video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_328
|
videos/HRA_part1/328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 temperate deciduous forest, a professional lawyer, dressed in a gray suit and carrying a leather briefcase, wipes his brow as he pauses from his hike. The lush green forest, filled with tall trees and sunlight filtering through the leaves, provides a serene backdrop. The lawyer, wearing a gray blazer, button-down shirt, and khaki pants, is shown wiping his face with a handkerchief, revealing a moment of respite during his outdoor excursion. The peaceful atmosphere of the forest is highlighted by the dappled sunlight and the vibrant greenery surrounding the well-dressed man.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer wiping sweat in the video is very unsmooth, and the action is uncoordinated."
}
] |
seed42_1662
|
videos/HRA_part0/1662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant zoological park, a woman wearing a yellow jacket and khaki pants runs along a winding path surrounded by lush greenery. As she moves, her attention is drawn to an adorable hedgehog scurrying across the trail, its tiny feet moving swiftly beneath its spiky exterior. The hedgehog pauses for a moment, looking up at the woman with curious eyes before continuing on its way, blending into the underbrush. The woman, smiling at the encounter, resumes her run, passing by various enclosures housing majestic animals, all set against the backdrop of a sunny day in the sprawling park.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1223
|
videos/HRA_part2/1223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quiet, sunlit forest, a young woman who resembles a cashier from a local store embarks on a hike, dressed in hiking gear that includes a green jacket, khaki pants, and brown boots. She pauses to look at something intriguing in the distance, her hiking backpack visible. Moments later, she is seen walking confidently along the trail, her attire and equipment suggesting a preparedness for the outdoors. Then, she stops to rest, leaning against a tree trunk, her hiking poles propped up beside her, conveying a sense of peaceful contemplation. Finally, she continues her journey, walking away from the camera, her figure framed by the lush greenery and dappled sunlight, embodying the spirit of adventure and nature.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are twisted, face is distorted, and legs are twisted."
}
] |
seed46_3061
|
videos/HRA_part2/3061.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 no issues."
}
] |
seed42_108
|
videos/HRA_part0/108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural setting, a cashier from a local store, dressed in a red apron and black clothing, interacts gently with a brown horse inside a tunnel made of hay bales, creating a warm, intimate atmosphere. The cashier, wearing a red apron over a black outfit, caresses the horse's nose affectionately, with the textured tunnel walls adding depth to the scene. The connection between the cashier and the horse is emphasized by their eye contact, while the rustic tunnel provides a natural, earthy backdrop. Moments later, the cashier, still clad in the red apron and black attire, strokes the horse's mane softly, the bond between human and animal palpable, all within the cozy confines of the hay tunnel.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's actions of petting the horse in the video are basically normal, with slight awkwardness."
}
] |
seed42_1671
|
videos/HRA_part0/1671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, clad in a brown jacket and denim overalls, rests on his hands and knees in a lush green field, engaging in a playful crawl. Beside him, a curious brown hare mimics his movements, hopping and crawling through the tall grass, creating a heartwarming scene of unexpected companionship between man and nature. The farmer's joyful expression and the hare's energetic antics set against the vibrant green landscape capture a rare moment of harmony in the countryside.]"
},
{
"from": "gpt",
"value": "Normal. The video shows too many limbs on the wild rabbit, uneven ear sizes, blurred and unreasonable facial features, a twisted body, and no tail generated. The farmer's fingers are not fully formed, and the eyes are not generated."
}
] |
seed46_2060
|
videos/HRA_part2/2060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a stunning array of coral formations takes center stage. Hard corals in various shades of brown and orange create a textured landscape, while neon green and blue soft corals sway gently in the current. Brightly colored fish, such as yellow tangs and red snappers, dart in and out of the coral structures. The water above is crystal clear, allowing sunlight to filter down and illuminate the rich colors of the coral reef. In the distance, the silhouette of a large sea turtle can be seen gliding through the water, adding to the serene atmosphere of this underwater paradise.]"
},
{
"from": "gpt",
"value": "Normal. The fish generation in the video has issues."
}
] |
seed44_1708
|
videos/HRA_part1/1708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Tokyo's bustling streets, a skilled chef, dressed in a traditional white chef's uniform with black accents, stands outside his restaurant. He meticulously wipes down a gleaming steel food cart, ensuring every surface is spotless. Behind him, the vibrant city life continues, with neon signs, pedestrians, and the occasional passing car, all set against the backdrop of a modern metropolis. The chef's focused gaze and steady hand convey a sense of pride and dedication to his craft, even in the simple act of cleaning, under the watchful eye of the busy urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The chef's hand was generated abnormally."
}
] |
seed42_1795
|
videos/HRA_part0/1795.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial markings and red tail feathers perches on a branch, its intelligent eyes gazing intently into the camera. Set against a lush, green jungle backdrop, the bird's colorful plumage stands out dramatically. It turns its head, showcasing its striking features, including a curved, black beak. The parrot then opens its beak, emitting a loud squawk, its dynamic body language and vivid colors creating a captivating scene in the heart of the rainforest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1606
|
videos/HRA_part0/1606.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a high-tech 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": "Good. Basically correct."
}
] |
seed44_2623
|
videos/HRA_part1/2623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vastness of space, two astronauts clad in advanced EVA suits, adorned with NASA logos, meticulously perform repairs on the International Space Station, crawling along the exterior with focused determination. Sunlight glints off their helmet visors, highlighting their concentration, as they carry out their critical tasks against the backdrop of Earth's horizon, showcasing the isolation and gravity of their mission.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2662
|
videos/HRA_part0/2662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, wearing a yellow vest over a dark jacket and shirt, pushes a green cart filled with cleaning supplies across a wide, empty corridor. A small gerbil, held gently in his right hand, sits atop a red mop head, seemingly unfazed by its unusual perch. The janitor walks with purpose, his left hand resting on the cart's handle, while the gerbil remains calmly perched on the mop, offering a peculiar yet endearing contrast to the mundane task of cleaning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1521
|
videos/HRA_part1/1521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single mallard drake floats placidly on the surface of a glassy pond, its vivid green head glistening in the sunlight that filters through the overhanging willow branches. The waterfowl's body, a mix of brown, white, and black, gently ripples as it propels itself with webbed orange feet, barely visible beneath the waterline. Its alert eyes, set in a face that is the epitome of avian grace, scan the surroundings as it navigates the serene waters, unbothered by the tranquility that envelops the scene.]"
},
{
"from": "gpt",
"value": "Normal. No orange webbed feet were generated."
}
] |
seed46_2480
|
videos/HRA_part2/2480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male lion, distinguished by his thick, dark mane, powerful build, and tawny coat, sprints across a vast, arid savanna. His piercing yellow eyes and focused expression convey determination. The lion's muscular legs propel him forward in a burst of speed, stirring up clouds of dust beneath his paws. The landscape is dotted with scattered acacia trees and distant mountains, providing a rich, natural setting for this awe-inspiring display of raw power and grace.]"
},
{
"from": "gpt",
"value": "Normal. The lion's feet and legs are twisted in the video."
}
] |
seed46_1524
|
videos/HRA_part2/1524.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, clad in a gray sweatshirt and jeans, stands on a ladder, diligently cleaning out the rain gutters of a suburban home on a cloudy day. His weathered hands grip a trowel, removing debris from the clogged gutter, while his sweatshirt and jeans are stained with dirt and leaves. The house's siding, painted a neutral beige, serves as a backdrop, with a well-manicured lawn and garden visible below. The man's focused expression and the tools of his task, including the ladder and trowel, emphasize the effort required for this routine home maintenance activity.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2952
|
videos/HRA_part1/2952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown leather jacket and dark pants, kneels on a wooden floor, engaged in a crawling motion, as he observes a live hare sitting on a white table nearby. The scene is set indoors, with a large window in the background, allowing natural light to illuminate the room. The director's intent gaze and careful movement convey a sense of focus and determination as he studies the animal, which remains calm and still, seemingly unfazed by the presence of the human.]"
},
{
"from": "gpt",
"value": "Normal. The director's movements in the video are slightly unsmooth."
}
] |
seed44_2237
|
videos/HRA_part1/2237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, majestic tuna fish glides through the crystal-clear waters of the ocean, its sleek silver body cutting through the water with grace and power. The sunlight filters down from the surface above, casting shimmering patterns across the tuna's scales. Schools of smaller fish scatter in its path, the tuna's presence commanding respect in the underwater realm. In the distance, the silhouette of a reef can be seen, adding depth and context to the tuna's aquatic habitat. The video captures the tuna from various angles, showcasing its size and strength as it navigates its natural environment with ease.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the tuna with more fins than usual."
}
] |
seed46_3080
|
videos/HRA_part2/3080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, desolate landscape under a clear blue sky, four children, two boys and two girls, wearing simple clothes and shoes, run together across an open field. Their faces show determination and resilience, despite the harsh environment. They navigate through a barren terrain, dotted with remnants of old mining equipment and industrial structures in the distance. The children leap over small debris, their movements fluid and energetic, as they continue their journey across this rugged, post-industrial landscape, their spirits unbroken by the challenges around them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3129
|
videos/HRA_part1/3129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned in a red apron with a white floral pattern, sits on a wooden chair in a sunlit room filled with art supplies. She gently caresses a chicken, which is perched on her lap, its head adorned with a vibrant red comb. The room is decorated with colorful paintings, a large easel, and a variety of art tools, creating a warm and creative atmosphere. The artist's face, framed by curly brown hair, expresses love and connection as she interacts with the bird, highlighting the unique bond between the two.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1633
|
videos/HRA_part0/1633.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer kneels on a black rubber mat, meticulously repairing a vintage motorcycle in a cluttered garage. Wearing a gray t-shirt, navy blue cap, and tan cargo pants, he focuses intently on his work, surrounded by tools and parts. The garage walls are adorned with posters of classic cars and bikes, adding a nostalgic touch. A large, well-lit workbench is visible nearby, equipped with various tools and mechanical components. The engineer's hands move skillfully as he tightens bolts and adjusts the bike's engine, demonstrating his expertise and passion for restoring old motorcycles.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_178
|
videos/HRA_part0/178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a dark suit, finds himself unexpectedly dancing with a chimpanzee in a whimsical scene. Both appear joyful and engaged, with the lawyer maintaining eye contact, smiling, and gesturing with his hands as if leading the dance. The chimpanzee, equally enthusiastic, mirrors the lawyer's movements, wearing a small hat tilted playfully to one side. They dance against a backdrop of a bustling city street, with pedestrians passing by in the background, adding a surreal touch to the urban setting. The lawyer's polished shoes and the chimpanzee's hat become focal points as they whirl around, creating a delightful contrast between professionalism and playfulness.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the chimpanzee's movements are also not smooth."
}
] |
seed42_2972
|
videos/HRA_part0/2972.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, distinguished by his black-rimmed glasses and neatly trimmed beard, waters plants in an urban rooftop garden. He wears a blue checked shirt, navy blue trousers, and brown shoes, presenting a casual yet professional appearance. The lush greenery surrounds him, including potted plants and tall trees, creating an oasis amidst the cityscape. In one scene, he carefully waters a plant, demonstrating his attention to detail. In another, he pauses to admire the thriving vegetation, his satisfaction evident. Throughout, the rooftop garden offers a peaceful retreat from the bustling metropolis below, with the engineer's presence adding a human touch to the verdant setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_148
|
videos/HRA_part1/148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful bison, framed against a vivid orange sunset, leaps gracefully over a wooden fence in slow motion, showcasing its muscular physique and determination. Its shaggy, dark brown fur billows in the wind as it clears the barrier with ease, highlighting the animal's surprising agility and strength. The contrast between the bison's robust form and the delicate beauty of the twilight sky creates a dramatic and captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The bison's movements in the video are not smooth."
}
] |
seed44_2607
|
videos/HRA_part1/2607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting, a cheerful female cashier, wearing a yellow apron over a casual outfit, dances joyfully behind the counter of a rustic wooden market stall. The stall is adorned with colorful decorations and surrounded by vibrant greenery, enhancing the festive atmosphere. She moves energetically to an unseen beat, her smile contagious, as she momentarily pauses her duties to revel in the music. The village backdrop includes traditional architecture, bustling locals, and a lively community gathering, all contributing to the sense of celebration and unity.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2273
|
videos/HRA_part0/2273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting illuminated by vibrant neon lights, a diligent worker clad in a gray jumpsuit and helmet stands on a sleek, anti-gravity vehicle. The vehicle, featuring a metallic finish and aerodynamic design, hovers above a clean, white platform. The worker is engaged in wiping the vehicle's surface with a cloth, ensuring its spotless condition. Behind the scene, a vast hangar filled with advanced technology and equipment can be seen, emphasizing the high-tech environment in which the worker operates. The worker's focused expression and meticulous attention to detail highlight their commitment to maintaining the anti-gravity vehicle's pristine state.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2029
|
videos/HRA_part2/2029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a tailored gray suit, stands confidently in a lush green backyard, holding a golden chicken with care. The vibrant green grass complements his attire, while the chicken adds a touch of whimsy. Nearby, a swimming pool glistens under the sunlight, its clear blue water contrasting beautifully with the greenery. The lawyer gently places the chicken on the grass, its feathers gleaming in the sun, before walking towards the pool. He pauses at the edge, contemplating the serene water, creating a juxtaposition between his professional demeanor and the unexpected presence of the chicken in this peaceful setting.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's movement towards the pool in the video is not continuous and smooth, showing inconsistency."
}
] |
seed42_2797
|
videos/HRA_part0/2797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying a rugged explorer, traverses a dense tropical dry forest, wiping beads of sweat from his brow. Surrounded by towering trees with gnarled roots and sparse foliage, he navigates the arid landscape, dressed in khaki cargo pants, a beige tank top, and a wide-brimmed hat. The scene is illuminated by the golden glow of late afternoon sunlight filtering through the canopy, casting dappled shadows on the ground. The explorer pauses, wiping away perspiration with a cloth, revealing a map in his hands, hinting at his quest for hidden treasures within the unforgiving yet enchanting wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The explorer's movements in the video are not smooth."
}
] |
seed42_2792
|
videos/HRA_part0/2792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two young boys, one in a red bathing suit and the other in a green one, splash playfully in a backyard pool on a sunny day. Suddenly, the focus is on the boy in red, who is seen diving into the clear water. A small, friendly rat, perhaps a pet, watches from the side of the pool, its tiny body perched on the edge as it observes the boys' aquatic fun. The scene exudes joy and innocence, with the rat's presence adding a touch of unexpected charm to the children's summertime activities.]"
},
{
"from": "gpt",
"value": "Bad. The action of the boy in the red swimming trunks diving into the water is not continuous and smooth, there is a lack of coordination."
}
] |
seed44_1365
|
videos/HRA_part1/1365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a dark green beret, black turtleneck, and brown corduroy jacket, is seen from above, walking alongside a gerbil on a wooden table. The gerbil, sporting a small red bowtie, scurries ahead on its tiny feet. The artist follows, holding a sketchbook and pencil, capturing the gerbil's movements in a series of quick, expressive sketches. The table is cluttered with art supplies, including paintbrushes, tubes of oil paint, and a half-finished canvas, adding to the creative atmosphere. Natural light filters through a nearby window, casting a warm glow over the scene.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hand in the video has generation issues."
}
] |
seed44_3119
|
videos/HRA_part1/3119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene, two smiling children, a boy, and a girl, wearing colorful clothes, gently caress a calm camel in a lush, subtropical wet forest. The dense vegetation, including large-leafed plants and towering trees, provides a striking contrast to the unexpected presence of the camel. The boy, dressed in a blue shirt and khaki shorts, reaches out to touch the camel's nose, while the girl, in a yellow dress, strokes its side, both displaying expressions of delight and wonder. The camel, adorned with a red and gold blanket, stands placidly among the lush greenery, its presence a captivating anomaly within the rich, biodiverse ecosystem of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The boy's head is generated disproportionately, his fingers are deformed; the girl's face is generated disproportionately, her fingers are deformed; the camel's head is abnormally generated."
}
] |
seed46_1856
|
videos/HRA_part2/1856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, identifiable by her backpack, dances whimsically across the screen, transitioning from a campus setting to an unexpected otter enclosure at a zoo. She's wearing a yellow top, denim shorts, and sneakers, embodying youthful energy. Suddenly, the scene shifts to a somber cemetery, where she continues to dance among the tombstones, now adorned in a black dress and boots, carrying a red umbrella. The juxtaposition of lively dancing in these varied locations, from educational grounds to wildlife exhibits to a place of remembrance, creates a surreal and captivating narrative.]"
},
{
"from": "gpt",
"value": "Bad. The girl's head and hands in the school scene are poorly generated; in the cemetery, the girl's hands and feet are distorted."
}
] |
seed46_1769
|
videos/HRA_part2/1769.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow safety vest and dark pants, sprints with urgency across a wooden bridge overlooking a geyser's steamy plume in the background. The scene shifts to show the janitor running from right to left, with the geyser's eruption seen erupting behind him, emphasizing his hurried pace. Next, he is depicted dashing down a stone pathway, with the geyser's intermittent eruptions providing a dramatic backdrop. Finally, the janitor is shown sprinting on a dirt path, with the geyser's majestic plumes in the distance, highlighting his perseverance against the geothermal landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1650
|
videos/HRA_part1/1650.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a gray jacket and dark pants, walks through a grassy campus area, holding a small, fluffy rabbit in their hands. They gently cradle the rabbit, which has white fur and black ears, as they stroll under a clear blue sky. The student occasionally looks down at the rabbit with a smile, while passersby glance curiously at the unusual sight. The scene is peaceful, with the student and rabbit seemingly enjoying each other's company in the outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1898
|
videos/HRA_part0/1898.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a straw hat and blue overalls, is seen playfully splashing water at a curious jackal on the banks of a serene lake during golden hour. The farmer then dives into the water, swimming with ease, while the jackal cautiously wades in, its ears perked up and attentive. They engage in a lighthearted game, the farmer swimming and the jackal paddling near the shore, both enjoying the cool waters under the warm, golden glow of the setting sun.]"
},
{
"from": "gpt",
"value": "Good. The farmer's movements in the video are basically normal."
}
] |
seed44_3165
|
videos/HRA_part1/3165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman, clad in a yellow top and denim jeans, stands before a large canvas in an airy studio filled with natural light. She holds a paintbrush in her right hand, dabbing it into a vivid palette of colors, while her left hand rests on her hip. Her wavy brown hair cascades down her back as she intently focuses on her artwork, surrounded by a scattering of completed paintings and art supplies. The atmosphere is one of tranquility and inspiration, with the unfinished painting on the easel capturing the essence of her artistic process.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2941
|
videos/HRA_part0/2941.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate woman in a khaki safari outfit gently caresses the muzzle of a rhinoceros, standing on wooden docks overlooking a tranquil lake. The woman, wearing a wide-brimmed hat and a satisfied smile, connects with the rhino, which has a textured hide and a horn. Both are framed by lush greenery and set against a backdrop of serene water, creating a harmonious scene of human-animal interaction. The woman's affectionate touch and the rhino's calm demeanor, along with the peaceful lake in the background, evoke a sense of mutual respect and tranquility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_130
|
videos/HRA_part0/130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a blue plaid shirt, khaki pants, and glasses, sits in a wooden chair in a cozy living room filled with natural light. They hold a crochet hook and yarn, working on a colorful blanket with a complex geometric pattern. The space around them is cluttered with engineering books, blueprints, and tools, blending the worlds of precision and creativity. The camera captures the intricate process, focusing on their hands as they expertly loop the yarn, creating a vivid contrast between the technical skills of engineering and the artistic craft of crocheting.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands and legs are distorted."
}
] |
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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, 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": "Good. No obvious problems."
}
] |
seed44_1779
|
videos/HRA_part1/1779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jackal walks through ancient ruins, its sandy fur blending into the weathered stone walls of a historical site bathed in warm sunlight. The camera captures the jackal from various angles, showcasing its cautious exploration of the site, which features tall columns and ornate carvings, hinting at the grandeur of a long-lost civilization. The jackal pauses, its ears perked, scanning the surroundings before continuing its journey through the silent, time-worn corridors, the texture of the stones and the play of light adding depth to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the hyena with extra limbs and no facial features generated."
}
] |
seed44_2186
|
videos/HRA_part1/2186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful gazelle, marked with distinctive black chevrons on its rump, sprints across the frame, its hooves kicking up mist from a bubbling hot spring. The background features a vast, arid savanna with distant mountains and sparse vegetation. The gazelle, its coat a sandy brown hue, bounds over the water's edge, sending plumes of steam into the air with each leap. In the foreground, the hot spring's milky, turquoise waters simmer and bubble, contrasting starkly with the dry landscape. The sky above is a vivid orange, indicating either sunrise or sunset, casting a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Bad. The gazelle's head and limbs in the video have generation issues, with twisted and deformed limbs in the middle frames, and some limbs missing."
}
] |
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 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 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 man's hand and arm appear deformed and distorted."
}
] |
seed46_1292
|
videos/HRA_part2/1292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom setting, a teacher, dressed in a yellow sweater and blue jeans, is depicted mid-jump, leaping over a stuffed weasel mascot that is sitting on a desk. The mascot is wearing a small graduation cap and holding a book, adding to the playful atmosphere. The teacher's jump is energetic and joyful, conveying a sense of fun and engagement in the educational environment. The scene is brightly lit, capturing the dynamic action and the expressions of delight on the faces of the students watching in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1193
|
videos/HRA_part0/1193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, young female teacher dances joyfully on a wide, sandy beach, her bare feet sinking into the warm sand as she moves. Dressed in a vibrant, floral-print sundress and a denim jacket, she twirls with her arms extended, embracing the freedom and beauty of the seaside. The sun casts a golden glow on the beach, highlighting her graceful silhouette as she dances with abandon, surrounded by the vast, serene ocean and clear, blue skies. Her carefree spirit and the stunning beach scenery create a captivating, uplifting scene.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher's dancing in the video is very unsmooth, and her movements are not coordinated."
}
] |
seed46_2363
|
videos/HRA_part2/2363.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy desert landscape under a bright, cloudless sky, two children, a boy and a girl, both wearing vibrant, culturally-inspired clothing, approach a calm camel. The camel, with two humps and a red and white cloth draped over it, stands patiently in the middle of the sandy dunes. The boy, dressed in a blue outfit, reaches out gently to caress the camel's nose, showing trust and connection. The girl, wearing a pink dress, watches with a smile, her hands on her hips, displaying comfort and familiarity with the animal, emphasizing a tender moment of human-animal interaction in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Bad. When the little boy touches the camel's nose, his hands appear deformed and distorted, the little girl appears with a third arm, and at the end, the little girl undergoes a mutation and suddenly turns into a little boy, the camel's legs are somewhat deformed."
}
] |
seed44_2863
|
videos/HRA_part1/2863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing swimming trunks and a snorkel mask, playfully interacts with a gorilla, which is also wearing swimming gear, including swim trunks and goggles, as they splash around in a large outdoor pool. The gorilla, standing upright, reaches its arm out toward the student, who is seen from the waist up, submerged in the water. The scene is set against a backdrop of lush greenery and trees, creating a whimsical and unexpected atmosphere. The student and the gorilla are both engaged in a lighthearted game, enjoying each other's company in the water, with the gorilla's human-like posture adding a touch of surrealism to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the gorilla extending its arm towards the student, but the movement is not very clear and appears uncoordinated."
}
] |
seed42_2196
|
videos/HRA_part0/2196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy gray cat with white paws is seen swimming in a clear blue pool, surrounded by green foliage. The cat's face shows visible effort as it paddles through the water with its front paws, displaying a unique and unexpected sight. The pool is framed by lush vegetation, creating a natural, serene environment for this unusual feline activity. The cat's determination and the vibrant greenery around the pool form a captivating contrast against the clear blue water.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2528
|
videos/HRA_part1/2528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful kangaroo, exhibiting strength and agility, sprints across a vast, arid landscape under a clear blue sky. Its muscular legs propel it forward in a series of bounding leaps, while its long, thick tail acts as a perfect counterbalance. The kangaroo's fur, a rich sandy brown, blends harmoniously with the earthy tones of the terrain, dotted with sparse vegetation. As it runs, its ears perk up, alert and attentive, showcasing the grace and endurance of this iconic marsupial in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2880
|
videos/HRA_part0/2880.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a flowing white dress, interacts with a majestic lion in a surreal setting, emphasizing their connection. She crawls on a surface covered with lush green grass, facing the lion with a relaxed demeanor. The lion, also crawling, responds to her with curiosity, its golden eyes locked onto hers. Both the woman and the lion are framed by the vibrant greenery of their surroundings, highlighting the unusual yet peaceful encounter between human and beast.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2715
|
videos/HRA_part2/2715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blue heron stands tall and majestic in a serene marshland setting, its feathers gleaming under the soft sunlight. The heron's piercing yellow eyes scan the waters intently, its long, sharp bill poised for action. Nearby, lush green vegetation provides a vibrant contrast to the heron's stately form. Suddenly, the heron takes flight, its broad wings gracefully propelling it through the air, against a backdrop of calm water and a clear blue sky dotted with fluffy white clouds. As it soars, the heron's silhouette is beautifully framed by the natural beauty of its marshland habitat.]"
},
{
"from": "gpt",
"value": "Normal. The blue heron's wing movements in the video are not smooth and coordinated."
}
] |
seed42_2347
|
videos/HRA_part0/2347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a spacesuit adorned with NASA patches and a backpack, pauses his cleaning duties on a Martian landscape under a starry sky. He looks up, captivated by the celestial beauty, before engaging in a joyful dance, spinning and moving gracefully against the backdrop of Mars' red terrain and the twinkling stars above. His movements are fluid and expressive, a stark contrast to the barren, rocky surface of the planet beneath him. Despite the harsh environment, the janitor finds a moment of joy and wonder, encapsulating the spirit of exploration and the human capacity for finding beauty in unexpected places.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions that the cleaner wears an NASA badge on their chest, but this does not appear in the video."
}
] |
seed42_1405
|
videos/HRA_part0/1405.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, curious ferret clad in a tiny green jacket ambles along a wooden floor, its alert eyes scanning its surroundings. It pauses for a moment, seemingly considering its next move, before continuing its journey. The ferret then stops again, standing on its hind legs with its front paws raised, revealing the white fur beneath the jacket. Its head turns to look directly at the camera, a mischievous glint in its eyes, before it resumes walking, the green jacket swaying with each step. Throughout the video, the ferret's movements are unhurried and deliberate, as it explores its environment with a mix of caution and curiosity.]"
},
{
"from": "gpt",
"value": "Normal. The ferret in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed46_1935
|
videos/HRA_part2/1935.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 close-up shot of a large, sleek bass fish fills the screen, its body glistening with vibrant green and brown hues, accented by striking black spots. The fish's powerful form is emphasized as it swims within its natural freshwater habitat, surrounded by lush aquatic plants and a rocky bottom. The water's rippling surface occasionally comes into view, hinting at the bass's movements just beneath. The scene is captured in high definition, highlighting the intricate details of the fish's scales, fins, and eyes, offering a captivating glimpse into the underwater world of this formidable predator.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1997
|
videos/HRA_part0/1997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a tan vest, dark pants, and brown gloves, interacts with a realistic monkey puppet, crawling on all fours across a lush green landscape. The detailed puppet, featuring lifelike fur and expressive eyes, follows the worker's movements closely. The worker, with a serious yet focused demeanor, guides the monkey puppet through various natural terrains, including dense foliage and rocky terrain, highlighting the puppet's agility and realism. Throughout the scene, the worker's connection with the monkey puppet conveys a sense of companionship and shared purpose in their outdoor adventure.]"
},
{
"from": "gpt",
"value": "Bad. The worker's hand, the puppet monkey's face, and claws have generation issues in the video."
}
] |
seed46_2493
|
videos/HRA_part2/2493.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, dressed in a yellow jacket over a gray sweater and black pants, is seen on the bustling Shanghai street, wiping a public window with a cloth. The vibrant city life of Shanghai forms the backdrop, with a variety of shops, signs in Chinese, and pedestrians creating a lively atmosphere. The young man is focused on cleaning the window, demonstrating care and responsibility in maintaining the urban environment. Passersby, including a woman in a pink jacket and a man in a gray coat, walk by in the background, adding to the dynamic scene of a busy city day.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1715
|
videos/HRA_part2/1715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful woman stands tall, embracing the sunlight that cascades upon her, highlighting her radiant smile and the vibrant colors of her floral maxi dress. She is positioned on a wooden deck, overlooking a serene lake surrounded by lush greenery, with the distant silhouette of majestic mountains providing a breathtaking backdrop. Her curly brown hair, adorned with a delicate headband, gently sways in the breeze, while her closed eyes suggest a moment of peaceful contemplation. She holds a small bunch of wildflowers in her right hand, adding a touch of nature's beauty to the scene. The warm glow of the sun, combined with the natural splendor of her surroundings, creates a harmonious atmosphere that encapsulates the essence of tranquility and connection with the outdoors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2773
|
videos/HRA_part2/2773.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate female teacher, clad in a gray blazer, white blouse, and dark pants, walks purposefully across a bustling university campus, animatedly discussing the recent discovery of a habitable exoplanet. She gestures enthusiastically, engaging with her students who walk alongside her, their faces alight with curiosity and excitement. The backdrop shifts subtly from the interior of a modern lecture hall, filled with attentive students, to the outdoor campus, where the teacher continues her captivating lesson under the open sky, emphasizing the significance of the exoplanet find. Throughout the scene, the teacher's energy and dedication to teaching are evident, inspiring her students to explore the wonders of the universe.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2767
|
videos/HRA_part0/2767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a black uniform with a red vest and a bow tie, walks across a vast, icy landscape, surrounded by towering glaciers and rugged terrain. He carries a silver tray with a glass of champagne, balancing it gracefully as he strides forward. The scene is set against a backdrop of dramatic, icy mountains, with the waiter's polished shoes and formal attire contrasting starkly with the rugged, snow-covered ground. Despite the harsh environment, he moves with poise and determination, the luxurious glass of champagne glistening under the pale arctic sun.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2976
|
videos/HRA_part0/2976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal space setting illuminated by cosmic lights, a brave firefighter in full gear, complete with a helmet and breathing apparatus, stands solemnly beside a wise-looking badger, both participating in a mysterious, otherworldly religious ceremony. The ceremony takes place on a floating platform surrounded by stars, galaxies, and celestial bodies. The scene then shifts underwater, where the firefighter and the badger are swimming gracefully in a clear, tranquil pool, with the firefighter's gear now adapted for aquatic environments. The pool is encircled by ancient, space-themed ruins, giving the impression of an extraterrestrial civilization. Throughout the sequence, the two characters maintain a sense of reverence, as if honoring a sacred tradition in this unique blend of terrestrial heroism, woodland wisdom, and cosmic spirituality.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's face is severely distorted, fingers are deformed, the badger's head is disproportionate, and the video overall does not conform to reality."
}
] |
seed42_1596
|
videos/HRA_part0/1596.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stag strides purposefully across an ancient stone bridge, its antlers framing the scene like natural architecture against a backdrop of lush greenery and a misty morning sky. The deer's confident gait and the bridge's weathered texture tell a story of time and resilience in nature. As it walks, the stag's hooves make soft sounds on the moss-covered stones, creating a harmonious melody echoing through the serene woodland setting. The bridge, arching gracefully over a tranquil stream, becomes a pathway connecting two verdant forests, with the deer serving as a symbol of grace and wildness moving between these spaces.]"
},
{
"from": "gpt",
"value": "Bad. The buck's body is twisted, legs are twisted, and head is twisted."
}
] |
seed44_1232
|
videos/HRA_part1/1232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a well-dressed doctor, wearing a suit and tie, spectacles, and a stethoscope around his neck, playfully floats on a yellow inflatable raft in a clear blue swimming pool. In the background, a mammoth, standing at the edge of the pool, looks on curiously, its massive body shaded by the trees overhead. The doctor's attire remains perfectly neat despite the water, and the mammoth's presence adds an element of surrealism to the otherwise ordinary setting of a backyard pool surrounded by lush greenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2400
|
videos/HRA_part0/2400.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear including a yellow reflective jacket, black helmet, and breathing apparatus, rests his head on his hands atop a wooden table in a dimly lit room. The scene conveys a sense of quiet repose after a night shift, with the firefighter appearing tired yet ready to respond at a moment's notice. His equipment is scattered around him, including a flashlight, gloves, and boots, adding to the realism of the setting. The firefighter's body language suggests exhaustion, as he leans forward with his elbows on the table, seeking solace in a brief moment of rest.]"
},
{
"from": "gpt",
"value": "Good. The firefighter's resting movements in the video are basically normal."
}
] |
seed44_2572
|
videos/HRA_part1/2572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An African elephant, distinguished by its large ears and tusks, is depicted swimming in a serene, reflective body of water under a starlit sky, evoking a sense of tranquility and vastness. The elephant is shown in a three-quarter view, with water droplets visible on its skin, indicating its aquatic activity. The stars above, including the prominent red dot of Mars, twinkle in the dark, clear night sky, providing a cosmic backdrop to the scene. The elephant's trunk is partially submerged, and its eyes are closed, conveying a peaceful, almost meditative state as it floats in the water, encapsulating the unique combination of stargazing and swimming.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2042
|
videos/HRA_part2/2042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a green spacesuit with a clear helmet, stands on an alien planet with vibrant purple foliage and orange skies, holding a tablet displaying educational diagrams. Nearby, a body of water shimmers under the exotic sky, showing aquatic life adapted to this unique ecosystem, swimming gracefully beneath the surface. The teacher occasionally glances up from the tablet to observe the surrounding alien flora and fauna, integrating real-world examples into the lesson. Throughout the scene, the focus remains on the teacher's engagement with the alien environment, using it as a teaching tool, while the colorful, otherworldly landscape provides a captivating backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted in the video, and the animals in the water are also distorted."
}
] |
seed44_2702
|
videos/HRA_part1/2702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, vibrant kitchen filled with the warm glow of overhead lights, a group of four individuals, two men and two women, are energetically washing dishes. One man, wearing a dark green apron over a white t-shirt, vigorously scrubs a pot under running water from a stainless steel sink. Beside him, a woman in a yellow apron laughs as she dries a plate with a colorful cloth. Across the room, another man in a chef's coat rinses glasses, while a woman in a floral apron sorts cutlery, her hands deftly separating forks and spoons. The atmosphere is lively, with steam rising from the sink and the clinking of dishes adding to the symphony of post-meal cleanup.]"
},
{
"from": "gpt",
"value": "Normal. There are two men in the video, not three."
}
] |
seed44_2698
|
videos/HRA_part1/2698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmhand, clad in a khaki shirt, beige trousers, and brown shoes, walks purposefully across a well-kept yard. In the foreground, a vibrant red barn provides contrast against the clear blue sky. The worker pauses, bending down to pick up a lively chicken, its feathers a mix of brown and white, before continuing on his path, the bird calmly tucked under his arm. They stroll together, the worker's gait steady and the chicken seemingly unperturbed, encapsulating the peaceful rhythm of life on the farm.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, head, and body are distorted in the video."
}
] |
seed42_2025
|
videos/HRA_part0/2025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, donning a green jacket, blue jeans, and a gray cap, stands on a ladder propped against the side of a barn, which features a vibrant red exterior and white trim. He is engaged in cleaning the gutters, using a gloved hand to remove debris. The scene is set against a backdrop of lush greenery and a clear blue sky. Moments later, he pauses to survey his work, a pitchfork leaning against the barn wall beside him. The farmer then continues his task diligently, his attire and the pastoral setting creating a vivid image of rural life.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1536
|
videos/HRA_part1/1536.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous nurse, clad in a blue medical scrub top and black pants, stands in a dramatic pose against a vivid, cloudy sky, with a buffalo charging in the background, creating a striking contrast. Moments later, she is shown running swiftly across a grassy field, the buffalo now galloping alongside her in the distance, both set against a backdrop of lush greenery and distant mountains. The nurse's attire remains consistent throughout, consisting of the blue scrub top, black pants, and white sneakers, while the buffalo's powerful form and the natural landscape provide a dynamic setting for this unique scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1928
|
videos/HRA_part1/1928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large, live lobster is displayed prominently in the center of the frame, set against a dark, shadowy background that accentuates its vibrant red shell. The creature's two massive claws are bound by twine, and it rests on a bed of fresh, green seaweed. Its long, segmented body curves slightly, and its many legs are splayed out, giving the impression of strength and vitality. The intricate details of the lobster's textured shell and its small, bead-like eyes are clearly visible in high-definition detail, making this a striking and memorable image.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_136
|
videos/HRA_part0/136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a white martial arts uniform with a red stripe, executes a high kick against a blue sky, showcasing agility and precision. Surrounded by lush greenery, including palm trees and bushes, the scene highlights the contrast between nature and human skill. The artist's ponytail swings during the kick, emphasizing the dynamic motion. Nearby, a wooden fence and a building with a thatched roof add to the tropical setting. Throughout the sequence, the artist maintains a focused gaze, highlighting determination and control.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2745
|
videos/HRA_part2/2745.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform with a black necktie and a tall toque blanche hat, stands on a small wooden stool. He is in the process of changing a light bulb in a restaurant kitchen, surrounded by stainless steel appliances and shelves stocked with cooking utensils. The kitchen is brightly lit, except for the area where the burnt-out bulb needs replacement. The chef, with a slight smile, carefully unscrews the old light bulb, demonstrating a lighthearted moment in his daily routine amidst the professional culinary environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2364
|
videos/HRA_part0/2364.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-looking man with short, dark hair and a trimmed beard focuses intently on repairing a vintage bicycle, his body partially covering the bike's frame. Dressed in a light blue, short-sleeved shirt, khaki pants, and brown work boots, he leans over the bike, which is held upright by a repair stand. His right hand grips a wrench, while his left hand steadies the bike, both hands stained with grease. The scene is set against a backdrop of a cluttered garage filled with various tools and equipment, emphasizing the worker's expertise and dedication to his craft.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_2836
|
videos/HRA_part0/2836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and whimsical scene, a small, cartoonish grey elephant, adorned with a red polka-dotted bow around its neck, is shown mid-jump, its trunk lifted playfully. Against a vivid, clear blue sky, this joyful creature leaps from a lush green meadow dotted with yellow flowers, capturing a moment of pure delight and fantasy. The elephant's large ears are spread wide, adding to the comical effect, while its tiny eyes are closed in sheer happiness, creating a charming and unforgettable visual.]"
},
{
"from": "gpt",
"value": "Normal. The elephant's movements in the video are not smooth."
}
] |
seed46_108
|
videos/HRA_part2/108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique rural setting, a cashier from a local store, dressed in a red apron and black clothing, interacts gently with a brown horse inside a tunnel made of hay bales, creating a warm, intimate atmosphere. The cashier, wearing a red apron over a black outfit, caresses the horse's nose affectionately, with the textured tunnel walls adding depth to the scene. The connection between the cashier and the horse is emphasized by their eye contact, while the rustic tunnel provides a natural, earthy backdrop. Moments later, the cashier, still clad in the red apron and black attire, strokes the horse's mane softly, the bond between human and animal palpable, all within the cozy confines of the hay tunnel.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2613
|
videos/HRA_part0/2613.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, dressed in full gear and helmet, finds himself at the base of a towering space elevator, its sleek silver structure piercing the clouds. Against this futuristic backdrop, he begins to dance, his movements a surprising juxtaposition of grace and strength. The flames from a nearby controlled fire flicker and dance along with him, casting an orange glow on the space elevator's metallic surface. The firefighter's steps are lively and expressive, a mix of joy and determination, as he performs beneath the vast starlit sky, the space elevator standing tall and unwavering behind him.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2496
|
videos/HRA_part1/2496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, green-brown jungle cobra crawls across a lush, moss-covered log in the dense rainforest undergrowth. The snake's hood is slightly raised, revealing its distinctive markings as it navigates the textured surface. Sunlight filters through the canopy, casting dappled light on the cobra, emphasizing its muscular body and smooth scales as it moves with purpose and grace in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2181
|
videos/HRA_part0/2181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A Caspian tern soars gracefully through the air, its large size and robust build evident as it navigates the skies above a serene coastal landscape. With a striking orange-red bill that is thick and strong, this bird exemplifies power and agility. Its plumage is predominantly white, with a faint tinge of grey on the back, and its wings display black tips that contrast beautifully with the rest of its feathers. As it glides over the water, the tern's keen eyes search for prey, showcasing its hunting prowess against the backdrop of a calm sea and a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The Caspian tern's flying movements in the video are not continuous, with abrupt changes."
}
] |
seed46_1891
|
videos/HRA_part2/1891.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling airport terminal, a large, lifelike panda costume lays on its side, partially inflated, as a person inside attempts to crawl into it. The individual struggles comically within the confines of the costume, drawing curious glances from nearby travelers. Once fully inside, the person begins to crawl across the airport floor, the oversized panda head bouncing with each movement, creating a surreal and amusing scene amidst the typical airport chaos. Passengers of all ages watch in amusement, some capturing the unusual sight on their phones, as the person in the panda suit continues to crawl, adding a touch of whimsy to the otherwise ordinary airport environment.]"
},
{
"from": "gpt",
"value": "Normal. The movements of the panda character in the video are not smooth."
}
] |
seed46_2322
|
videos/HRA_part2/2322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Against a backdrop of lush greenery and blue skies, two young boys, one wearing a yellow shirt and the other in red, are intently engaged in fixing a wooden fence. They work diligently, using a variety of tools spread out before them, their faces concentrated and serious as they tackle the task at hand. One boy, dressed in a yellow shirt, blue shorts, and brown shoes, leans against the fence, his hands busy with repair work, while the other, in a red shirt, khaki shorts, and blue sneakers, stands with a tool in hand, ready to assist. The scene captures the industrious spirit of childhood play, with the boys' clothes and tools adding vibrant details to the image.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2117
|
videos/HRA_part2/2117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, a well-dressed lawyer, complete with a suit, tie, and glasses, sits calmly on a wooden bench outdoors. Against a backdrop of lush greenery, the lawyer gently caresses a porcupine, which remains relaxed and quill-free. The lawyer's demeanor suggests a deep connection with nature, particularly with the docile porcupine, which is depicted without its typical defensive quills, highlighting a unique bond between human and animal in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1560
|
videos/HRA_part2/1560.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warbler, a small songbird with yellow-green plumage, perches on a branch, its head turned to the side, revealing its distinct facial markings. It opens its beak to sing, showcasing its natural habitat among lush green leaves. The bird then takes flight, its wings flapping gracefully, before landing on another branch, where it continues its melodious song, surrounded by the vibrant foliage of a tree. Throughout, the focus remains on the warbler's lively movements and distinctive features, set against the backdrop of a verdant forest environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1467
|
videos/HRA_part2/1467.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking beaver, clad in a miniature construction hat and suspenders, jumps enthusiastically over a series of logs arranged like hurdles, against a backdrop of lush greenery. The logs, positioned in a line, serve as obstacles for the beaver to leap over. The scene is set in a vibrant, verdant environment, with the beaver's energetic movements highlighting its industrious nature. As it clears each log, the beaver's determination and agility are evident, showcasing its ability to navigate challenges with agility and grace.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2836
|
videos/HRA_part1/2836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene, a small, cartoonish grey elephant, adorned with a red polka-dotted bow around its neck, is shown mid-jump, its trunk lifted playfully. Against a vivid, clear blue sky, this joyful creature leaps from a lush green meadow dotted with yellow flowers, capturing a moment of pure delight and fantasy. The elephant's large ears are spread wide, adding to the comical effect, while its tiny eyes are closed in sheer happiness, creating a charming and unforgettable visual.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1029
|
videos/HRA_part0/1029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown rat, with patches of white fur, walks methodically across a weathered wooden surface. It pauses momentarily, its whiskers twitching, before continuing its journey. The rat's movements are deliberate, each step calculated, as it navigates the worn planks. Its tail, long and pink, sways gently behind it, adding to the creature's curious demeanor. Throughout the scene, the rat remains the sole focus, walking with purpose on the textured wood, creating a compelling narrative of survival and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The rat in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2894
|
videos/HRA_part2/2894.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy kitchen with wooden cabinets and cream walls, two young children, a boy and a girl, stand on small stools by the sink, their sleeves rolled up. They are happily washing dishes together, the girl scrubbing a plate with a pink sponge, while the boy rinses a glass under the faucet. The room is filled with natural light from a window above the sink, casting a warm glow on the soap bubbles and wet surfaces. A few clean dishes are stacked neatly on a drying rack nearby, and a colorful dishcloth hangs over the tap, completing the scene of domestic harmony and teamwork.]"
},
{
"from": "gpt",
"value": "Bad. The child's face, hands, and arms are distorted in the video."
}
] |
seed44_3093
|
videos/HRA_part1/3093.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 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, 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": "Normal. The cleaner can be clearly seen wiping the glass display table in the video, the actions are basically normal but there is some lack of coordination."
}
] |
seed42_1393
|
videos/HRA_part0/1393.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, wearing a beige jacket, beige pants, and brown shoes, is seen in a close-up shot, wiping his face with a towel, looking exhausted yet determined. Behind him, a kangaroo, possibly a joeey given its smaller size, stands on the lush green grass of what appears to be a vast Australian outback, adding an element of surprise and quirkiness to the scene. The kangaroo's presence suggests an unusual encounter or storyline, while the actor's weary yet resolute demeanor hints at a challenging journey or performance.]"
},
{
"from": "gpt",
"value": "Bad. The actor in the video does not smoothly use the towel to wipe their face, and the movements are uncoordinated."
}
] |
seed44_3220
|
videos/HRA_part1/3220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a janitor, clad in a yellow high-visibility vest and dark pants, walks alongside an antelope in a vast, grassy landscape. The two figures move in unison across the screen, the janitor pushing a red cleaning cart, while the antelope, with its distinctive horns and russet fur, trots gracefully beside him. The scene is bathed in golden sunlight, casting long shadows from both the janitor and the antelope as they traverse the serene environment together. Behind them, a row of tall, green trees provides a striking contrast to the open field, further highlighting the unusual companionship between the janitor and the wild animal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3012
|
videos/HRA_part2/3012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed astronaut chicken, clad in a white spacesuit adorned with American flags and a NASA logo, leaps high into the air on the moon's surface, against a backdrop of a dark, starry sky and the distant Earth. The chicken's joyful jump is captured in mid-air, conveying a sense of weightlessness and adventure. The scene is reminiscent of the historic moon landing, with the chicken's playful leap adding a whimsical touch to the iconic moment. The astronaut chicken's suit includes a transparent helmet, revealing its beady eyes and beak, as it bounces on the lunar surface, encapsulating the spirit of exploration and fun.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the astronaut chicken jumping, but the movements are not very continuous and smooth, showing some coordination issues."
}
] |
seed42_1990
|
videos/HRA_part0/1990.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a majestic raven perched on a branch, its glossy black feathers shimmering under the sunlight, revealing hints of blue and green. The bird has striking yellow eyes that seem to hold a world of wisdom. Its beak is curved and sharp, a testament to its carnivorous nature. The raven is surrounded by lush green foliage, and in the background, misty mountains add to the mystical atmosphere. Occasionally, the raven caws, a deep, resonant sound that echoes through the dense forest, asserting its presence in the serene wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2381
|
videos/HRA_part1/2381.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cormorant, distinguished by its sleek black body, yellow lower mandible, and piercing eyes, is captured mid-flight over a tranquil lake, showcasing its powerful wingspan against the serene waters below. It then perches on a branch, drying its wings, revealing its unique ability to spread its feathers. Next, the bird plunges into the water, its form streamlined as it hunts beneath the surface, demonstrating its aquatic prowess. Finally, it emerges victorious, a small fish clasped in its beak, highlighting its hunting skills in the wild. Throughout, the cormorant's natural habitat, from the calm lake to the surrounding foliage, is depicted in vivid detail.]"
},
{
"from": "gpt",
"value": "Bad. The cormorant's wings and body deform and become distorted when flapping. And at one point, two heads appear."
}
] |
seed42_1350
|
videos/HRA_part0/1350.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European badger, with its distinct black and white striped face and grey fur, walks purposefully across a lush, green meadow under the dappled shade of tall trees. It pauses for a moment, standing on all fours, to sniff the air with its keen sense of smell. Then, it continues its journey, moving with a slight waddle due to its sturdy build, leaving behind a trail in the soft grass. The scene is set in the peaceful serenity of nature, with the badger as the sole focus, highlighting its natural habitat and behavior.]"
},
{
"from": "gpt",
"value": "Normal. The facial proportions of the Eurasian badger in the video are not quite right."
}
] |
seed44_2210
|
videos/HRA_part1/2210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 innovative engineer, adorned in a spacesuit and helmet, stands on the lunar surface, illuminated by the Earth's glow, holding a leash attached to a lion. The lion, also wearing a miniature spacesuit and helmet, jumps playfully in the low gravity environment. Both figures cast long shadows against the moon's dusty terrain, with the Earth shining brightly in the dark, star-studded sky. This surreal scene combines elements of space exploration, wildlife, and human ingenuity in a single captivating frame.]"
},
{
"from": "gpt",
"value": "Bad. The lion is not wearing the same helmet and spacesuit, and there are two lions."
}
] |
seed44_1642
|
videos/HRA_part1/1642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man dressed in a brown jacket and beige pants is seen crawling on his hands and knees through a lush, green forest, with ferns and mossy rocks surrounding him. Moments later, a large moose with a majestic rack of antlers stands tall and vigilant nearby, observing the man's unusual behavior. The scene then focuses on the man's face, showing his determination and focus, while the moose continues to watch from a distance, its presence adding a sense of wildness and unpredictability to the forest setting. Finally, the man and the moose share a silent moment of connection, both existing in harmony within the natural world, the man still crawling and the moose standing tall, creating a unique and unexpected encounter in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1141
|
videos/HRA_part0/1141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a blue shirt and khaki pants, stands in the center of a large, old theater, animatedly teaching a lesson about running. The stage is set with props from various plays, adding a touch of theatricality. Suddenly, a dingo, a wild dog native to Australia, runs onto the stage, interrupting the class. The teacher, unperturbed, incorporates the unexpected guest into the lesson, demonstrating running techniques while the dingo playfully bounds around, all under the grand chandelier of the theater.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1170
|
videos/HRA_part1/1170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, prehistoric landscape under a warm, golden sunlight, a large, woolly mammoth tenderly caresses a smaller mammoth with its trunk. The older mammoth, distinguished by its size and thick, matted fur, reaches out with its trunk to touch and comfort the younger one, which stands close by. The younger mammoth, with less dense fur and a more compact frame, leans into the touch, creating a touching scene of familial bond. Both mammoths stand against a backdrop of green vegetation and distant hills, with the younger mammoth mirroring the older one's grayish-brown coloration, highlighting their connection in this ancient, verdant setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2338
|
videos/HRA_part2/2338.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an assortment of smaller fish. The grouper, distinguished by its size and spotted brown skin, explores its surroundings with a sense of ownership, occasionally pausing to inspect something of interest. Its powerful body and broad fins propel it through the crystal-clear waters, showcasing the serene beauty of life beneath the ocean's surface.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the grouper's body and head twisted."
}
] |
seed44_1527
|
videos/HRA_part1/1527.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, dressed in a formal black suit, white shirt, and red bow tie, is seen walking side by side with a kangaroo in an urban cityscape. Both figures move with purpose down the street, the musician holding his violin case, while the kangaroo carries a small backpack. They navigate past various city elements, including fire hydrants, street signs, and a yellow cab, blending into the urban environment with an air of normalcy. The scene is framed by a cloudy sky and the tops of buildings, creating a surreal yet harmonious image of these unlikely companions on their shared journey.]"
},
{
"from": "gpt",
"value": "Bad. The musician and the kangaroo in the video walk very unsmoothly, with uncoordinated movements."
}
] |
seed42_2183
|
videos/HRA_part0/2183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a yellow vest and khaki pants, takes a break from cleaning the vast, empty stadium to joyfully dance alone under the bright lights. With a mop in his right hand and a bucket nearby, he moves across the polished concrete floor, surrounded by rows of blue seats. The overhead view captures his spontaneous dance moves, highlighting the contrast between his work and play in the expansive, quiet stadium. His movements, set against the backdrop of the stadium's architecture and the night sky visible through the open roof, convey a sense of freedom and self-expression.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_214
|
videos/HRA_part1/214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young college student, casually dressed in a white T-shirt and blue jeans, diligently paints a room with bright yellow walls, focusing on a corner where two walls meet. The room is filled with natural light from a nearby window, illuminating the student's task. They wear protective goggles and a face mask, ensuring safety while working. The student is surrounded by painting supplies, including a ladder, paint cans, and brushes, indicating a thorough preparation for the project. As the camera pans out, we see the student's friends in similar attire, contributing to the painting effort, fostering a sense of camaraderie and teamwork in transforming the space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_1812
|
videos/HRA_part1/1812.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, recognized by her messy red hair and paint-splattered white apron over a yellow dress, scrubs the bathroom floor with vigor, her face expressing determination. She uses a green scrub brush and a blue bucket filled with soapy water, set against a backdrop of white tiles. The scene conveys the juxtaposition of creativity and mundane chores, as she kneels on the floor, her hands stained with dirt and her sleeves rolled up, highlighting the physical effort involved in cleaning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.