video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2509
|
videos/HRA_part2/2509.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, wearing a gray shirt and blue jeans, is seen laughing heartily, holding a black electric guitar. The scene is set against a dark background with bright, colorful lights illuminating the musician from behind, adding a vibrant touch to the joyful moment. The musician's laughter is contagious, creating a warm and inviting atmosphere that captures the essence of pure happiness and the love for music.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1646
|
videos/HRA_part0/1646.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a brown jacket over a green shirt, leans over the railing of a pier to fish, with a small fishing rod in hand and a yellow bucket by his side. He is seen from behind, gazing intently into the water, the sun reflecting off his balding head and casting a warm glow on his upturned face. The pier is old and weathered, with faded paint and worn wooden planks, and the water below is calm and clear, dotted with the occasional ripple from a fish. In the distance, a city skyline can be seen, its tall buildings silhouetted against the bright blue sky, providing a stark contrast to the peaceful scene unfolding on the pier.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_3055
|
videos/HRA_part1/3055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush green meadow, two majestic moose gently caress each other with their large, velvety noses, expressing tenderness and affection. They stand side by side, their dark coats contrasting beautifully against the vibrant flora surrounding them. One moose looks intently at its companion, while the other closes its eyes, savoring the intimate moment. Their antlers, impressive and intricate, frame their faces as they share this loving gesture, all captured in stunning high definition. The background is a harmonious blend of nature, with tall grass swaying gently in the breeze, creating a peaceful and idyllic setting for this touching wildlife interaction.]"
},
{
"from": "gpt",
"value": "Bad. The nose of the moose on the right in the video is problematic, and the antlers of the moose on the left are missing."
}
] |
seed44_278
|
videos/HRA_part1/278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clear, close-up underwater shot, a tiny ghost shrimp, nearly transparent with faint grayish-blue hues, scuttles along the sandy bottom of a freshwater environment. Its delicate, see-through body reveals its intricate internal structure, while its antennae and legs move rapidly as it navigates its habitat. Surrounded by small stones and plant roots, the shrimp pauses momentarily before continuing its journey, showcasing its unique ability to blend into the aquatic surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The ghost shrimp walks basically normally, but there is slight uncoordination in the movements."
}
] |
seed42_2323
|
videos/HRA_part0/2323.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, identifiable by his gray lab coat over a casual button-up shirt and jeans, gently bathes a small, fluffy white dog in an elevated washbasin typically used for washing cars. The scene is set outdoors, with the dog standing on its hind legs, paws on the basin's edge, and the engineer tenderly pouring water over its head from a white jug. The engineer's caring demeanor contrasts with his professional attire, creating a heartwarming image of an unexpected task being performed with love and care.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the dog standing on its hind legs with its paws on the edge of the basin."
}
] |
seed44_1433
|
videos/HRA_part1/1433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid scene, two children, a boy and a girl, sprint across a grassy area with wide smiles, dressed in casual play clothes—a red T-shirt and blue shorts for the boy, and a floral dress for the girl. Suddenly, the focus is on the boy as he runs with gleeful determination. Then, the girl takes center stage, her pigtails bouncing as she races forward. The action culminates with both children laughing and running together, their eyes filled with joy, all while a gorilla statue stands watchfully in the background, adding a touch of whimsy to the playful atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1032
|
videos/HRA_part0/1032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge, cap, and sunglasses, stands at the edge of a zoo's flamingo enclosure, where vibrant pink birds congregate. The scene shifts slightly to reveal a clear blue pool within the zoological park, where the officer now interacts with the public, demonstrating water safety techniques. Nearby, children and families watch, some seated on benches under the shade of lush trees, while others lean on the railing, observing the swimming demonstration with interest. Throughout, the police officer remains engaged and attentive, fostering a sense of community and safety among the zoo visitors.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video, as well as the flamingo's neck."
}
] |
seed44_311
|
videos/HRA_part1/311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 high-visibility vest over a gray jacket, khaki cargo pants, and black shoes, rests his head on his right arm, which is propped on a mop handle. He leans against a wall, his body language conveying exhaustion, as he takes a nap beside a bucket and cleaning supplies, all bathed in dim light. Moments later, the scene subtly changes, showing him still asleep, now with his left hand resting on his forehead, while the bucket and cleaning tools remain nearby. This sequence captures the quiet solitude and hard work of a janitor during his brief respite.]"
},
{
"from": "gpt",
"value": "Normal. The scene does not show the man resting his right arm on the mop handle."
}
] |
seed46_1148
|
videos/HRA_part2/1148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diligent male worker, clad in a green jacket, dark pants, and brown gloves, meticulously rakes a large pile of autumn leaves in the foreground, creating a tidy heap. Behind him, a vast expanse of fallen leaves covers the grassy area, extending into the distance. The scene is set in a spacious backyard surrounded by a wooden fence, with a row of mature trees framing the horizon. As the worker continues to rake, the pile of leaves grows larger, highlighting the laborious task at hand. Throughout the process, the worker maintains a focused demeanor, his movements methodical and efficient, embodying the essence of hard work and determination.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2298
|
videos/HRA_part0/2298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, industrial warehouse space filled with rows of neatly stacked boxes, a doctor, identifiable by her stethoscope draped around her neck and wearing a white lab coat over a blue shirt, performs an unexpected action. She leaps into the air with an expression of pure joy, her feet leaving the ground, and her arms spread wide, capturing a moment of uninhibited happiness amidst the sterile environment. The high-definition shot captures the contrast between the clinical setting and the doctor's spontaneous act of exuberance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1309
|
videos/HRA_part1/1309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a yellow fire-resistant jacket, leads a calm brown horse into a shallow, clear lake during a sunny day. The firefighter gently guides the horse, which is adorned with a red blanket, into the water. Both the firefighter and the horse are knee-deep in the refreshing lake, surrounded by lush greenery and a peaceful environment, creating a heartwarming and unexpected scene of tranquility.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's arm is twisted, the hand is twisted, the face is distorted, the horse's legs are twisted, and the face is slightly deformed."
}
] |
seed42_1503
|
videos/HRA_part0/1503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor, wearing a white lab coat, blue shirt, and khaki pants, gently caresses a small, brown squirrel nestled in her hands. The scene is set in a cozy, well-lit room with wooden floors, where the doctor, sporting a ponytail, glasses, and a warm smile, tenderly holds the squirrel. The focus is on the interaction between the caring medical professional and the tiny creature, emphasizing the nurturing bond formed in this peaceful environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's hands and the head of a squirrel are generated abnormally."
}
] |
seed46_2688
|
videos/HRA_part2/2688.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 experienced engineer, clad in a yellow hard hat, safety glasses, and a blue uniform, stands amidst the towering structures and pipelines of an oil refinery complex. He is seen wiping his hands on a cloth, perhaps after completing a task, with the industrial landscape of the facility stretching behind him. The scene captures the essence of hard work and maintenance in the heart of the oil industry.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2726
|
videos/HRA_part2/2726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh cod fish is presented on a bed of ice, its body a pristine silver with a distinctive dark spot pattern. The fish's eyes are bright and clear, indicating freshness, while the gills are a vivid red. The scene is set in a bustling fish market, with other varieties of seafood visible in the background, adding to the atmosphere of a vibrant marketplace. The focus remains on the cod, emphasizing its quality and size, perfect for a gourmet meal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1011
|
videos/HRA_part1/1011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a film director, clad in a beige jacket, navy-blue shirt, and brown trousers, kneels on the floor of an art gallery, observing a taxidermied beaver. The setting is an exhibition space filled with various artworks, including paintings and sculptures. The director's intent gaze and body language suggest deep engagement with the beaver specimen, which is placed on a pedestal among other natural history exhibits. The camera captures this curious interaction from multiple angles, highlighting the director's fascination and the eclectic atmosphere of the gallery.]"
},
{
"from": "gpt",
"value": "Bad. The director's movements in the video are not smooth and coordinated."
}
] |
seed46_139
|
videos/HRA_part2/139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, dressed in a green shirt and black pants, kneels in a grassy outdoor setting, intently observing a small brown hedgehog. The hedgehog, rolling into a ball and uncurling repeatedly, captures the director's attention as it explores its surroundings. Suddenly, the hedgehog leaps into the air, its spines gleaming in the sunlight, while the director watches with fascination, camera in hand, ready to capture this unexpected moment of agility against a backdrop of lush greenery.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2851
|
videos/HRA_part0/2851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown monkey walks purposefully across a lush green forest floor, sunlight filtering through the dense foliage above, casting dappled shadows on the ground. The monkey, with its fur ruffled by a gentle breeze, carries a small object in its mouth, possibly food, as it navigates the underbrush with agile movements. Its eyes, alert and curious, scan the surroundings, showcasing its adaptability in the wild. The scene is set against a backdrop of verdant vegetation, with the occasional sound of rustling leaves and chirping birds adding to the natural ambiance.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the monkey in the video are missing, and the face generation is blurry."
}
] |
seed46_2247
|
videos/HRA_part2/2247.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating scene, a janitor in a space museum is seen cleaning near a large, detailed model of the International Space Station, which is submerged in a serene indoor pool. Wearing a yellow vest, gray pants, and a white shirt, he carefully maneuvers around the underwater exhibit, highlighting his unique cleaning duties. The water around him is crystal clear, allowing viewers to appreciate the intricate details of the space station replica. As he works, the ambient lighting from above gently illuminates the water, creating a mesmerizing visual effect that blends the worlds of space exploration and aquatic tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's movements in the video are uncoordinated."
}
] |
seed42_2798
|
videos/HRA_part0/2798.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A badger, typically terrestrial, is shown swimming in a serene lake under a cloudy sky, creating a rare and captivating scene. Its body, adapted for digging, moves surprisingly gracefully through the water, showcasing its unexpected aquatic abilities. The badger's head, with distinctive black and white stripes, breaks the water surface as it propels itself forward with powerful strokes, leaving ripples across the calm lake. Surrounding trees and foliage frame the peaceful setting, highlighting the unusual yet mesmerizing sight of this normally land-dwelling creature taking to the water.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2238
|
videos/HRA_part2/2238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a costumed firefighter, clad in full gear and a helmet, is engaging in a lively dance on a vibrant green stage. Accompanying him is a person dressed as a colorful lizard, both moving energetically to an unseen beat. The firefighter's hose is coiled at their feet, adding to the whimsical juxtaposition of elements. The lizard, with its detailed costume, sways in sync, creating an unexpected duo in a performance that blends heroism and fantasy in a dazzling display of dance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1131
|
videos/HRA_part0/1131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a black leather jacket and jeans, pulls vigorously on the strings of an electric violin, his face contorted in intense concentration. The scene is set against a dark, moody backdrop, illuminated only by the warm glow emanating from the instrument. Close-ups capture the intricate movements of his fingers, adorned with silver rings, as they dance across the fretboard. The energy is palpable, as if the very essence of the music is being channeled through him, creating an electrifying performance that captivates the viewer.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1187
|
videos/HRA_part0/1187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, clad in dark attire with a badge and hat, interacts with a large, gray elephant at a beachside location, both standing near the water's edge. The elephant, with its distinctive tusks and wrinkles, playfully splashes water with its trunk, while the officer watches with an amused smile. In another scene, the officer gently pats the elephant's head, which is dripping with water, suggesting they have been swimming together. Lastly, the duo is captured in a heartwarming moment, with the officer and the soaking-wet elephant sharing a tender interaction against the serene backdrop of a sandy shore and the vast ocean.]"
},
{
"from": "gpt",
"value": "Bad. The elephant's action of playing with its trunk and splashing water is basically normal."
}
] |
seed42_1294
|
videos/HRA_part0/1294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a red jacket and black cap, ascends a rocky cliff face with intense concentration, showcasing determination against a dramatic, cloudy sky. He pauses to rest, surveying the landscape below, revealing a secluded cabin surrounded by dense forest, hinting at his remote writing retreat. Continuing his ascent, he reaches for a sturdy rock hold, highlighting his physical strength and mental fortitude. At the summit, he pauses to write in a small notebook, capturing inspiration from the vast, misty valley below, embodying the adventurous spirit of an author seeking solitude and muse.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1239
|
videos/HRA_part2/1239.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 larger size and ears shaped like the continent, walks through an unexpected environment - an industrial zone. Its massive body moves with surprising grace among warehouses with corrugated metal roofs, concrete walls, and large steel containers. The elephant's gray skin, wrinkled and textured, contrasts sharply with the man-made structures. It strides on paved roads, passing by utility poles and electrical wires, creating an unusual juxtaposition of nature and industry. Despite the urban surroundings, the elephant maintains its majestic presence, walking with a purposeful gait, its trunk swaying gently as it navigates through this industrial landscape.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not coordinated, the actions are not continuous."
}
] |
seed42_1751
|
videos/HRA_part0/1751.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a blue striped shirt and khaki pants, is seen in a backyard, carefully washing a small brown dog with a hose. The dog, standing on a white table, looks content as the teacher, wearing rubber gloves, gently scrubs its fur with a sponge. The scene is set against a backdrop of green grass and a wooden fence, creating a peaceful and nurturing environment. The teacher's caring demeanor and the dog's relaxed stance convey a sense of trust and affection between them, making for a heartwarming moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1559
|
videos/HRA_part1/1559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a crisp uniform consisting of a navy blue shirt, matching trousers, and a peaked cap, is engaged in an unusual task inside a busy restaurant district. He is meticulously wiping down a row of outdoor tables, each set with white tablecloths and surrounded by patrons enjoying their meals. The backdrop features a variety of restaurants, ranging from elegant dining establishments to casual eateries, all bustling with activity. The scene captures the unexpected sight of law enforcement taking on a service role, contributing to the cleanliness and ambiance of the dining area.]"
},
{
"from": "gpt",
"value": "Normal. The officer's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2980
|
videos/HRA_part1/2980.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, dressed in a brown jacket, beige pants, and brown boots, stands on a dirt floor, meticulously wiping a wooden table with a cloth. The scene takes place in a large, open arena, filled with wooden tables and chairs, reminiscent of a medieval feast setting. Sunlight filters through the high windows, casting a warm glow over the space. The man's focused gaze and the repetitive motion of his hand convey a sense of purpose and care in his task, set against the vastness of the arena.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video wiping the wooden table is basically normal, but there is slight uncoordination in his movements."
}
] |
seed44_1808
|
videos/HRA_part1/1808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small gerbil, with a brown and white coat, leaps energetically from one wooden platform to another within its cage, demonstrating agility and speed. The rodent lands on a branch, its furry tail swaying, before it jumps again, this time onto a spinning wheel. It pauses for a brief moment, standing upright on the wheel with its front paws raised, before continuing to jump and explore its habitat. Throughout the scene, the gerbil's movements are captured in high detail, highlighting its playful nature and lively spirit.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's body is twisted, and its paws are twisted."
}
] |
seed44_224
|
videos/HRA_part1/224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, rustic market, a young female cashier, wearing a green apron with a name tag reading \"Ibex,\" diligently wipes down the countertop with a cloth. The wooden cash register stand is adorned with a small flower pot and a framed picture, adding a personal touch to the space. Ibex works efficiently, her movements confident and practiced, as she cleans the area where customers place their items for purchase. The background features shelves stocked with various goods, giving a glimpse into the variety of products available in the store.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2324
|
videos/HRA_part1/2324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, embodying the essence of carefree summer days, walks along a pristine beach with white sand, wearing a vibrant floral shirt, khaki shorts, and brown leather sandals. He gently caresses the smooth, sun-warmed surface of a driftwood log, as the crystal-clear turquoise waters of the sea softly lap at the shore behind him. The serene beach landscape, with lush greenery and palm trees framing the horizon, complements the peaceful atmosphere. The man's relaxed posture and the idyllic beach setting evoke a sense of tranquility and connection with nature.]"
},
{
"from": "gpt",
"value": "Normal. The man's walking action in the video is basically normal, with slight disharmony."
}
] |
seed44_1279
|
videos/HRA_part1/1279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a sharp charcoal suit and red tie, leisurely walks down a bustling boardwalk at a luxurious seaside resort. With the soothing sound of waves in the background and the sun casting a warm glow, he strolls past vibrant shops and cafes. His polished leather shoes step on the wooden planks of the boardwalk, while vacationers and resort staff pass by, creating a lively atmosphere. The lawyer's confident demeanor and tailored attire stand out against the casual beachside setting, offering a glimpse into his balanced life between work and leisure.]"
},
{
"from": "gpt",
"value": "Bad. When walking, the person's feet become deformed."
}
] |
seed46_296
|
videos/HRA_part2/296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a dark suit, white shirt, and blue tie, finds himself inexplicably transported to a different era, reminiscent of the TV show 'Quantum Leap.' Crawling through a dimly lit, gritty tunnel, he struggles to understand his time-bending predicament. The tunnel walls are adorned with graffiti and debris, adding to the disorienting atmosphere. Suddenly, the lawyer emerges into a bustling courtroom from the past, where he must now navigate unfamiliar legal challenges. His bewildered expression and the stark contrast between his modern attire and the vintage courtroom setting underscore the surreal nature of his quantum leap experience.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's face is blurry and the hands and feet are deformed in the tunnel; the lawyer's face is disproportionate in the courtroom."
}
] |
seed46_1040
|
videos/HRA_part2/1040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene set against the backdrop of a bustling harbor, a snake charmer dressed in traditional attire, complete with a red turban and colorful vest, plays an enchanting melody on his pungi. The cobra, coiled and alert, rises from its basket, swaying hypnotically to the music under the golden glow of the setting sun. The charmer's skilled hands guide the snake into a mesmerizing dance, captivating the audience gathered around the harbor, where boats gently rock in the water and seagulls circle overhead. The cobra's movements, synchronized with the charmer's music, create a powerful display of control and grace against the maritime setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2504
|
videos/HRA_part1/2504.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated doctor, clad in a white lab coat and protective goggles, embarks on an extraordinary adventure, crawling through a meticulously detailed, space-themed diorama. This unique setting features a realistic comet in pursuit, depicted through dynamic lighting and visual effects, creating an engaging narrative. The doctor, equipped with a futuristic tool kit, exhibits determination and focus, navigating the challenging terrain with precision. The comet, represented by a meticulously crafted model, trails closely behind, adding a thrilling element to the scene. Throughout the video, the doctor's journey is portrayed with a blend of scientific curiosity and cosmic wonder, set against a backdrop of meticulous craftsmanship and vivid imagination.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's movements in the video are not smooth."
}
] |
seed42_278
|
videos/HRA_part0/278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clear, close-up underwater shot, a tiny ghost shrimp, nearly transparent with faint grayish-blue hues, scuttles along the sandy bottom of a freshwater environment. Its delicate, see-through body reveals its intricate internal structure, while its antennae and legs move rapidly as it navigates its habitat. Surrounded by small stones and plant roots, the shrimp pauses momentarily before continuing its journey, showcasing its unique ability to blend into the aquatic surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The ghost shrimp in the video are deformed, with missing claws and eyes not generated."
}
] |
seed42_1570
|
videos/HRA_part0/1570.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with advanced equipment, a dedicated scientist, wearing a white lab coat over a dark shirt and jeans, gently caresses a sophisticated device used in dark matter research. The scientist, sporting short hair and glasses, exhibits a deep connection with the apparatus, conveying the tender care required in handling delicate scientific instruments. The background features a complex arrangement of machinery and computer screens, highlighting the cutting-edge nature of the research being conducted. This intimate interaction between the researcher and the technology underscores the human element in the pursuit of understanding the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Normal. The scientist's fingers in the video are not fully generated, and there are issues with the generation of the eyes and mouth."
}
] |
seed42_2777
|
videos/HRA_part0/2777.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a doctor, wearing a white lab coat and stethoscope, stands in a spacious, brightly lit room. Suddenly, a majestic lion jumps into the frame from the right, landing gracefully on its hind legs. The doctor, unfazed, calmly observes the lion, who is leaping with its front paws extended and mouth slightly open, displaying its sharp teeth. Both the doctor and the lion are framed against a neutral, light background, emphasizing the unusual yet harmonious interaction between these two characters.]"
},
{
"from": "gpt",
"value": "Normal. The lion's movements in the video are not smooth."
}
] |
seed44_2500
|
videos/HRA_part1/2500.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visually stunning scene, an ibex is depicted crawling across a rocky landscape, as if experiencing time dilation, where time appears to slow down from the perspective of an observer. The ibex, with its distinct curved horns, moves deliberately over the rugged terrain, emphasizing the surreal sensation of time distortion. The camera captures this unusual sight in high detail, highlighting the ibex's textured fur and the stark, rocky environment, creating a captivating juxtaposition between the animal's natural agility and the slowed-down, almost meditative pace of its movement.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1189
|
videos/HRA_part0/1189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, softly lit room, two young girls sit on a large, colorful rug, engrossed in crocheting a vibrant patchwork blanket. One girl, with short brown hair, wears a yellow T-shirt and blue jeans, focusing intently on her work. Beside her, a girl with long blonde hair, dressed in a pink dress, stitches away with determination. The room is filled with an array of yarn balls in various colors, scattered around them, and a white wooden table stands nearby, holding a cup of crayons and a half-finished coloring book, hinting at other creative activities. The atmosphere is warm and nurturing, with the girls' concentration and the colorful surroundings creating a scene of creativity and companionship.]"
},
{
"from": "gpt",
"value": "Bad. The little girl's hand is twisted, and her face is distorted."
}
] |
seed42_2966
|
videos/HRA_part0/2966.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a gray hoodie and khaki pants, walks alongside a camel in a desert landscape. The sun casts long shadows, highlighting the serene connection between the two. The student, wearing a backpack and a wide-brimmed hat, looks thoughtful as they journey together. The camel, adorned with vibrant red and orange textiles, ambles along gracefully, its large, expressive eyes gazing ahead. Together, they traverse the sandy dunes under a vast, cloudless sky, embodying a sense of adventure and exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_3196
|
videos/HRA_part1/3196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, wearing a black tank top, dark jeans, and a silver necklace, stands against a backdrop of a sandy beach and clear blue skies. He jumps into the air, guitar in hand, against the stunning landscape of palm trees and a pristine shoreline. His silhouette is highlighted by the golden hour sunlight, casting a warm glow over the scene. The camera captures the moment of mid-air suspension, emphasizing the dynamic energy of the performance, with the tranquil beach serving as a picturesque contrast to the vibrant action.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1771
|
videos/HRA_part2/1771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, equipped with a duty belt and a radio, is seen kneeling on a polished wooden floor in a residential setting, attentively wiping the muddy paws of a large, brown dog. The officer wears a serious expression, focused on the task at hand, ensuring the canine's paws are clean. The environment is warm and welcoming, with a Christmas tree in the background, decorated with colorful ornaments and lights, adding a festive touch to the scene. The officer's careful actions and the presence of the holiday decorations create a sense of care and community during the holiday season.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2369
|
videos/HRA_part2/2369.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a yellow shirt and blue jeans stands on a wooden chair, her right hand holding a new light bulb, her left hand unscrewing the old one. She has short brown hair and wears glasses, her face showing concentration as she works against a background of a white ceiling and pale green walls. Moments later, she screws in the new bulb, her tools, a screwdriver and pliers, rest on the chair next to her. The room is sparsely furnished, featuring a wooden table and chairs, and a window covered by white curtains, as she completes her task with skill and determination.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand and arm undergo deformation and mutation, and the light bulb and screwdriver in her hand suddenly disappear."
}
] |
seed46_1799
|
videos/HRA_part2/1799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green meadow under a partly cloudy sky, a majestic stag stands tall, its large, expressive eyes gazing into the distance. It shakes its head vigorously, sending droplets of water flying from its fur. The stag, with its impressive antlers and auburn coat, continues to shake itself dry after what seems to have been a refreshing drink from a nearby stream. The rolling hills and scattered trees provide a serene backdrop, emphasizing the beauty and tranquility of nature. As it finishes drying off, the deer looks around, alert and aware, before returning to its peaceful grazing.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2180
|
videos/HRA_part1/2180.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast school of silver sardines elegantly maneuvers through the clear blue ocean, their synchronized movements creating mesmerizing patterns as they navigate around a large, rocky coral reef structure. Sunlight filters through the water, illuminating the fish and highlighting their metallic scales against the vibrant coral and lush underwater flora. The sardines' fluid dynamics and the contrast between their silvery bodies and the colorful marine environment create a stunning visual display in the depths of the sea.]"
},
{
"from": "gpt",
"value": "Normal. The video shows too many silver mysid shrimps, and their bodies are not fully generated."
}
] |
seed44_2790
|
videos/HRA_part1/2790.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and a helmet, walks alongside a majestic jaguar in a surreal scene. Both stride purposefully on a dirt path, the wild cat's spots contrasting with the firefighter's bright orange suit. The setting sun casts a golden glow, highlighting the unusual pair as they move together, the jaguar's powerful form and the firefighter's protective stance forming an unforgettable image. The firefighter's heavy boots and the jaguar's confident gait are in sync, creating a unique bond between human and beast in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Normal. The video shows firefighters walking alongside a jaguar, with basically normal movements, but there is some lack of coordination."
}
] |
seed44_3190
|
videos/HRA_part1/3190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, pristine oyster rests on a bed of ice, its shell partially open to reveal a lustrous interior. The oyster is large and plump, with a deep cup that holds a pool of clear, briny liquid. Its exterior shell is rough and textured, with shades of gray and brown that contrast sharply with the icy base. A fork and lemon wedge are placed nearby, ready for someone to savor the fresh, oceanic flavors of this exquisite seafood delicacy, all captured under crisp, high-definition lighting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2830
|
videos/HRA_part2/2830.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic cityscape illuminated by neon lights, a waiter dressed in a sleek, silver apron over a black uniform walks purposefully across a crowded outdoor plaza filled with diverse patrons enjoying their meals. Behind him, an AI pilot, recognizable by its advanced humanoid form with a polished metallic exterior and glowing blue eyes, strides confidently, carrying what appears to be a flight helmet under its arm. Both figures navigate through the bustling scene, the waiter balancing a tray laden with exotic dishes, while the AI pilot's movements are precise and efficient, highlighting the seamless integration of technology and service in this high-tech environment.]"
},
{
"from": "gpt",
"value": "Normal. The server's eyes and the customers in the outdoor square are generated abnormally."
}
] |
seed44_1712
|
videos/HRA_part1/1712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinctive black markings, perches on a stone statue in the middle of a bustling city square. It has a full, rounded body, and its wings are slightly spread, revealing a flash of green and purple iridescence near the base. Its head, adorned with a small red beak, turns to face the camera, displaying its alertness and curiosity. The bird's legs, pink and sturdy, grip the statue firmly, while its red eyes, surrounded by yellow orbital rings, watch the surroundings keenly. The pigeon is set against a backdrop of urban life, with pedestrians, buildings, and traffic providing a sense of scale and context.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2549
|
videos/HRA_part0/2549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 actor, wearing a beige jacket and dark trousers, sits on a wooden dock by the water's edge. He gently caresses a small, curious otter that has climbed onto his lap, looking into its eyes with a warm smile. The otter, with its sleek brown fur and bright, inquisitive gaze, seems comfortable and at ease in the actor's presence. The scene is set against a serene backdrop of gently lapping waves and lush greenery, capturing a tender moment between human and animal in a peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2672
|
videos/HRA_part1/2672.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-groomed doctor, complete with a stethoscope around his neck and wearing a white lab coat over a button-down shirt and slacks, is seen cleaning a large aquarium. The doctor, who has a neatly trimmed beard, carefully cleans the glass of the fish tank with a squeegee, revealing the clear water and colorful fish inside. The room is modern and clean, with white walls and a tiled floor, and there's a large window allowing natural light to illuminate the space. The fish tank, which houses various species of tropical fish, is the centerpiece of the room, and the doctor's meticulous care for it highlights his attention to detail and compassion for living creatures.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3087
|
videos/HRA_part1/3087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a full-body, realistic coyote costume, performs an interpretive dance against a dark backdrop. The costume features intricate details, including fur texture and realistic facial features, as the artist embodies the coyote's movements. The dance is expressive and fluid, conveying the essence of the coyote's wild nature. The artist's commitment to the performance is evident in the graceful and emotive gestures, all captured under dramatic stage lighting that highlights the costume's texture and the intensity of the dance.]"
},
{
"from": "gpt",
"value": "Normal. The arm of the artist playing the coyote in the video has generation issues."
}
] |
seed44_140
|
videos/HRA_part1/140.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitorial worker, clad in a crisp, light blue uniform shirt and black pants, meticulously rearranges furniture in a spacious, modern office during the daytime. He lifts a wooden chair with a green seat cushion, revealing a clean, polished floor beneath. Next, he pushes another chair into place, aligning it perfectly with the desk. Then, he adjusts a sleek, white office table, ensuring it is straight and centered. Finally, he steps back, hands on hips, surveying his work with a sense of pride and accomplishment, the room now neatly organized and ready for use.]"
},
{
"from": "gpt",
"value": "Bad. A chair in hand suddenly disappears. A third arm appears on a person at one moment. The legs also become deformed."
}
] |
seed44_1696
|
videos/HRA_part1/1696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a middle-aged doctor, wearing a stethoscope around his neck and a crisp white lab coat over his neatly pressed blue scrubs, finds himself unexpectedly dancing in a vast savanna. As he moves with surprising grace, a curious cheetah, intrigued by the unusual sight, approaches cautiously from the tall grass. The big cat, known for its speed and agility, mirrors the doctor's dance steps, its movements fluid and powerful. The unlikely pair continues their impromptu dance, surrounded by the vast, open landscape, creating a surreal and captivating moment captured in high-definition footage.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2444
|
videos/HRA_part2/2444.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with a round face, brown hair styled in a bun, and wearing a gray top is seen sitting alone, her eyes welling up with tears that stream down her cheeks. She looks lost in thought, her gaze distant, as she holds a tissue in her right hand. Moments later, she wipes away her tears with the tissue, her emotions visible in her expressive face. Then, she is captured in a close-up, her eyes closed, a tear rolling down her cheek, her lips slightly parted, as she seems to be taking a deep breath. Lastly, she looks directly at the camera, her eyes filled with unshed tears, her cheeks flushed, conveying a sense of vulnerability and strength in her emotional state.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1271
|
videos/HRA_part2/1271.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a yellow high-visibility vest and dark pants, diligently wipes a glass window with a cloth in a bustling mall food court. Amidst the vibrant setting, complete with a McDonald's restaurant and various retail stores in the background, he pauses to assess his work. With determination, he continues wiping the glass surface, ensuring it remains clean and clear. Throughout, the dynamic environment of the mall is evident, from the diverse crowd to the commercial signage, yet the focus remains on the janitor's meticulous efforts.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_2217
|
videos/HRA_part2/2217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed writer, wearing a gray t-shirt, sits at a desk in a modern, minimally decorated room with large windows and a wooden floor, yawning widely as he leans back in his chair. The room is sparsely furnished, featuring a desk lamp and a painting on the wall. As the scene progresses, the yawning writer, now seen from the side, wears a black cap and glasses, revealing more of his appearance. He continues to yawn, appearing tired yet relaxed, as he rests his head on his hand, gazing out the window. Throughout, the setting remains a contemporary space with ample natural light and simple decor.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and arms are deformed."
}
] |
seed44_3178
|
videos/HRA_part1/3178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a red beret and carrying a large canvas, walks purposefully down a bustling city street lined with vintage cinemas. Each theater features marquee signs advertising classic films from the golden age of cinema. The artist's attire includes a striped shirt, dark trousers, and a pair of worn-out sneakers, giving a sense of his creative and casual lifestyle. As he strides, passersby glance curiously at his oversized artwork, which is draped in a protective cloth, hinting at the mystery and anticipation of his latest creation. The vibrant atmosphere of the old movie houses and the artist's journey through the urban landscape evoke a sense of nostalgia and artistic inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The artist's arm is twisted, the hand is twisted, and the item in the hand is twisted."
}
] |
seed42_2301
|
videos/HRA_part0/2301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man with short brown hair and glasses, wearing a green striped shirt and apron, is baking a vanilla sponge cake in a home kitchen with white cabinets and countertops. He starts by pouring milk into a bowl containing flour, sugar, eggs, and butter, mixing the ingredients together with an electric mixer. The batter is then poured into a round cake pan and placed in a preheated oven. The camera captures the cake rising and turning golden brown. Once baked, the man removes the cake from the oven, lets it cool, and proceeds to frost it with whipped cream frosting using a spatula. The final shot shows the beautifully frosted cake on a white plate, ready to be served.]"
},
{
"from": "gpt",
"value": "Bad. No generation of a cheerful man with short brown hair and glasses wearing a green striped shirt and an apron; no generation of the process of mixing milk, flour, sugar, eggs, and butter in a bowl with an electric mixer; no generation of the cake rising and gradually turning golden yellow in the oven; no generation of the man taking the cake out of the oven."
}
] |
seed46_2446
|
videos/HRA_part2/2446.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hazy, ethereal atmosphere of Neptune, a space-suited firefighter, equipped with a specialized breathing apparatus and protective gear, is seen wiping the visor of his helmet. A neon bat, adapted to the planet's unique environment, hangs upside-down from a rocky outcropping nearby, its vibrant wings contrasting against the dimly lit, gaseous landscape. The firefighter's actions are deliberate and methodical, emphasizing the importance of maintaining clear visibility in the challenging conditions of Neptune's alien skies.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand and arm are distorted in the video."
}
] |
seed44_1600
|
videos/HRA_part1/1600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white hare runs through the city at night, its fur glowing under the streetlights, navigating urban obstacles like a seasoned athlete. It bounds across a busy intersection, dodging between yellow cabs and pedestrians, its powerful legs propelling it forward with graceful ease. The hare then leaps over a low brick wall, lands on the cobblestone sidewalk, and continues its journey, its silhouette framed by the neon signs of city storefronts. Finally, it pauses beneath a towering skyscraper, its large ears perked up, listening to the sounds of the city before continuing its mysterious nocturnal run.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit in the video has a twisted body, twisted paws, twisted face, and twisted legs."
}
] |
seed42_2357
|
videos/HRA_part0/2357.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a hare, donning a red apron and a name tag, works diligently as a cashier in a charming store nestled deep within a lush rainforest. The store's wooden shelves are stocked with unique items, including exotic fruits, colorful fabrics, and handmade crafts. Outside, the vibrant rainforest comes alive with the sounds of wildlife and the gentle patter of rain. Suddenly, the hare takes a break and ventures outside, where it encounters a serene natural pool, its clear waters inviting for a refreshing swim amidst the emerald greenery. The hare, now in swimming attire, joyfully splashes in the pool, surrounded by the lush foliage and the calming atmosphere of the rainforest.]"
},
{
"from": "gpt",
"value": "Bad. The body of the wild rabbit has undergone deformed mutations."
}
] |
seed42_2467
|
videos/HRA_part0/2467.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, energetic ferret with a tan and black fur pattern leaps from a wooden platform in a spacious room, showing its agility and playfulness. The room is filled with natural light, highlighting the ferret's mid-air jump with a backdrop of a large window and potted plants. The ferret lands gracefully on another platform, part of a series of interconnected wooden structures designed for climbing and exploration. It pauses for a moment, looking curious and alert, before making another sudden leap, showcasing its lively spirit and acrobatic abilities against the serene indoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's movements in the video are not smooth."
}
] |
seed44_1258
|
videos/HRA_part1/1258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and imaginative scene, a cheerful nurse, clad in a crisp white uniform and cap, is playfully chasing a capybara across a vast, sandy terrain reminiscent of Mars. The capybara, surprisingly agile, bounds ahead with its short legs, its wet nose glistening under the alien sun. Meanwhile, a Mars rover, equipped with intricate mechanical arms and advanced sensors, rolls steadily alongside, capturing the unusual chase on its high-definition cameras. The rover's solar panels gleam, and its wheels kick up puffs of red dust as it follows the unlikely pair, documenting their lively interaction on the Martian surface.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, and there are sudden changes."
}
] |
seed46_1398
|
videos/HRA_part2/1398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with curly brown hair tied back in a ponytail and wearing a red apron over a casual outfit stands in a modern kitchen, illuminated by bright overhead lights. She focuses intently on slicing a red bell pepper on a white cutting board, her silver ring catching the light. Next, she stirs a sizzling pan of vegetables on a stainless steel stove, steam rising from the pan. Then, she adds a pinch of salt and a sprinkle of fresh herbs to the dish, enhancing its aroma. Finally, she smiles as she plates the finished meal, garnishing it with a sprig of parsley, ready to serve a delicious dinner.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are not smooth and coordinated."
}
] |
seed42_1601
|
videos/HRA_part0/1601.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single sand dollar lies on a bed of pristine white sand, its intricate pattern clearly visible against the stark background. Sunlight filters through crystal-clear water, casting a warm glow on the delicate creature. The sand dollar, positioned at a slight angle, reveals its stunning symmetry and fine details. Surrounding it, the sandy bottom is undisturbed, save for a few tiny grains caught in the gentle current, highlighting the serenity of the underwater scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1851
|
videos/HRA_part1/1851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A futuristic engineer, clad in a high-tech silver suit, is depicted running across a vast Galactic nebula, with swirling cosmic clouds and distant stars providing a dramatic backdrop. The engineer, wearing a sleek helmet that reflects the nebula's vibrant colors, is shown in various dynamic poses, conveying a sense of speed and determination. The scene is set against a massive, ethereal nebula, its colorful gas formations creating a stunning visual contrast with the engineer's metallic attire, emphasizing the thrilling combination of human endeavor and the awe-inspiring scale of the universe.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's running in the video is basically normal, but there are some coordination issues."
}
] |
seed46_1108
|
videos/HRA_part2/1108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic orange Bengal tiger with black stripes swims gracefully in a large, natural pond surrounded by lush green vegetation, showcasing its strength and agility in the water. The tiger, with piercing amber eyes and a powerful body, propels itself through the clear blue water with effortless strokes, its thick tail acting as a rudder. Sunlight filters through the dense foliage above, casting dappled light on the tiger's wet fur, highlighting its muscular physique and the water droplets clinging to its coat. The serene environment, complete with the sounds of nature and the gentle lapping of water against the shore, creates a captivating scene of wild beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1166
|
videos/HRA_part1/1166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning avant-garde space fashion, sprints across a futuristic stage illuminated by neon lights. Dressed in a metallic silver bodysuit, complete with high-tech accessories and a helmet visor, they leap with dynamic energy. The scene is set in a grand, space-themed venue, filled with an audience captivated by the performance. Spotlights follow the actor as they navigate the runway, showcasing the innovative designs against a backdrop of cosmic visuals and ambient electronic music. The fusion of performance art, cutting-edge fashion, and sci-fi aesthetics creates a mesmerizing spectacle.]"
},
{
"from": "gpt",
"value": "Bad. The actor in the video has missing limbs and is not fully generated."
}
] |
seed46_2270
|
videos/HRA_part2/2270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man named Jay, distinguished by his short brown hair and beard, stands against a backdrop of tall pine trees. Dressed in a gray sweater, black shirt, and brown pants, he looks intently at the camera. His gaze shifts upwards, revealing a curious expression. Then, he smiles warmly, his eyes crinkling at the corners, exuding friendliness. Lastly, he closes his eyes in delight, basking in the beauty of nature surrounding him, the sunlight filtering through the dense forest creating a serene atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The man's facial expressions in the video are basically normal, but there is slight inconsistency."
}
] |
seed46_2942
|
videos/HRA_part2/2942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 strong, focused woman wearing a red helmet and climbing gear scales a towering rock face, the texture of the stone rough under her hands and feet. The camera captures her intense concentration, the strain in her muscles, and the determination in her eyes. Sunlight filters through wispy clouds, casting dramatic shadows on the cliffside as she ascends higher, leaving the green valley far below. The scene is framed by rugged terrain, emphasizing her solitary endeavor against the vast, natural landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2055
|
videos/HRA_part0/2055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling train station, a middle-aged doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, carries a brown leather bag. He walks purposefully past a massive, lifelike mammoth skeleton displayed as a scientific exhibit, the structure towering above the busy commuters. The scene captures the juxtaposition of the prehistoric and the modern, with the well-lit, contemporary train station bustling with people going about their day, while the imposing mammoth skeleton looms as a reminder of Earth's ancient past.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's eyes were not generated, and there were issues with the limbs."
}
] |
seed46_2175
|
videos/HRA_part2/2175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, golden hamster in swimwear, including water goggles and a miniature life jacket, floats on a raft in a clear, gently flowing river surrounded by lush greenery. It paddles with its tiny paws, navigating through the serene waters with determination. The hamster then jumps into the river, swimming energetically, its little body moving gracefully through the water. Finally, it rests on a rock near the riverbank, basking in the sunlight, wearing a happy expression, all set against the peaceful backdrop of a forest and a calm river.]"
},
{
"from": "gpt",
"value": "Bad. The dwarf hamster in the video has a distorted face and twisted paws."
}
] |
seed42_160
|
videos/HRA_part0/160.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray glides effortlessly through crystal clear waters, its vast wingspan casting a shadow on the sandy seabed below. The graceful creature is adorned with a constellation of spots and lines, unique to each individual, as it moves with a serene, almost meditative quality. Sunlight filters through the surface, creating a mesmerizing play of light around the manta ray, which occasionally flips upside down to feed on plankton near the water's surface, showcasing its acrobatic abilities in the vibrant marine environment.]"
},
{
"from": "gpt",
"value": "Bad. The manta ray's body generation in the video is unreasonable."
}
] |
seed46_1316
|
videos/HRA_part2/1316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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: [On a sandy beach, two smiling children, a boy and a girl, gently caress a small green lizard that rests on a patch of dry sand, surrounded by lush vegetation. The boy, wearing a blue t-shirt and blue swimming trunks, and the girl, clad in a pink dress, sit cross-legged as they tenderly pet the lizard. The scene is filled with warmth and sunlight, casting shadows of the children and the lizard onto the sandy ground. Moments later, the lizard scurries away into the foliage, and the children watch it go, their faces a mix of fascination and delight, embodying the innocence and wonder of childhood discovery.]"
},
{
"from": "gpt",
"value": "Bad. The child's hands and feet are deformed, and finally, the lizard also undergoes deformation."
}
] |
seed46_3007
|
videos/HRA_part2/3007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male spruce grouse, perched on a branch in a dense forest, displays its vibrant plumage featuring shades of brown, gray, and white speckles. Its red eyelids stand out against the dark eye, while its yellow bill adds a striking contrast. The bird's feathers are ruffled, perhaps due to a breeze or during a display, and it is surrounded by lush green foliage, indicating a healthy habitat. The grouse is stationary, offering a clear view of its unique features against the backdrop of a richly textured forest environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3064
|
videos/HRA_part1/3064.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished, middle-aged male doctor stands in a well-lit hospital corridor, wearing a stethoscope around his neck and a white lab coat over a crisp, button-down shirt and slacks. He holds a clipboard in his right hand, reviewing patient records intently. Behind him, the hallway is bustling with medical personnel and equipment, conveying the busy atmosphere of a healthcare facility. The scene captures the essence of a dedicated healthcare professional in the midst of his duties, surrounded by the sights and sounds of a working hospital.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's fingers and stethoscope in the video have generation issues."
}
] |
seed44_2242
|
videos/HRA_part1/2242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man wearing a blue shirt, tan shorts, and brown shoes sweeps his wooden porch with a broom, against the backdrop of a sunny day and a lush green forest. He pauses for a moment to look into the distance, where a lake can be seen shimmering under the sunlight. The man resumes sweeping, revealing a clean, well-maintained porch. Suddenly, a playful dog rushes towards him, and the man stops to pat the dog affectionately, before continuing his task. The scene concludes with the man leaning against the porch railing, enjoying the peaceful surroundings and the company of his furry friend.]"
},
{
"from": "gpt",
"value": "Bad. The man and the dog's movements in the video are very unsmooth and uncoordinated."
}
] |
seed46_1637
|
videos/HRA_part2/1637.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden retriever, framed against a vibrant green meadow under a clear blue sky, experiences a unique perception of time as it runs. Initially, the dog is seen standing still, looking forward with anticipation. It then starts running, its legs blurring as if time has accelerated for the viewer. Next, the dog leaps into the air, seemingly frozen in mid-air, giving the impression of time slowing down. Finally, the dog bounds across the field, its motion smooth and unhurried, conveying a sense of normal time flow, all while the lush green landscape and clear blue sky provide a serene backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The dog's running in the video is uncoordinated."
}
] |
seed44_1305
|
videos/HRA_part1/1305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek black panther leaps majestically across a moonlit savannah, its muscles rippling beneath dark fur that shimmers under the celestial glow. The powerful feline bounds over tall grasses, leaving a trail of disturbed foliage in its wake, as it propels itself forward with a burst of speed and grace. Upon landing, the panther crouches low, ready for its next spring, against the backdrop of a vast landscape, dotted with distant trees and illuminated by the silvery light of the full moon.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1417
|
videos/HRA_part0/1417.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone buzzard soars gracefully across a vast, cloud-dappled sky, its wings spread wide in a display of effortless flight. Its keen eyes scan the rugged terrain below, a patchwork of sunlit earth tones and deep shadows cast by towering rock formations. The bird's majesty is further highlighted by its striking profile, showcasing its hooked beak and sharp talons as it circles overhead, a silent sentinel surveying its domain from the heavens. Against the dramatic backdrop of a sunlit landscape, the buzzard embodies the untamed spirit of nature in its purest form.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1540
|
videos/HRA_part2/1540.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy white dog runs alongside a futuristic lunar buggy as it traverses the desolate, rocky terrain of the moon's surface, illuminated by the distant Earth shining brightly in the sky. The dog, wearing a red bandana and a small backpack, bounds energetically over the rugged landscape, while the lunar buggy, equipped with large, treaded wheels and a solar panel roof, cruises steadily beside it. Inside the buggy, a figure in a spacesuit can be seen piloting the vehicle, their helmet visor reflecting the barren lunar scenery. The Earth hangs low on the horizon, casting a pale blue glow over the stark, airless environment.]"
},
{
"from": "gpt",
"value": "Bad. The dog's limbs in the video are incomplete, and its body is not well-proportioned."
}
] |
seed46_1858
|
videos/HRA_part2/1858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a college student, dressed in a traditional ceremonial robe, kneels on a lush, green meadow under a clear night sky filled with stars. Beside them, a squirrel, unusually adorned in miniature ceremonial attire, mirrors the student's position. The student gently wipes away what appears to be ceremonial paint from their face using a soft cloth, alluding to a cleansing ritual. This intimate act is witnessed by the squirrel, which seems to participate in its own way, creating a surreal, touching moment between human and nature, set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee's movements in the video are not smooth."
}
] |
seed44_249
|
videos/HRA_part1/249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 and imaginative scene, two children, a boy and a girl, are dancing in a whimsical, cartoon-like environment. The girl, with curly red hair, wears a pink dress, while the boy, sporting brown hair, dons a blue shirt. They are accompanied by a friendly, animated coyote who mirrors their dance moves. The backdrop is a scientific laboratory filled with high-tech equipment, where researchers in lab coats are studying dark matter. This unusual juxtaposition of elements creates a captivating and unique visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video."
}
] |
seed42_2465
|
videos/HRA_part0/2465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 curious brown monkey, with its fur ruffled by the breeze, is seen playfully paddling in a tranquil body of water, surrounded by lush green foliage. It uses its arms to splash about, moving gracefully through the clear blue water, with trees and plants in the background framing the scene. The monkey's expressive face shows delight as it swims, its limbs working rhythmically beneath the surface, and droplets of water scatter around it, capturing the joy of this unexpected aquatic adventure.]"
},
{
"from": "gpt",
"value": "Normal. The monkey's arm is somewhat deformed."
}
] |
seed46_2158
|
videos/HRA_part2/2158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray shirt and khaki pants, sits in a modern office space with a clean desk, listening intently. He leans forward with his right elbow on his knee, his face partially covered by his right hand, and his eyes closed, indicating deep concentration. His left hand rests on a high-tech, silver-colored device, possibly a piece of machinery or equipment, while a large screen displays complex diagrams and data in the background. The office is illuminated by natural light from a window, casting a soft glow on the engineer and his workspace.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, and face of the person in the video are distorted."
}
] |
seed44_2119
|
videos/HRA_part1/2119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, a firefighter clad in a specialized silver suit and equipped with an advanced helmet wipes down a high-tech control panel with a cloth, ensuring cleanliness in zero gravity. The background showcases intricate machinery and complex equipment typical of a space exploration module, with the firefighter's actions highlighting the routine maintenance tasks necessary for maintaining operational integrity in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1299
|
videos/HRA_part2/1299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an unusual scene, a waiter wearing a black vest, white shirt, and black pants performs a kick in a dining room. The room features a long wooden table adorned with a white cloth, set with plates and glassware. The waiter's kick is high and assertive, contrasting with the formal setting. His black shoes, part of his uniform, add to the unexpected nature of the action. Behind him, a large window allows natural light to illuminate the space, highlighting the waiter's dynamic movement against the backdrop of the elegantly arranged dining area.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1778
|
videos/HRA_part1/1778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, casually dressed in a dark gray t-shirt and black sweatpants, attentively unloads a dishwasher in a modern kitchen. The space features sleek white cabinets, a stainless steel refrigerator, and a large window allowing natural light to illuminate the room. He carefully places dishes into cupboards, revealing a methodical approach to the task. With a half-smile and relaxed posture, he demonstrates an unexpected domestic side, contrasting his typical on-screen persona. Throughout the scene, the kitchen remains orderly and clean, emphasizing the mundanity of the chore juxtaposed with his celebrity status.]"
},
{
"from": "gpt",
"value": "Bad. The character's head, arms, hands, and dishwasher are distorted in the video."
}
] |
seed42_2389
|
videos/HRA_part0/2389.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a person wearing a brown bear costume and another individual, both standing in a lush green forest, engage in playful interaction. The person in the bear suit wipes their face with a cloth, as if perspiring from the heat inside the costume, while the other person looks on with amusement. The vibrant greenery of the forest and the clear, sunny sky provide a cheerful backdrop for this lighthearted moment between friends, one of whom is dressed as a bear, playfully wiping their face as they enjoy each other's company in the great outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The person in the brown bear costume has a distorted face, twisted hands, and twisted arms."
}
] |
seed44_1218
|
videos/HRA_part1/1218.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diligent male artist applies paint to a large, colorful abstract artwork on a vertical easel, positioned outdoors against a sunny, clear blue sky. Dressed in a simple white tank top and khaki cargo shorts, he works intently, surrounded by various tools of his trade including brushes, a palette, and a small table holding additional supplies. His focused expression and the vibrant colors of the painting contrast sharply with the natural greenery and clear sky in the background, creating a dynamic scene of creative energy and artistic passion.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1847
|
videos/HRA_part2/1847.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a blue shirt and khaki pants, leaps into the air with arms outstretched against the vast desert landscape, showcasing his adventurous spirit. Moments later, he is captured in mid-jump, his silhouette framed by the golden hues of the dunes and the clear blue sky. Then, he lands on the sandy terrain, his posture reflecting a sense of accomplishment, with the desert's serene beauty serving as a dramatic backdrop. Finally, he jumps again, this time with a wide smile, embodying the joy of exploring the wilderness, all set against the stunning desert scenery.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed42_1828
|
videos/HRA_part0/1828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature woman with graying hair, wearing a white blouse and glasses, meticulously irons clothes in a well-lit room. She starts by carefully smoothing out a white shirt with a hot iron, steam rising gently. Then, she moves on to press a pair of khaki pants, folding them neatly over the ironing board. Throughout, she maintains a focused demeanor, her glasses catching the light as she works diligently, the steam from the iron creating a serene, domestic atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, and the hand is distorted."
}
] |
seed42_2018
|
videos/HRA_part0/2018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a leopard print scarf, sits in a dimly lit room, engaged in caressing a small, furry creature. Behind her, a screen displays complex diagrams related to quantum entanglement experiments, adding a layer of intrigue. Her attire, which includes the eye-catching leopard print accessory, contrasts with the scientific theme of the scene. The focus is on her gentle interaction with the creature, while the backdrop hints at her intellectual pursuits, creating a compelling juxtaposition between the personal and professional aspects of her life.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the writer's fingers in the video has problems."
}
] |
seed44_1225
|
videos/HRA_part1/1225.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a panda-costumed police officer sits in the cockpit of a futuristic space vehicle, navigating through the vast cosmos with a serious yet adorable demeanor. Moments later, the panda officer is shown swimming gracefully underwater, fully clad in the panda suit and police uniform, including a badge and a cap, creating a surreal and humorous contrast against the aquatic environment. The scene is set in a large, clear, space-themed aquarium, with stars and planets adorning the backdrop, merging elements of space travel and aquatic life in a playful and unexpected manner.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the panda's limbs missing and body deformed underwater."
}
] |
seed44_2136
|
videos/HRA_part1/2136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 character, resembling a panda with black-rimmed eyes and a friendly smile, walks down a bustling city street. Dressed in a full-body panda suit, they navigate the urban landscape, passing by pedestrians and city structures. The panda mascot's outfit includes large, padded paws and a fuzzy, rounded silhouette, adding to the whimsical nature of the scene. As they stroll, the surrounding environment, filled with buildings and people going about their day, contrasts with the playful presence of the panda.]"
},
{
"from": "gpt",
"value": "Normal. The panda walks basically normally, but there is slight uncoordination in the movements."
}
] |
seed46_2503
|
videos/HRA_part2/2503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown mouse leaps through the air in a grassy field, its tiny body arched gracefully as it propels itself forward. The scene is set against a backdrop of lush green foliage and blue skies, with the mouse's agile movement captured mid-jump. Its wiry tail extends behind it, adding to the sense of dynamic motion, while its round ears and beady eyes give it a characteristically cute appearance. The mouse lands softly on a patch of green grass, ready to spring into action again at a moment's notice.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the brown rat in the video are missing, and there are deformities in the face and body generation."
}
] |
seed42_1627
|
videos/HRA_part0/1627.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal parallel universe, a robust farmer leaps high into the air, his body mid-jump, showcasing an extraordinary ability. Dressed in a brown shirt, green vest, beige trousers, and black boots, he appears surprised by his own supernatural power. Behind him, an array of vibrant vegetables and fruits grow in perfect rows, defying the laws of physics in this fantastical realm. The farmer's leap is captured in stunning detail, highlighting his muscular physique and the otherworldly setting that surrounds him.]"
},
{
"from": "gpt",
"value": "Normal. The jumping action of the character in the video is not very smooth, and there are sudden changes in the limbs."
}
] |
seed42_304
|
videos/HRA_part0/304.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, dressed in a classic white uniform and black pants, walks through a lush, green forest carrying a live rabbit in his arms. The chef's attire is detailed, complete with a traditional white chef's jacket, black trousers, and a pristine white chef's hat. The rabbit, a live and lively creature, is held gently in the chef's arms as he strolls through the dense woodland. The forest setting is richly depicted, with tall trees, vibrant foliage, and dappled sunlight filtering through the leaves, creating a dramatic contrast with the chef's uniform and the rabbit's fur.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1211
|
videos/HRA_part0/1211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer wearing a traditional conical hat and a long-sleeved shirt walks down a narrow dirt path bordered by tall grasses and lush greenery, reminiscent of a tropical landscape. In his right hand, he carries a long wooden staff, while his left hand rests gently on his hip. Suddenly, his attention is drawn to a cobra emerging from the foliage, its hood dramatically spread as it rises to meet his gaze. The farmer stops, standing tall and watchful, maintaining eye contact with the snake, creating a tense standoff between man and wild creature. The cobra, with its distinctive hood fully expanded, remains in a defensive posture, mirroring the farmer's cautious stance, as they both seem to assess each other in the midst of the dense vegetation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.