliage with its bushy tail as it moves gracefully through the sparse landscape. The fox, with its vibrant fur and alert demeanor, interacts tenderly with the arid environment, highlighting the delicate balance between predator and habitat. Against the backdrop of scrub vegetation and scattered trees, the fox's movements convey a sense of care and connection to the natural world.]"
},
{
"from": "gpt",
"value": "Bad. The red fox in the video has uncoordinated movements."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chef wearing a 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 facial and limb generation of the lynx in the video is problematic, as well as the chef's hands and legs."
}
] |
seed44_2638
|
videos/HRA_part1/2638.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene directed with artistic flair, a bobcat, known for its secretive nature, emerges from the dense undergrowth of a temperate deciduous forest. The sunlight filters through the canopy, casting dappled shadows on the ground as the bobcat approaches a serene, crystal-clear pool. With a sudden burst of energy, it leaps into the water, its powerful muscles propelling it forward as it swims gracefully beneath the surface. Bubbles rise around it, creating an enchanting underwater ballet, before it resurfaces, shaking droplets from its fur, and returns to the safety of the forest edge, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Normal. The mountain cat's swimming in the video is basically normal, but there are slightly uncoordinated movements."
}
] |
seed44_233
|
videos/HRA_part1/233.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": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_3106
|
videos/HRA_part0/3106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded male musician, clad in a brown jacket, blue jeans, and a gray hat, walks through a dense forest filled with tall, lush green trees. He carries a guitar case over his shoulder, suggesting a journey to or from a performance. The woodland environment is rich with ferns and moss, creating a vibrant, natural setting. Sunlight filters through the canopy, casting dappled light on the forest floor as the musician strides purposefully along the path, his attire and equipment blending harmoniously with the woodlands.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3198
|
videos/HRA_part1/3198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 firefighter, clad in a specialized Neptune atmospheric suit, complete with a helmet and breathing apparatus, runs across a rugged, alien landscape bathed in eerie, ethereal light. The environment is dominated by hues of blue and green, evoking the mysterious atmosphere of Neptune. Wisps of cloud-like formations swirl in the distance, adding to the otherworldly ambiance. The firefighter's suit, equipped with advanced technology to withstand the harsh conditions, glimmers under the faint illumination, highlighting the bravery and determination required to perform such a daunting task in an extraterrestrial setting.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's hands and feet are deformed in the video."
}
] |
seed42_2947
|
videos/HRA_part0/2947.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a gray sweatshirt with the sleeves rolled up, dark pants, and black gloves, stands on a ladder propped against a white house, cleaning the rain gutters. The scene is set in the backyard, with lush green grass and shrubs in the foreground. The artist's tools, including a trowel and a bucket, are visible as they scoop out debris from the gutters. The ladder leans against the house, providing support as the artist works diligently, the greenery and peaceful suburban setting creating a serene backdrop for this everyday task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2408
|
videos/HRA_part2/2408.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, seasoned farmer, clad in a futuristic spacesuit with a clear helmet, stands on Mars Base Camp, a sprawling, high-tech habitat amidst the planet's iconic red landscape. The domed settlement, bustling with advanced technology and greenery, contrasts starkly with the desolate Martian terrain. Inside a transparent dome, the farmer enjoys a leisurely swim in a serene pool, surrounded by lush vegetation and state-of-the-art hydroponic farming systems, showcasing the remarkable fusion of agriculture, leisure, and space exploration on the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. Missing the scene of the farmer swimming in the pool."
}
] |
seed46_225
|
videos/HRA_part2/225.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, dressed in a crisp white lab coat, stands in an oil refinery, its towering structures and pipelines creating an industrial skyline. He gently caresses a small, clay hippopotamus sculpture, its smooth surface contrasting with the rough, metallic environment. The scene is lit by the warm glow of industrial lights, casting long shadows across the doctor and the miniature hippo, encapsulating an unexpected moment of tenderness amidst a typically harsh landscape.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1534
|
videos/HRA_part2/1534.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, surveys its surroundings with keen eyesight. Suddenly, it springs into action, jumping high into the air from the sandy ground of its desert habitat. The meerkat's body is arched gracefully mid-leap, showcasing its agility and strength. Its fur, a blend of tans and browns, contrasts beautifully against the clear blue sky, capturing the essence of life in the wild. As it lands, the meerkat's alert ears and expressive face reveal its readiness for any challenge in its environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1659
|
videos/HRA_part1/1659.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and 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": "Good. No obvious problems."
}
] |
seed46_1206
|
videos/HRA_part2/1206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars gracefully through the crisp, blue sky, its powerful wings spread wide, casting a shadow on the rugged mountain terrain below. The eagle's piercing golden eyes scan the landscape intently, searching for prey. Its striking white head and tail feathers contrast vividly against the dark brown body, creating an awe-inspiring sight against the panoramic backdrop of snow-capped peaks and lush valleys. As it glides effortlessly, the wind ruffles its feathers, highlighting the intricate patterns and textures of its plumage, while the sun illuminates the scene, casting a warm glow on the breathtaking view.]"
},
{
"from": "gpt",
"value": "Normal. The eagle's wings and claws in the video have issues."
}
] |
seed46_1606
|
videos/HRA_part2/1606.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 abnormal limb generation, and during the middle frame of the dance, the character appears with three hands."
}
] |
seed46_1371
|
videos/HRA_part2/1371.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic display, a snake charmer clad in a richly colored red robe and matching turban leans forward, engaging intently with a king cobra emerging from a traditional wicker basket. The snake, adorned with intricate patterns, rises dramatically from the basket, its hood spread wide. The charmer's hands, decorated with silver bracelets, gently caress the serpent's body, emphasizing the bond between human and animal. The scene is set against a vibrant, patterned cloth, adding to the exotic atmosphere, with the charmer's face expressing both respect and control as he interacts with the majestic creature.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted, and the cobra's body is twisted."
}
] |
seed42_2215
|
videos/HRA_part0/2215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a dark suit, sits in an office with wooden shelves and books in the background, gently caressing a porcupine. The lawyer, with neatly combed gray hair and glasses, looks directly at the camera, holding the porcupine with care. In another shot, the lawyer, still in his professional attire, cradles the porcupine in his hands, showing a softer side amidst the serious atmosphere of the law office, filled with books and legal documents. Throughout, the unlikely pairing of the suited lawyer and the spiky porcupine conveys a message of tenderness and unexpected connections.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are distorted, face is distorted, and the hedgehog's face is distorted."
}
] |
seed44_3038
|
videos/HRA_part1/3038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with complex machinery and computer screens displaying intricate data, a lone scientist in a white lab coat meticulously examines a vial containing a mysterious, shimmering liquid, believed to be a sample of dark matter. Meanwhile, in a contrasting scene, a majestic gray wolf, its fur glistening under the moonlight, leaps gracefully from a rock into a serene, moonlit lake, creating ripples that spread across the water's surface. The juxtaposition of these two scenes highlights the intriguing connection between the enigmatic world of dark matter research and the primal, untamed beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the scientist's hand examining the sample, the movements are basically normal but there is some lack of coordination; the video shows the gray wolf's head and the ripples in the lake, the action of the gray wolf jumping into the lake is not very smooth."
}
] |
seed44_2998
|
videos/HRA_part1/2998.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious indoor playroom illuminated by large windows, two young children engage in a playful tug-of-war over a vibrant red toy firetruck. The room is filled with various toys scattered across the wooden floor, adding to the sense of fun and activity. The children, both wearing colorful clothing - one in a blue striped shirt and the other in a pink floral dress - display expressions of determination and joy as they pull on opposite ends of the firetruck, their feet firmly planted on the floor. The background features a wall painted with cheerful, cartoonish animal murals, enhancing the whimsical atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1423
|
videos/HRA_part1/1423.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a gray sweater and glasses, sits at a rustic wooden desk in a cozy room filled with books, typing away on a vintage typewriter. Beside her, a curious ferret emerges from a cage, its bright eyes scanning the environment. The animal then embarks on a playful walk across the desk, exploring various objects like a small potted plant and a glass jar. Throughout the scene, the writer continues to type, occasionally glancing at the ferret with a smile, capturing the essence of a peaceful day in her life, surrounded by literary works and a charming pet.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2299
|
videos/HRA_part0/2299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great egret, standing tall with folded wings, perches gracefully on one leg atop a weathered wooden post in the midst of a serene marsh landscape, surrounded by lush green vegetation and calm waters. Its pristine white feathers contrast beautifully against the natural backdrop, while its sharp yellow eyes scan the environment keenly. The scene is set during the golden hour, with the warm sunlight casting a soft glow over the bird and its habitat, highlighting the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1245
|
videos/HRA_part0/1245.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, adorned in a red apron over a casual black t-shirt and dark jeans, skillfully chops fresh vegetables on a wooden cutting board in a vibrant kitchen filled with natural light. The room is alive with warm colors and modern decor, featuring a large window that lets in the afternoon sun. The musician, with short brown hair and a friendly smile, gracefully moves about the space, stirring a sizzling pan on a high-end stove, the aroma of a delicious meal blending with the upbeat tunes playing softly in the background. Moments later, they taste-test the simmering sauce, adjusting the seasoning with a practiced hand, all while the inviting glow of the kitchen enhances the cozy atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. Missing a cutting board."
}
] |
seed44_1578
|
videos/HRA_part1/1578.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 creative writer, adorned in a cozy gray sweater and glasses, stands in a modern kitchen with sleek appliances, ready to craft stories. They pour water into a high-tech coffee machine, its illuminated screen displaying the brewing process, setting the scene for a productive day of writing. The individual then adds coffee grounds to the machine, preparing a perfect cup of coffee to fuel their creative endeavors. Dressed in a comfortable outfit and with a laptop nearby, they embody the ideal image of a writer ready to tackle the day, all while the aroma of freshly brewed coffee fills the air.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2439
|
videos/HRA_part2/2439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, balding with graying hair, wearing a dark green jumpsuit, is assembling a wooden table in a brightly lit, empty room with beige walls. He carefully reads the instruction manual, focusing intently on the task at hand. Moments later, he is seen tightening screws with a screwdriver, his brow furrowed in concentration. Then, he stands back to admire his handiwork, the completed table standing sturdy and polished. Finally, he wipes his forehead with a cloth, revealing a look of satisfaction and a hint of exhaustion, the newly assembled table now adorned with a vase of flowers, adding a touch of life to the barren room.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth."
}
] |
seed44_2304
|
videos/HRA_part1/2304.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, identifiable by his white uniform and toque, finds himself in an unexpected scenario, sharing a swimming pool with a large, brown bear. The pool, surrounded by lush greenery, offers a surreal setting as the chef, showing no fear, calmly floats on an inflatable raft, while the bear swims nearby, seemingly enjoying the water. Both characters coexist peacefully in this unusual scene, the chef maintaining his composure and the bear displaying a gentle demeanor, all under the clear blue sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_309
|
videos/HRA_part1/309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kneels on a hardwood floor, wearing a grey turtleneck sweater, dark jeans, and brown boots, painting a vivid abstract artwork on a large canvas. A friendly dog, possibly a Golden Retriever, crawls playfully toward the artist, who gently pets it with a loving smile, both surrounded by the warm glow of a studio space filled with art supplies and natural light. The scene captures a tender moment between the artist and their canine companion, with the unfinished artwork providing a glimpse into the creative process.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1758
|
videos/HRA_part0/1758.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged teacher waves energetically with both hands from a classroom filled with colorful decorations, wearing a bright yellow sweater over a patterned dress, against a backdrop of windows showing a clear blue sky, conveying a sense of warmth and welcome. She stands in front of a whiteboard adorned with educational posters and student artwork, her smile and enthusiastic gesture creating an inviting atmosphere for students. The room is bathed in natural light, highlighting the teacher's animated expression and the vibrant learning environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3116
|
videos/HRA_part0/3116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a black cap, black jacket, and khaki pants, pushes a large, vintage amp through a crowded, dimly lit backstage area at a music venue. The scene is filled with the energy of an upcoming performance, as the musician maneuvers the amp with determination, highlighting the physical effort and dedication required behind the scenes. The musician's attire and the bustling environment capture the spirit of live music culture.]"
},
{
"from": "gpt",
"value": "Normal. The musician's face in the video is distorted, and the hands and feet are deformed."
}
] |
seed42_1079
|
videos/HRA_part0/1079.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird's eyes are sharp and alert, observing its surroundings with an almost human-like curiosity. The bark of the tree it rests on is textured and dark, contrasting against the lighter shades of green leaves that surround it. In the background, the forest is alive with the sounds of nature; other birds calling, leaves rustling in the breeze, and the distant murmur of a stream. The crow, a symbol of intelligence and adaptability, stands proud and solitary, a master of its domain.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2325
|
videos/HRA_part2/2325.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a button-down shirt and khaki pants, rearranges the furniture in a modern living room. He first adjusts a wooden table, pushing it closer to a brown leather sofa. Next, he moves a gray armchair, placing it at an angle near the sofa, creating a cozy seating arrangement. The doctor then fine-tunes the position of a glass coffee table, centering it between the sofa and armchair. Lastly, he adds a touch of greenery by positioning a potted plant next to the armchair, completing the refreshed layout of the room.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_1696
|
videos/HRA_part2/1696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a middle-aged doctor, wearing a stethoscope around his neck and a crisp white lab coat over his neatly pressed blue scrubs, finds himself unexpectedly dancing in a vast savanna. As he moves with surprising grace, a curious cheetah, intrigued by the unusual sight, approaches cautiously from the tall grass. The big cat, known for its speed and agility, mirrors the doctor's dance steps, its movements fluid and powerful. The unlikely pair continues their impromptu dance, surrounded by the vast, open landscape, creating a surreal and captivating moment captured in high-definition footage.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1445
|
videos/HRA_part1/1445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 magnificent cheetah, adorned with vibrant orange beads and feathers woven into its fur, dances gracefully in the dappled sunlight of a lush savanna. Its body moves fluidly to an unheard beat, each leap and twist a display of raw power and elegance. Surrounded by tall grass swaying gently in the breeze, the cheetah's every motion is captured in high definition, from the flex of its muscles to the gleam in its eyes, embodying the spirit of the wild in a captivating dance.]"
},
{
"from": "gpt",
"value": "Normal. The cheetah's movements are not smooth."
}
] |
seed42_2866
|
videos/HRA_part0/2866.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with badge and name tag, black tactical vest, and duty belt adorned with various gear, is seen dancing joyously on a wooden deck. In his right hand, he holds a small hedgehog, which is safe and secure in a clear plastic container with air holes. The hedgehog, with its distinctively spiky quills and curious demeanor, peers out from within the container. Behind the officer, a lush garden with green hedges and vibrant flowers provides a lively backdrop, enhancing the whimsical atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The police's movements in the video are not smooth."
}
] |
seed44_244
|
videos/HRA_part1/244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 fearless firefighter, clad in full gear and holding a fire axe, leaps over a low obstacle in a training course, with a large, taxidermied leopard positioned on the ground nearby, creating an unusual juxtaposition of elements. The firefighter's helmet gleams under the bright lights, and the scene is set against a backdrop of firefighting equipment and vehicles, emphasizing the intensity and unpredictability of their training exercises.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1578
|
videos/HRA_part2/1578.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 creative writer, adorned in a cozy gray sweater and glasses, stands in a modern kitchen with sleek appliances, ready to craft stories. They pour water into a high-tech coffee machine, its illuminated screen displaying the brewing process, setting the scene for a productive day of writing. The individual then adds coffee grounds to the machine, preparing a perfect cup of coffee to fuel their creative endeavors. Dressed in a comfortable outfit and with a laptop nearby, they embody the ideal image of a writer ready to tackle the day, all while the aroma of freshly brewed coffee fills the air.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, and the hand is distorted."
}
] |
seed46_1778
|
videos/HRA_part2/1778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, casually dressed in a dark gray t-shirt and black sweatpants, attentively unloads a dishwasher in a modern kitchen. The space features sleek white cabinets, a stainless steel refrigerator, and a large window allowing natural light to illuminate the room. He carefully places dishes into cupboards, revealing a methodical approach to the task. With a half-smile and relaxed posture, he demonstrates an unexpected domestic side, contrasting his typical on-screen persona. Throughout the scene, the kitchen remains orderly and clean, emphasizing the mundanity of the chore juxtaposed with his celebrity status.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes, and the body is uncoordinated."
}
] |
seed46_2123
|
videos/HRA_part2/2123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid orange kite with intricate black patterns soars majestically against a clear blue sky, its long white tail streaming gracefully behind it. The kite, resembling a dynamic bird in flight, is seen from various angles, showcasing its detailed design and the fluidity of its movements. Against the serene backdrop of fluffy white clouds and the vast horizon, the kite seems to dance with the wind, captivating viewers with its aerial ballet. The interplay of sunlight and shadow enhances the kite's vibrant colors, making it a striking focal point against the peaceful sky.]"
},
{
"from": "gpt",
"value": "Good. The kite flying in the video has no obvious issues."
}
] |
seed46_1287
|
videos/HRA_part2/1287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful swift bird, known for its agility, soars against a cloudy sky, its dark silhouette outlined by the bright horizon. It swoops and glides effortlessly, its wings and tail spread wide, navigating the air currents with precision. The bird's streamlined body, adapted for speed, cuts through the sky as it performs acrobatic maneuvers, demonstrating its remarkable flying skills. Against the vast, cloud-filled backdrop, the swift's aerial ballet continues, highlighting its unparalleled aerial prowess and freedom.]"
},
{
"from": "gpt",
"value": "Normal. The swift's flight in the video is basically normal, with only slightly uncoordinated movements."
}
] |
seed42_1746
|
videos/HRA_part0/1746.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A prehistoric mammoth, covered in shaggy brown fur, is seen swimming in a vast, ancient lake, its large body creating ripples on the water's surface. The mammoth, with distinctive tusks and small ears, moves through the water with surprising grace, its trunk held high above the waterline like a snorkel. The scene is set against a backdrop of lush, green vegetation and towering, majestic mountains in the distance, capturing the essence of a bygone era when these magnificent creatures roamed the earth.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2317
|
videos/HRA_part2/2317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting reminiscent of a starship bridge, a young woman with a short bob haircut and bangs, wearing a red uniform, runs with a focused look on her face. She passes by various crew members, who are seated at their stations, as indicated by their presence in the background. The woman's attire matches the aesthetic of the spaceship, which features advanced technology and a sleek design. The action takes place within the command center of the vessel, where the crew operates controls and monitors various screens, highlighting the urgency and importance of the situation at hand.]"
},
{
"from": "gpt",
"value": "Normal. The woman's hand and arm show deformities, and her face is distorted."
}
] |
seed46_1722
|
videos/HRA_part2/1722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman, the spacewalking teacher, wearing a bulky white spacesuit with NASA logos and a clear helmet, floats against the dark cosmos filled with stars, the Earth visible in the distance. She is engaged in repairing a satellite, her gloved hands holding a tool while she wipes away debris. Her spacesuit bears her name, \"M. Taylor,\" and she exhibits determination and expertise as she works on the damaged satellite, emphasizing the critical nature of her task in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The series of actions of the character in the video is not recognized."
}
] |
seed44_2561
|
videos/HRA_part1/2561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, clad in a dark green jacket, blue jeans, and a beige hat, walks through a dry, rocky landscape, his attention fixed on a hyena in the distance. The hyena, displaying its characteristic spotted coat and large ears, roams freely in the arid environment. The director, holding a megaphone and script, seems to be guiding the action or observing the hyena's natural behavior, capturing the essence of the wild animal in a cinematic exploration. The scene conveys a sense of adventure and creativity as the director integrates the captivating presence of the hyena into his storytelling.]"
},
{
"from": "gpt",
"value": "Bad. The hyena's wandering movements in the video are not very continuous, there is a lack of coordination; however, the director's observation of the hyena's movements is basically normal."
}
] |
seed42_2926
|
videos/HRA_part0/2926.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": "Normal. The lawyer's movements in the video are not smooth."
}
] |
seed46_1274
|
videos/HRA_part2/1274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged fisherman, clad in a yellow raincoat and matching hat, stands waist-deep in the water, his gaze fixed on the horizon. His hands, weathered from years of labor, expertly handle the fishing net as he casts it into the vast, shimmering sea. The early morning sun bathes the scene in a golden glow, casting long shadows and highlighting the droplets of water clinging to the net. Seagulls circle overhead, their calls adding to the serene atmosphere of the coastal landscape. In the distance, the silhouette of a small fishing village can be seen, smoke rising from the chimneys of the quaint houses, a reminder of the community that thrives on the fruits of the sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2633
|
videos/HRA_part0/2633.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 hummingbird, vibrant green and purple, hovers in a sunny garden, its wings a blur as it feeds from a red salvia flower. The bird moves to another scarlet blossom, its long beak piercing the flower to drink nectar, all set against a lush, green foliage backdrop. It then perches on a branch, preening its feathers with a bright pink beak, before resuming flight, hovering near a spray of orange and yellow flowers. Finally, the hummingbird returns to the red blooms, feeding once more with the sun illuminating its iridescent plumage, showcasing its agility and grace against a garden filled with various colorful flowers.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's eye position in the video is incorrect, and the flying is overall distorted."
}
] |
seed44_1060
|
videos/HRA_part1/1060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patient, smiling teacher, dressed casually in a blue T-shirt and khaki shorts, tenderly bathes a small, brown dog in a white plastic tub placed atop a green picnic table, set against the backdrop of a lush, grassy park. The teacher, wearing a simple blue shirt and beige shorts, gently washes the dog, who looks content and relaxed. In another angle, the teacher, now seen from the back, continues to bathe the dog, demonstrating care and attention. Lastly, the teacher, still wearing the blue top and khaki bottoms, rinses the dog with a handheld showerhead, capturing the essence of a nurturing educator spending quality time with a beloved pet.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the teacher's smiling face or the showerhead."
}
] |
seed44_1515
|
videos/HRA_part1/1515.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a red t-shirt and black cap, meticulously cleans his silver car with a sponge in a residential driveway, set against a sunny day. His attire includes a red t-shirt with a white logo, black pants, and white sneakers, while his accessories consist of a black baseball cap and a wristwatch. As he works, his right leg occasionally bounces to an invisible beat, revealing his musical nature. Throughout the scene, he uses various cleaning tools, such as a bucket of soapy water, a hose, and a microfiber towel, all while maintaining a joyful demeanor.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video is not wearing a watch."
}
] |
seed46_1328
|
videos/HRA_part2/1328.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 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 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": "Bad. The limbs and facial features of the humans in the video are not fully generated."
}
] |
seed42_1295
|
videos/HRA_part0/1295.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, clad in a blue plaid shirt and black pants, sits cross-legged on a wooden floor, surrounded by a variety of eager pets. The room is dimly lit, with a single lamp providing a warm glow. The musician, with a friendly smile, gently strums an acoustic guitar, creating a soothing melody that fills the cozy space. Pets of different sizes and species gather around, their attentive faces showing enjoyment of the music and anticipation of being fed. A fluffy cat perches on the musician's lap, while a small dog sits patiently by a bowl of food, and a parrot watches from its cage. The scene conveys a sense of harmony and love between the musician and the pets, all sharing a special moment together.]"
},
{
"from": "gpt",
"value": "Normal. The musician's face and hands, as well as the pets' faces and bodies, are generated abnormally in the video."
}
] |
seed46_1881
|
videos/HRA_part2/1881.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a dark gray shirt and light gray pants, crawls through a subtropical desert landscape, surrounded by a variety of cacti and succulent plants. The terrain features sandy soil and scattered rocks, with distant hills adding depth to the scene. The actor's body language conveys determination as he moves forward, his facial expression reflecting the intensity of the environment. The lush vegetation, including a large cactus, provides contrast to the arid setting, while the warm sunlight highlights the texture of the sand and the resilience of the desert flora.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, and twisted arms."
}
] |
seed42_3007
|
videos/HRA_part0/3007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male spruce grouse, perched on a branch in a dense forest, displays its vibrant plumage featuring shades of brown, gray, and white speckles. Its red eyelids stand out against the dark eye, while its yellow bill adds a striking contrast. The bird's feathers are ruffled, perhaps due to a breeze or during a display, and it is surrounded by lush green foliage, indicating a healthy habitat. The grouse is stationary, offering a clear view of its unique features against the backdrop of a richly textured forest environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1647
|
videos/HRA_part0/1647.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, open ocean landscape fills the screen, with crystal clear water revealing a sandy bottom far below. Sunlight filters through the surface, casting dappled light on the scene. Suddenly, a magnificent manta ray enters the frame, its massive wings spanning wide as it glides effortlessly through the water. The creature is a stunning sight, its dark top and white underbelly contrasting beautifully against the blue surroundings. It performs an elegant somersault, showcasing its agility and grace, before continuing on its serene journey across the vast underwater expanse.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1382
|
videos/HRA_part0/1382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical space-themed casino, a large brown bear, standing on two feet, walks with a casual gait, wearing a red shirt, blue jeans, and a gold watch. The bear is surrounded by various elements of the space casino, including a bar with neon lights, slot machines, and a large window displaying a view of the galaxy. As it strides through the casino, the bear passes by a table where alien creatures play cards, their eyes following the unexpected visitor. The atmosphere is filled with a sense of wonder and fun, as the bear continues its stroll, blending seamlessly into the otherworldly environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1487
|
videos/HRA_part0/1487.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 realistic zebra, complete with black and white stripes, finds itself crawling under a barrier typically found at train stations. The striped animal moves slowly and carefully, its body almost touching the ground, as it navigates beneath the yellow and black-striped barrier. The train station's typical features, such as tracks, platforms, and overhead signs, are visible in the background, adding to the surreal nature of the scene. The zebra's unusual behavior in this urban setting creates a striking and memorable image.]"
},
{
"from": "gpt",
"value": "Bad. The zebra's head is twisted, and its legs are distorted."
}
] |
seed42_1883
|
videos/HRA_part0/1883.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a dark jacket and distressed jeans, stealthily walks through the dimly lit corridors of a futuristic space prison. His intense gaze is directed ahead, revealing his determination. The harsh, cold lighting accentuates the high-tech, metallic surfaces of the prison environment. As he moves, the camera captures the tension in his body language, hinting at the imminent danger. Despite the oppressive surroundings, the musician's confident stride and unwavering focus suggest a plan in motion, ready to execute his daring escape.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed42_2008
|
videos/HRA_part0/2008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a traditional snake charmer clad in a red turban and green vest kneels on a vibrant, patterned carpet, playing a wooden flute to entice a hooded cobra from a woven basket. The snake emerges, swaying hypnotically to the melody, its scales glistening under the golden glow of hanging lanterns. The charmer, with intense focus, maintains eye contact with the cobra, which dances in a mesmerizing rhythm, creating an age-old spectacle against a backdrop of bustling market life, complete with onlookers and the ambient sounds of a lively bazaar.]"
},
{
"from": "gpt",
"value": "Normal. The cobra's dancing in the video is not smooth, and its movements are not coordinated."
}
] |
seed46_1600
|
videos/HRA_part2/1600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 white hare runs through the city at night, its fur glowing under the streetlights, navigating urban obstacles like a seasoned athlete. It bounds across a busy intersection, dodging between yellow cabs and pedestrians, its powerful legs propelling it forward with graceful ease. The hare then leaps over a low brick wall, lands on the cobblestone sidewalk, and continues its journey, its silhouette framed by the neon signs of city storefronts. Finally, it pauses beneath a towering skyscraper, its large ears perked up, listening to the sounds of the city before continuing its mysterious nocturnal run.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's body is twisted, the paws are twisted, the face is twisted, and the legs are twisted."
}
] |
seed44_2560
|
videos/HRA_part1/2560.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor wearing a yellow high-visibility vest, khaki cargo shorts, and a green t-shirt is crawling on a sandy beach, possibly searching for lost items or performing an unusual cleaning task. The beach is wide and sandy, with shallow water and a calm sea stretching into the distance. Palm trees dot the landscape, and the beach is relatively empty except for a few people walking in the background. The janitor's actions are focused and deliberate, contrasting with the serene coastal scenery.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1774
|
videos/HRA_part0/1774.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene set within the lush environment of a tropical dry forest, a young, smiling female cashier, wearing a red apron over a white blouse and black pants, energetically jumps over a small log. She lands gracefully, holding a miniature baseball bat, as if ready for an unexpected game amidst the dense vegetation. The vibrant green foliage and dappled sunlight create a vivid contrast against her outfit, capturing the spirit of adventure and playfulness in an unconventional setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1286
|
videos/HRA_part2/1286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist in a gray jacket, black shirt, and brown pants stands before a large, unfinished painting of a space elevator, his right hand gently caressing the canvas as if feeling the texture of the depicted structure. His left hand rests on his hip, and he looks down at the artwork with a slight smile, conveying a sense of pride and connection to his creation. The studio is dimly lit, casting dramatic shadows across the room and highlighting the artist's interaction with the painting, which features the towering space elevator reaching towards the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3093
|
videos/HRA_part2/3093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, modern space education center, a diligent janitorial worker, clad in a gray uniform, meticulously wipes down an expansive, glass-topped display table. The room is filled with futuristic exhibits, including a large model of the solar system hanging from the ceiling, and interactive screens showing detailed information about planets and galaxies. The worker's attention to detail is evident as they ensure every inch of the table is spotless, allowing visitors to fully appreciate the educational materials displayed beneath the clear surface. The backdrop of the space-themed decor highlights the importance of cleanliness in maintaining a conducive learning environment for students eager to explore the cosmos.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3180
|
videos/HRA_part1/3180.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 orange tabby cat leaps across the gap between two weathered warehouse rooftops under an overcast sky, its hind legs pushing off a wooden crate. The cat lands gracefully on the adjacent rooftop, its green eyes alert, before bounding away toward a rusty metal water tower in the distance. The scene is set against a backdrop of urban decay, with broken windows and graffiti adorning the brick walls of the warehouses. As the cat jumps, it passes by a row of similar crates, adding to the industrial atmosphere of the setting.]"
},
{
"from": "gpt",
"value": "Bad. The tabby cat's body is twisted, its paws are twisted, and its legs are twisted."
}
] |
seed46_1112
|
videos/HRA_part2/1112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, protected national park during autumn, a majestic bull bison with a thick, shaggy brown coat leads a herd across a sunlit meadow, the golden grass swaying gently in the breeze. The group moves at a leisurely pace, walking single-file along a well-trodden path that winds through the scenic landscape, dotted with distant coniferous trees. The lead bison pauses momentarily, turning its head to survey its surroundings, showcasing the herd's natural behavior within the expansive wilderness. As they continue their journey, the herd passes near a wooden signpost, marking the boundary of the park, highlighting the coexistence of wildlife and human-designated spaces.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the bison passing by a wooden signpost as mentioned in the caption."
}
] |
seed42_1264
|
videos/HRA_part0/1264.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful college student, wearing a maroon shirt, navy vest, beige khaki pants, and brown hiking boots, pauses on a trail to gaze at a breathtaking mountain vista, his backpack leaning against a tree. Moments later, he sits on a rock, attentively examining something in his hands, perhaps a map or a natural specimen, with the stunning landscape as his backdrop. Then, he hikes uphill, trekking poles in hand, his outfit unchanged, as the lush greenery and distant mountains frame his journey. Finally, he stands at a scenic overlook, savoring the panoramic view, his maroon shirt, navy vest, beige pants, and brown boots standing out against the natural beauty.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and feet are deformed, the sitting posture is suspended in mid-air, the map in hand suddenly disappears, and the hiking pole also deforms and elongates."
}
] |
seed44_2041
|
videos/HRA_part1/2041.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 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, 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."
}
] |
seed44_2771
|
videos/HRA_part1/2771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 visionary director, dressed in a classic pinstripe suit, stands in a vast, dimly lit studio, skillfully orchestrating a surreal scene. Nearby, a Robot astronaut, adorned in a sleek silver spacesuit with gleaming gold accents, follows the director's guidance as it begins to dance. The robot's movements are fluid and precise, a captivating fusion of technology and artistry, set against the backdrop of cinematic equipment and the director's watchful gaze, creating a mesmerizing spectacle where reality meets imagination.]"
},
{
"from": "gpt",
"value": "Normal. The robot's hand is distorted, and the arm is twisted."
}
] |
seed46_1220
|
videos/HRA_part2/1220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, donning a black baseball cap, black shirt, khaki pants, and black shoes, is shown repairing a vintage bicycle against a backdrop of lush greenery and sunlight filtering through the trees. He is engaged in fixing the bike's chain, showcasing his mechanical skills. In another shot, he carefully inspects the bicycle's frame, his face expressing concentration and expertise. He then tightens a bolt on the bike's wheel, demonstrating his proficiency in bike maintenance. Lastly, he adjusts the bicycle's seat, ensuring it is perfectly aligned, all while surrounded by the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1982
|
videos/HRA_part0/1982.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a blue scrub top and pants is kneeling on lush green grass in a backyard, engaging playfully with an energetic brown dog. The dog leaps into the air, attempting to catch a red ball thrown by the nurse, who looks on with delight. Both the nurse and the dog are surrounded by a vibrant garden, with colorful flowers blooming in the background, creating a joyful and lively scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1129
|
videos/HRA_part0/1129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 village setting, a waiter dressed in a crisp white shirt and black pants is seen sprinting energetically between charming houses with red-tiled roofs. The houses are adorned with lush green vines and windows framed by vibrant flowers. The waiter carries a silver tray aloft, maintaining perfect balance as he navigates the cobblestone streets. Each house has its own unique character, from wooden shutters to ornate door knockers, providing a picturesque backdrop for the waiter's urgent dash. The scene is imbued with a sense of community and lively activity, as the waiter's route weaves through the heart of the village, connecting the homes with his swift, professional service.]"
},
{
"from": "gpt",
"value": "Bad. The person's legs and feet became deformed, and eventually the head also became deformed."
}
] |
seed42_2549
|
videos/HRA_part0/2549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a beige jacket and dark trousers, sits on a wooden dock by the water's edge. He gently caresses a small, curious otter that has climbed onto his lap, looking into its eyes with a warm smile. The otter, with its sleek brown fur and bright, inquisitive gaze, seems comfortable and at ease in the actor's presence. The scene is set against a serene backdrop of gently lapping waves and lush greenery, capturing a tender moment between human and animal in a peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, the hand is twisted, and the otter's face is distorted."
}
] |
seed42_2869
|
videos/HRA_part0/2869.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional nurse, clad in a light blue scrubs top and dark blue scrubs pants, sits attentively at a desk in a modern hospital setting, her hands deftly typing on a laptop keyboard. Behind her, the bustling hospital environment is visible, adding context to her role. She wears her hair in a neat bun, and her focused gaze is directed at the screen, indicating her concentration on the task at hand. Despite the busy surroundings, she maintains a calm demeanor, highlighting her dedication to her work in the healthcare field.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2506
|
videos/HRA_part1/2506.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an imaginative scene, a lone camel, adorned with vibrant red and yellow fabrics, stands gracefully at the edge of a bustling highway under a vivid orange sunset. Vehicles whiz by in the background, forming streaks of light against the twilight sky. The camel begins to sway and dance, moving its body to an unheard rhythm, creating a surreal contrast between the wild and the urban landscape. Its movements are fluid and expressive, drawing attention despite the chaos of the surrounding traffic. The highway lights and car headlights illuminate the scene, casting dramatic shadows as the camel continues its dance, a captivating spectacle where nature meets the modern world.]"
},
{
"from": "gpt",
"value": "Bad. The camel's head and limbs in the video have generation issues, with the legs twisting and deforming in the middle frames."
}
] |
seed42_1205
|
videos/HRA_part0/1205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative director, wearing a stylish black jacket and jeans, stands on a futuristic space stadium podium, passionately explaining the grand vision for an intergalactic sporting event. Below, a peculiar sight unfolds: a capybara, donning a sleek silver spacesuit and a determined look, prepares for the ultimate cosmic challenge. The rodent athlete crouches, ready to spring into action, against the backdrop of a vibrant, neon-lit cosmic arena, filled with alien spectators. The capybara leaps high into the air, propelling itself with incredible force, while the director watches intently from above, his eyes fixed on this extraordinary spectacle unfolding under the dazzling lights of the space stadium.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not coordinated, and the capybara's actions are not smooth."
}
] |
seed46_2719
|
videos/HRA_part2/2719.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station adorned with lavish decorations for an extravagant wedding, a neatly-dressed cashier, wearing a classic black vest and bow tie, diligently wipes the immaculate glass counter with a small cloth. The backdrop features elegant table settings, floral arrangements, and a large, illuminated dance floor, all indicative of an upscale celebration. The cashier's meticulous attention to detail ensures the space station's cash register area remains spotless amidst the grand festivities.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2934
|
videos/HRA_part0/2934.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a dark suit and carrying a leather briefcase, walks with purpose across a dimly lit, gritty urban environment. Simultaneously, a CGI weasel, also dressed in a miniature lawyer's outfit complete with a bow tie and a tiny briefcase, scurries alongside the human lawyer. Both characters navigate through the cityscape, which features brick walls, fire escapes, and a sense of the urban jungle. The juxtaposition of the human lawyer and the anthropomorphized weasel lawyer adds a layer of whimsy and metaphor to the scene, suggesting themes of cunning and legal maneuvering.]"
},
{
"from": "gpt",
"value": "Normal. The weasel is missing a briefcase."
}
] |
seed44_2253
|
videos/HRA_part1/2253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and vivid scene, a beautifully rendered CGI cheetah, marked by its distinctive black spots, sits calmly on a restaurant's hardwood floor, bathed in warm lighting. Surprised diners watch from their tables, which are set with white tablecloths and elegant place settings, as a brave individual reaches down to caress the wild cat's head. The cheetah, relaxed and unperturbed by the surroundings, accepts the gentle touch, creating an extraordinary juxtaposition of nature and civilization.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_3061
|
videos/HRA_part1/3061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, complete with a tailored suit and carrying a leather briefcase, finds himself in an unexpected scenario amidst a lush, verdant forest. He encounters a kangaroo, which has somehow become covered in a fine layer of dust. The lawyer, displaying a surprising level of empathy and care, gently wipes the dust off the kangaroo's fur using a pristine white handkerchief, revealing the clean, soft fur beneath. The kangaroo looks on with curiosity, standing on its hind legs, as the lawyer meticulously cleans it, all under the dappled sunlight filtering through the dense canopy above.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1168
|
videos/HRA_part0/1168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant park, a majestic leopard, its golden eyes alert, crouches near the edge of a pristine swimming pool, surrounded by vibrant greenery and towering palm trees. The big cat, with its distinctive rosette patterns on a tawny coat, gazes intently at the clear water, contemplating a playful leap. Moments later, it leaps gracefully into the pool, its powerful body slicing through the water in a fluid motion. Emerging from the pool, the leopard shakes off droplets, revealing its muscular physique, as it strides confidently across the park, leaving behind a trail of shimmering water on the sun-drenched pavement.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2052
|
videos/HRA_part0/2052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 whimsical scene opens with a koala, wearing swimming goggles and a yellow floatie, perched on the edge of a turquoise pool. It peers into the water with curiosity, its plush toy-like appearance adding charm. In the next shot, the koala, still in its floatie and goggles, is seen paddling in the shallow end of the pool, surrounded by clear, sparkling water. The camera then captures the koala as it floats on its back, appearing relaxed and content, with the floatie supporting it and the goggles keeping its eyes dry. Finally, the koala is shown sitting upright in the pool, holding onto the side with one paw, its other arm stretched out as if waving, all while maintaining its adorable and playful demeanor.]"
},
{
"from": "gpt",
"value": "Normal. In the video, Koala's face and claws are distorted."
}
] |
seed42_2904
|
videos/HRA_part0/2904.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 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 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": "Bad. The moose's head and limbs are deformed in the video, with three front legs appearing in some middle frames, and the limbs suddenly disappearing or reappearing."
}
] |
seed46_1850
|
videos/HRA_part2/1850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a green apron over a casual outfit, stands in a pet store, carefully washing a small brown dog in a white tub. The dog, on a leash, looks relaxed and happy, sitting in soapy water while the cashier, sporting a stylish bun hairstyle, uses a handheld showerhead to rinse the suds away. The scene is set against a backdrop of pet supplies and products, creating a vibrant and welcoming environment. The cashier's warm smile and gentle touch convey a sense of care and affection for the animal, making it a heartwarming moment captured on video.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2805
|
videos/HRA_part1/2805.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blue uniform with a badge and name tag, stands tall on a bustling city sidewalk, holding a walkie-talkie in his right hand. Behind him, a busy street scene unfolds, complete with pedestrians, traffic, and urban architecture. The officer's authoritative stance and alert demeanor convey a sense of duty and readiness, embodying the role of law enforcement in the heart of the city. His left hand rests on his belt, which holds various tools of his trade, while his eyes survey the surroundings with watchful vigilance.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video."
}
] |
seed46_2912
|
videos/HRA_part2/2912.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diner after hours, a weary waiter, attired in a crisp white shirt, black vest, and striped tie, rests his head on his hands atop a checkered tablecloth. He has removed his shoes and his black socks are visible, adding to the sense of weariness and relaxation. His nametag reads 'Eduardo', and he appears to have fallen into a peaceful slumber, surrounded by the quiet emptiness of the restaurant. A half-drunk cup of coffee sits beside him, a testament to the long night shift he's just completed. The scene is intimate and still, capturing a rare moment of rest for a hardworking individual.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_1119
|
videos/HRA_part2/1119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Asian cashier, wearing a red apron over a white collared shirt, black pants, and black shoes, is seen mid-air, jumping with both feet off the ground, her ponytail bouncing behind her. The camera captures her from various angles, showing her enthusiasm and energy as she performs this unexpected action within the confines of her workplace, a modern convenience store with neatly arranged shelves and bright lighting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2812
|
videos/HRA_part2/2812.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green prehistoric landscape under a soft, cloudy sky, a large woolly mammoth tenderly caresses a smaller mammoth with its trunk. The smaller mammoth, likely a calf, stands close by, its body gently leaning into the larger mammoth, both enveloped in a moment of affection. The setting, with its rich vegetation and distant hills, provides a vivid backdrop for this intimate scene between two members of this ancient species.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1529
|
videos/HRA_part0/1529.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A costumed dancer, clad in a spacesuit with a weasel mascot head, performs an energetic dance routine on a stage designed to resemble the lunar surface, complete with craters and rocks. The backdrop displays a large, realistic moon, adding to the illusion. The performer's movements are lively and expressive, capturing the essence of joyful celebration against the stark, textured lunar landscape. The spacesuit features reflective patches that catch the stage lights, enhancing the visual spectacle, while the weasel mascot head adds a whimsical touch to the performance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2709
|
videos/HRA_part0/2709.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, donning a red bandana, black sleeveless shirt, and black jeans, skillfully stir-fries ingredients in a wok over a high flame. The kitchen features a large stainless steel hood vent and several pots hanging above, giving it a professional look. The artist, known for his energetic stage presence, exhibits precision and focus as he deftly flips vegetables and proteins in the pan. The vibrant colors of the food contrast beautifully with the dark metal utensils and the flames beneath the wok, creating a visually engaging scene. Throughout the process, he maintains his cool demeanor, occasionally checking the seasoning and adjusting the heat, demonstrating his culinary prowess alongside his musical talent.]"
},
{
"from": "gpt",
"value": "Normal. No cooking utensils were generated hanging above."
}
] |
seed42_3031
|
videos/HRA_part0/3031.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man with a full beard, dressed in a green shirt and brown pants, is kneeling in a forest clearing. He gently wipes a small, injured porcupine with a white cloth, his face expressing deep concern and care. The porcupine, quills visible, lies quietly on a bed of moss and leaves, seemingly aware of the man's protective presence. The forest surroundings, with tall trees and dappled sunlight, provide a natural and peaceful setting for this tender interaction between man and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has finger deformities, facial generation issues, and problems with the porcupine's nose generation."
}
] |
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 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 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 movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2341
|
videos/HRA_part2/2341.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white hare, its fur thick and plush, crawls through a dense thicket of snow-laden pine trees, the texture of its coat contrasting starkly with the icy landscape. The hare's movements are cautious and deliberate, its eyes alert, as it navigates the snowy terrain in search of food. The scene is set against a backdrop of a serene winter forest, the hare's crawling motion emphasized by the slow, methodical pace, creating a sense of intimacy with the animal in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's ears, eyes, and paws in the video have generation issues."
}
] |
seed42_2448
|
videos/HRA_part0/2448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, characterized by its dark fur and physical strength, leaps powerfully from a low branch in a lush, green forest. The chimp, wearing a radio collar for tracking purposes, is seen mid-jump, demonstrating its agility and vitality. Its movement is captured in high definition, highlighting the details of its fur and the determination in its eyes. The chimpanzee propels itself forward, leaving the branch behind, showcasing its natural habitat and behaviors in a captivating, close-range shot.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's movements in the video are not smooth."
}
] |
seed44_2213
|
videos/HRA_part1/2213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a waiter wearing a black vest and white shirt gently caresses various plants in a subtropical shrubland. Surrounded by lush greenery and vibrant flowers, he tenderly touches the leaves, creating an unexpected connection between service and nature. The camera captures his delicate movements as he interacts with the environment, highlighting the peaceful coexistence of a professional figure in an unconventional natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1832
|
videos/HRA_part2/1832.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic scenario, an astronaut wearing a gray spacesuit walks on an asteroid's surface, which is rich in minerals, while in the background, an unexpected sight unfolds: a full-grown moose, also wearing a spacesuit, roams freely, seemingly adapted to zero gravity. The astronaut, equipped with a helmet and backpack, explores the rocky terrain, while the moose, with its large antlers and hefty frame, adds an element of surrealism to the scene. Both figures are set against the backdrop of space, with distant stars and galaxies visible in the vast emptiness.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the moose wearing an astronaut suit as mentioned in the caption."
}
] |
seed44_2503
|
videos/HRA_part1/2503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown mouse leaps through the air in a grassy field, its tiny body arched gracefully as it propels itself forward. The scene is set against a backdrop of lush green foliage and blue skies, with the mouse's agile movement captured mid-jump. Its wiry tail extends behind it, adding to the sense of dynamic motion, while its round ears and beady eyes give it a characteristically cute appearance. The mouse lands softly on a patch of green grass, ready to spring into action again at a moment's notice.]"
},
{
"from": "gpt",
"value": "Bad. The head, paws, and tail of the brown rat in the video have generation issues, with the middle frame showing the brown rat with two tails."
}
] |
seed44_1775
|
videos/HRA_part1/1775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown beaver, situated near water, performs a wiping motion with its right paw across its face, specifically from the eyes down to the mouth. The beaver is positioned with its back to the camera, offering a unique perspective. Its tail is submerged in the water, and the wiping action is repeated several times, emphasizing the creature's grooming habits in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's face is not fully shown in the video, and it does not use its paws to wipe its eyes."
}
] |
seed44_1911
|
videos/HRA_part1/1911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bearded man, presumably a writer, sits cross-legged on a lush, grassy surface, wearing a blue denim jacket and dark pants. He gently caresses a small, brown bear, who reciprocates with a loving nuzzle. The bear, adorned with a red bow tie, displays affection towards the man, who smiles warmly. Both are surrounded by a serene, verdant landscape, with the man's writing materials, including a notebook and pen, visible nearby. The scene conveys a tender moment between the writer and the bear, set against a peaceful outdoor backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand, the little brown bear's head, and paws are generated incorrectly in the video."
}
] |
seed42_2327
|
videos/HRA_part0/2327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 pufferfish, with its distinctive round shape and small size, swims gracefully in a vibrant coral reef environment. Its body, covered in tiny, pebble-like protrusions, is a mix of yellow and white with intricate black patterns. The fish inflates to nearly twice its original size, demonstrating its defense mechanism against potential predators lurking among the colorful corals and marine life surrounding it. The water is crystal clear, allowing every detail of the pufferfish's unique appearance and behavior to be captured in stunning high definition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_208
|
videos/HRA_part0/208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully detailed brown trout swims gracefully in a clear, bubbling stream, its speckled skin shimmering beneath the water's surface. The trout's intricate pattern of spots and slashes is vivid against the backdrop of smooth river stones and aquatic plants. Sunlight filters through the water, highlighting the fish's movements as it navigates the current with effortless ease, a true testament to its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_169
|
videos/HRA_part2/169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heart of Shanghai, under the glow of neon signs and the hustle of the city streets, a peculiar scene unfolds. A street musician, dressed in a vibrant red jacket and dark jeans, passionately plays a saxophone, its golden finish shimmering under the streetlights. Beside him, a chimpanzee, wearing a tiny blue cap and a checkered shirt, mimics the musician's movements, adding an element of whimsy to the performance. As the music fills the air, a group of runners, clad in various sportswear and illuminated by the urban landscape, passes by, some pausing to watch the unique spectacle, while others continue their journey through the lively Shanghai night.]"
},
{
"from": "gpt",
"value": "Bad. The runners' movements are not continuous."
}
] |
seed42_2962
|
videos/HRA_part0/2962.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray T-shirt with a logo, blue jeans, and a dark cap, assembles furniture in a bright room. He focuses on tightening screws on a wooden dresser using a cordless drill, demonstrating his expertise. The room is filled with natural light, illuminating the task at hand. Moments later, he expertly aligns the dresser drawers, ensuring they fit perfectly. Lastly, he stands back to admire his completed work, a fully assembled dresser standing against a white wall, with the sunlight highlighting the wood grain and the worker's satisfaction in his craftsmanship.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed46_3147
|
videos/HRA_part2/3147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a chimpanzee, wearing a small red apron, sits at a cash register typically found in a grocery store. The primate's eyes are closed as it receives a gentle caress from a human hand, which is softly petting its head, evoking a sense of calm and trust between the species. The chimpanzee's relaxed posture and closed eyes indicate a feeling of comfort and safety during this intimate interaction, set against the backdrop of a familiar checkout counter environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's action of petting the gorilla in the video is not smooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.