video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2210
|
videos/HRA_part0/2210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An innovative engineer, adorned in a spacesuit and helmet, stands on the lunar surface, illuminated by the Earth's glow, holding a leash attached to a lion. The lion, also wearing a miniature spacesuit and helmet, jumps playfully in the low gravity environment. Both figures cast long shadows against the moon's dusty terrain, with the Earth shining brightly in the dark, star-studded sky. This surreal scene combines elements of space exploration, wildlife, and human ingenuity in a single captivating frame.]"
},
{
"from": "gpt",
"value": "Normal. The lion's movements in the video are not smooth."
}
] |
seed46_1686
|
videos/HRA_part2/1686.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A fluffy, baby panda with distinctive black and white fur crawls across a lush, green forest floor, surrounded by vibrant vegetation and bamboo shoots. It moves with a curious, almost playful demeanor, its tiny paws gripping the mossy ground. The scene is filled with natural light filtering through the dense canopy above, casting dappled shadows on the panda as it explores its environment.]"
},
{
"from": "gpt",
"value": "Normal. The panda in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_111
|
videos/HRA_part1/111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with gold accents and a peaked cap, runs purposefully across a grand hall within a futuristic space station. The hall is lined with flags from various nations and interspersed with abstract art pieces, all illuminated by the soft glow of recessed lighting. In the distance, a large, circular window reveals the vastness of space and the distant twinkle of stars. The officer's run suggests urgency, possibly related to security matters at the ongoing political summit, where delegates from Earth and various space colonies gather to discuss interstellar policy. The polished floor reflects the officer's movement, emphasizing the gravity of the situation in this otherwise serene and majestic setting.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's running motion in the video is not smooth and coordinated."
}
] |
seed42_2411
|
videos/HRA_part0/2411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, grassy plains under a wide, clear blue sky, two small children, a boy and a girl, both wearing vibrant yellow raincoats and red boots, walk alongside a majestic bison. The bison, with its shaggy brown fur and large, powerful body, moves gracefully across the landscape, leading the children on an adventurous journey. The siblings follow closely, their expressions a mix of awe and delight, as they explore the wilderness together with their unlikely companion. The scene is peaceful, with the gentle swaying of tall grass and the distant silhouette of mountains framing the horizon.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_301
|
videos/HRA_part1/301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 marlin breaches the sparkling turquoise ocean, its sleek indigo body glistening in the sunlight. The fish soars through the air, its elongated rostrum pointed skyward, before plunging back into the sea with a splash. Surrounded by the vastness of the ocean, the marlin's powerful leap is captured against a backdrop of rolling waves and a cloud-dappled sky, showcasing the beauty and grace of this magnificent marine creature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_13
|
videos/HRA_part0/13.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, solitary moose is depicted swimming in a clear, glassy lake surrounded by lush vegetation, with its head and antlers visible above the water's surface. The majestic creature gracefully propels itself forward, its body partially submerged, showcasing its surprisingly strong swimming abilities. In the distance, dramatic cliffs rise from the water's edge, their rugged surfaces covered in dense greenery, providing a stunning contrast against the calm waters. The scene is completed by the inclusion of a second moose, also swimming, creating a captivating visual of these powerful animals in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2187
|
videos/HRA_part2/2187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse with short brown hair, wearing a blue uniform and a stethoscope around her neck, playfully interacts with a ferret on a clean, white examination table in a well-lit veterinary clinic. The ferret, displaying its natural agility, leaps from the nurse's hands as she gently tosses it upwards. The nurse, with a joyful smile, catches the ferret mid-air, showcasing a tender bond between the caregiver and the small animal in a serene medical environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the ferret's movements are also not smooth."
}
] |
seed46_1875
|
videos/HRA_part2/1875.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a white shirt and denim overalls, stands on the edge of a serene pond, watching attentively as a rabbit swims gracefully through the clear water. The rabbit, defying expectations, moves with surprising agility, its brown fur glistening beneath the golden afternoon sunlight. The farmer, hat in hand, looks on with a mix of surprise and delight, the rolling green fields and distant barn providing a quintessential rural backdrop to this unexpected scene.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's ears and eyes in the video have generation issues, with the face and body being distorted."
}
] |
seed46_1371
|
videos/HRA_part2/1371.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 display, a snake charmer clad in a richly colored red robe and matching turban leans forward, engaging intently with a king cobra emerging from a traditional wicker basket. The snake, adorned with intricate patterns, rises dramatically from the basket, its hood spread wide. The charmer's hands, decorated with silver bracelets, gently caress the serpent's body, emphasizing the bond between human and animal. The scene is set against a vibrant, patterned cloth, adding to the exotic atmosphere, with the charmer's face expressing both respect and control as he interacts with the majestic creature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1190
|
videos/HRA_part1/1190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant supermarket setting, a middle-aged janitor, clad in a green vest and holding a mop, finds himself unexpectedly chasing after a mischievous weasel. The weasel, sporting a tiny red cap, races down the aisles filled with neatly stacked produce and canned goods, causing mild chaos. The janitor, with a look of determined amusement, sprints behind, weaving through shoppers and dodging displays. Amidst the commotion, the supermarket's bright lights and colorful signage create a dynamic backdrop for this unusual pursuit.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the hands are deformed, the face is distorted, the legs are twisted, and the weasel's body is twisted, with the head deformed."
}
] |
seed46_1416
|
videos/HRA_part2/1416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a whole, raw cod fish, lying on a bed of ice, is showcased in stunning high-definition. The fish, with its distinctive greenish-grey skin and large, pearly eyes, is presented head-on, giving a clear view of its mouth and gills. The camera zooms in to reveal the intricate details of the cod's texture and scales, emphasizing its freshness. The background consists of a blurred array of seafood items, highlighting the cod as the central subject in a market or fishmonger's stall.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1612
|
videos/HRA_part0/1612.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful doctor, wearing a stethoscope around his neck and a colorful tie, is laughing heartily with his head thrown back, his eyes closed, and his mouth wide open, showing his amusement in a candid moment. The laughter is contagious, spreading joy and positivity in a medical setting, with the doctor's facial features animated and expressive, capturing the essence of happiness and camaraderie in a professional environment.]"
},
{
"from": "gpt",
"value": "Normal. The facial generation of the doctor in the video is problematic."
}
] |
seed42_1374
|
videos/HRA_part0/1374.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room, two young siblings, a boy and a girl, are fast asleep in their cozy beds, surrounded by an assortment of toys. The boy, wearing a red superhero costume, lies sprawled across his bed, one arm hanging over the side, with a toy dinosaur resting on his chest. The girl, dressed in a pink nightgown adorned with stars, sleeps peacefully with her favorite teddy bear clutched tightly in her arms. A nightlight shaped like a moon casts a warm glow over the scene, highlighting the innocence and tranquility of childhood sleep.]"
},
{
"from": "gpt",
"value": "Normal. The boy's face, the girl's face, and the teddy bear in the video are generated normally, but the boy's arm is missing."
}
] |
seed42_2035
|
videos/HRA_part0/2035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape, a large, hairy mammoth tenderly caresses a smaller mammoth with its trunk, creating a touching scene of familial affection. The larger mammoth, covered in thick, shaggy fur, gently touches the younger one, who stands beside it, also covered in a coat of dark, coarse hair. Both creatures possess impressive tusks, with the adult displaying a more formidable set. They are surrounded by green vegetation and tall trees, with a waterfall visible in the distance, contributing to the serene atmosphere of this ancient bonding moment.]"
},
{
"from": "gpt",
"value": "Bad. The nose of the right mammoth in the video is problematic."
}
] |
seed46_2666
|
videos/HRA_part2/2666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant forest setting, a mother beaver gently caresses her kits with her large, flat tail, while they sit cozily together on the riverbank. The kits, with their soft, brown fur, look up at her with adoration, as the mother's nurturing touch conveys love and protection. Surrounded by the vibrant greenery and tranquility of nature, this heartwarming scene captures the tender bond between a beaver mother and her offspring.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1236
|
videos/HRA_part2/1236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A handsome, clean-shaven actor with short brown hair and wearing a black turtleneck sweater and gray blazer is seen in a dimly lit room. He gently caresses a small bat, which rests calmly on his hand, demonstrating a tender interaction between man and animal. The bat, with its leathery wings folded, seems comfortable in his presence, creating a unique and intimate scene. The actor's other hand, adorned with a watch, occasionally enters the frame, adding to the personal nature of the moment. Throughout the video, the focus remains on the actor's face and the bat, capturing the essence of their connection in a softly lit environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2606
|
videos/HRA_part1/2606.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, spotted jaguar leaps powerfully across a narrow stream in a lush, green rainforest, its muscles rippling beneath golden-brown fur, with water droplets splashing upwards. The big cat's intense gaze is fixed ahead, showcasing its agility and grace in motion against the vibrant jungle setting, complete with lush vegetation and the misty atmosphere of the rainforest environment.]"
},
{
"from": "gpt",
"value": "Bad. The jaguar's head, claws, and legs are distorted in the video."
}
] |
seed44_1623
|
videos/HRA_part1/1623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, likely his cub, against the backdrop of a lush, green savannah during the golden hour. The father lion, with his thick, dark mane, displays affection and protection as he rubs his cheek against the cub's head. The cub, with its curious eyes and playful demeanor, responds with a nuzzle of its own, showcasing the intimate bond between them. This heartwarming interaction unfolds under a sky painted with warm hues of orange and pink, highlighting the emotional connection between the two lions.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1570
|
videos/HRA_part1/1570.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, 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": "Good. No obvious problems."
}
] |
seed42_1248
|
videos/HRA_part0/1248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, young female barista with brown hair pulled into a bun and wearing a gray shirt smiles warmly as she expertly crafts a coffee beverage. Behind her, a vibrant cafe atmosphere is visible, complete with patrons seated at tables and a counter displaying delectable pastries. The barista's hands are busy pouring steaming milk from a silver frothing pitcher into a cup filled with rich, dark coffee, creating a perfect latte. Her name tag identifies her as 'Sara', and she works at a bustling coffee shop where she deftly prepares a frothy cappuccino, her practiced movements and bright smile enhancing the welcoming vibe of the place.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1372
|
videos/HRA_part0/1372.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a patterned blue dress and a white apron over it, stands against the lush greenery of a botanical garden, holding her apron's lower edge. Moments later, she leaps into the air with a joyful expression, surrounded by vibrant green foliage and blooming flowers, with sunlight filtering through the trees. Her attire remains unchanged, consisting of a blue floral-print dress and a white apron, as she jumps in a patch of sunlight, with the vibrant garden providing a lively contrast to her figure.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's jumping in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed44_1896
|
videos/HRA_part1/1896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dreamlike sequence, an astronaut clad in a pristine spacesuit gently caresses a bobcat on the lunar surface, under the Earth's watchful gaze. The astronaut's visor reflects the desolate landscape, while the bobcat, undeterred by its extraterrestrial surroundings, responds with curiosity. The scene is illuminated by the distant Earthshine, casting a soft glow on the moon's dusty terrain, highlighting the tenderness of this interstellar encounter.]"
},
{
"from": "gpt",
"value": "Normal. The astronaut's fingers are not fully generated, there are issues with the feet, the cat's limbs are generated disharmoniously, the tail is too long, and the facial features are not generated."
}
] |
seed46_2700
|
videos/HRA_part2/2700.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest setting, a majestic gray wolf gently caresses a smaller, white wolf with its nose, demonstrating a tender moment of affection between the two creatures. The gray wolf, with piercing yellow eyes, a thick, shaggy coat, and a muscular build, leans its head down to touch noses with the smaller white wolf, which looks up with a similar intensity. Both wolves are standing in a grassy clearing within the dense forest, surrounded by tall trees and patches of sunlight filtering through the leaves, creating a serene atmosphere for this intimate interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1127
|
videos/HRA_part2/1127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beret, thick-rimmed glasses, and a patterned shirt, nods his head in time with the music he plays on his acoustic guitar. The scene is set in a dimly lit room, with the focus solely on the artist. His eyes are closed in concentration, lost in the melody, as he strums the guitar with skillful fingers. The atmosphere is intimate, capturing the essence of a solo performance, with the musician's nodding head emphasizing the rhythm of the song.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_270
|
videos/HRA_part2/270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 musician, wearing a red bandana, black leather jacket, and dark jeans, walks through an abandoned mine with caution. He carries a vintage guitar case, adding to his rugged, artistic persona. The mine, filled with debris and old machinery, provides a stark, industrial backdrop. The musician's confident stride and the detailed textures of the mine walls and floor convey a sense of exploration and mystery. As he moves deeper into the mine, the dim lighting highlights his silhouette, creating a dramatic effect. Throughout the video, the focus remains on the musician's journey, emphasizing his presence and the unique setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2879
|
videos/HRA_part1/2879.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a majestic stag with a full, impressive rack of antlers finds itself in an industrial setting, surrounded by large, gray warehouses under a cloudy sky. The deer begins to move gracefully, almost as if it's dancing, its hooves delicately stepping on the concrete ground. The scene is surreal, with the wild animal seemingly unfazed by the urban environment, embodying a unique blend of nature and industry as it prances amidst the towering structures.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2441
|
videos/HRA_part1/2441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its distinctive black and white fur, engages in a leisurely stroll through a lush, green bamboo forest, its round body moving gracefully despite its bulk. It then proceeds to crawl, using its front paws to pull itself forward in a slow, deliberate motion, highlighting its unique method of navigating its environment. The panda's movements are unhurried and methodical, showcasing its relaxed demeanor as it explores its verdant surroundings. Throughout the scene, the panda remains the central focus, with the vibrant greenery of the bamboo forest providing a vivid contrast to its striking fur pattern.]"
},
{
"from": "gpt",
"value": "Bad. The giant panda in the video has uncoordinated movements while walking."
}
] |
seed46_2438
|
videos/HRA_part2/2438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, dressed in a futuristic silver spacesuit, is depicted in zero gravity within a space station habitat, performing a series of jumps against a backdrop of LED-lit panels. He executes a powerful jump, legs spread wide, arms extended, and face obscured by his helmet's visor, capturing the essence of weightlessness. In another frame, he appears to push off from a handrail, propelling himself through the air with a sense of effortlessness. Throughout the sequence, the space station's cylindrical structure, complete with porthole windows and complex machinery, provides a vivid setting for his graceful movements.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2126
|
videos/HRA_part0/2126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, costumed in a shimmering silver outfit reminiscent of celestial bodies, performs an interpretive dance against a backdrop of the Uranus aurora. The aurora, with its vivid green and purple hues, illuminates the scene with an ethereal glow. The actor's movements are fluid and expressive, capturing the essence of cosmic energy and the mystical atmosphere of the distant planet. As the dance progresses, the auroral lights pulsate and swirl, creating a mesmerizing visual harmony between the performance and the celestial phenomenon. Throughout the video, the focus remains on the captivating dance, with the Uranus aurora serving as a breathtaking and dynamic canvas for the actor's artistry.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2179
|
videos/HRA_part0/2179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a dark green winter jacket, gray gloves, and a matching hat, diligently shovels snow from a pathway in front of a red-brick building with a yellow door. Snowflakes continue to fall gently, accumulating on the ground and surrounding trees. The man, with a serious yet focused expression, works methodically, clearing the path section by section. His breath visible in the cold air, he pauses momentarily, looking up at the sky as if assessing the weather conditions, before resuming his task with renewed determination.]"
},
{
"from": "gpt",
"value": "Bad. The character's walking in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed46_2438
|
videos/HRA_part2/2438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, dressed in a futuristic silver spacesuit, is depicted in zero gravity within a space station habitat, performing a series of jumps against a backdrop of LED-lit panels. He executes a powerful jump, legs spread wide, arms extended, and face obscured by his helmet's visor, capturing the essence of weightlessness. In another frame, he appears to push off from a handrail, propelling himself through the air with a sense of effortlessness. Throughout the sequence, the space station's cylindrical structure, complete with porthole windows and complex machinery, provides a vivid setting for his graceful movements.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs in the video are deformed and missing, and the body is generated blurry."
}
] |
seed44_2402
|
videos/HRA_part1/2402.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed firefighter, complete with helmet and yellow firefighting jacket, races through a lush, green forest, closely pursued by an animated beaver wearing a miniature firefighter uniform, also with a helmet and a small red cape. The firefighter leaps over a fallen log, demonstrating agility, while the beaver follows suit, mimicking every action with playful determination. Both characters run with purpose, the firefighter leading the charge and the beaver keeping pace, highlighting a fun, animated adventure set against the vibrant backdrop of a dense woodland.]"
},
{
"from": "gpt",
"value": "Bad. Did not generate mini firefighter uniforms, red cloaks; the beaver's position in the video does not match the text description."
}
] |
seed42_2957
|
videos/HRA_part0/2957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown and white coat, swims through clear, bubbling water, showing its unique swimming style with its head held high and nose just above the waterline. It uses its webbed feet to propel itself forward, highlighting its natural aquatic abilities. The water droplets glisten around it, and its determined face conveys a sense of joy and playfulness in its unusual swimming endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The ferret in the video has uncoordinated movements."
}
] |
seed46_1600
|
videos/HRA_part2/1600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 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": "Normal. The rabbit's movements in the video are not smooth."
}
] |
seed42_2903
|
videos/HRA_part0/2903.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier, wearing a red apron over a white collared shirt, black pants, and brown shoes, pulls a heavy, overflowing shopping cart across a busy supermarket floor. She moves with determination, navigating the aisles filled with various products and customers. The cart, brimming with goods, contrasts with her clean and tidy appearance, highlighting the physical demands of her job. Behind her, the supermarket's brightly lit shelves and bustling atmosphere provide a dynamic backdrop to her task.]"
},
{
"from": "gpt",
"value": "Bad. The female cashier's face in the video is slightly blurry, and her fingers are deformed."
}
] |
seed42_1905
|
videos/HRA_part0/1905.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, imposing goose stands tall on the bank of a misty lake, its yellow beak agape as it emits a loud honk. Its body is a mix of gray and white feathers, with a distinctive black mark around one eye. The goose's webbed feet are visible as it wades into the water, creating ripples that disturb the stillness of the early morning. Against the backdrop of a cloudy sky, the goose swims gracefully, its head held high, exuding an air of confidence and territorial dominance. The scene is set in a natural, serene environment, with the goose being the focal point, highlighting its majestic presence in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the goose opening its beak or showing its webbed feet."
}
] |
seed44_2389
|
videos/HRA_part1/2389.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 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 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 brown bear costume person's movements are not smooth."
}
] |
seed46_1741
|
videos/HRA_part2/1741.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male janitor, dressed in a gray sweater over a white collared shirt and khaki pants, pauses from his cleaning duties to take deep breaths, standing in a brightly lit, modern office hallway. He holds a mop in his right hand and rests his left hand on a mop bucket, while his eyes are closed, focusing on his breathing. The clean, minimalist surroundings emphasize the tranquility of the moment as he takes a moment to collect himself, his facial expression one of peaceful concentration.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2557
|
videos/HRA_part0/2557.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, two figures, a man and a woman, both wearing sophisticated, form-fitting silver spacesuits with intricate blue detailing, walk purposefully down a sleek corridor lit by soft, ambient blue light. They carry themselves with the poise and dignity of diplomats, their movements deliberate and confident. The man sports a neatly trimmed beard and short, dark hair, while the woman wears her long, curly hair in a high bun, adorned with small, sparkling silver clips. Both wear expressions of intense concentration, reflecting the gravity of their mission among the stars. Behind them, the corridor stretches into darkness, hinting at the vastness of space and the unknown adventures awaiting them.]"
},
{
"from": "gpt",
"value": "Good. The man's walking movements in the video are basically normal."
}
] |
seed42_1726
|
videos/HRA_part0/1726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, clad in a gray suit, white shirt, and patterned tie, rearranges furniture in an office setting. He lifts a wooden chair with leather seating, moving it across the room with ease. The scene is set in a corner office, featuring a large window with a cityscape view, a desk adorned with legal documents, and a bookshelf filled with law books. The lawyer's actions are deliberate, indicating a need for change or reorganization in his workspace. Despite the professional environment, the act of rearranging furniture adds a personal touch to the narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2103
|
videos/HRA_part1/2103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a spacesuit with a NASA logo, stands against the striking backdrop of a Martian sunset, characterized by its pinkish-blue hue. The director is captured mid-jump, with one arm raised in triumph, against the dramatic landscape of Mars. The sandy terrain stretches into the distance, dotted with rocks and craters, providing a stark contrast to the vibrant colors of the sunset. The director's silhouette is outlined by the warm glow of the setting sun, creating a powerful visual representation of human exploration and the beauty of the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The logo on the character's spacesuit in the video is not fully visible."
}
] |
seed42_2752
|
videos/HRA_part0/2752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two small children wearing vibrant yellow raincoats and boots venture into a lush, green forest on a misty day. They walk side by side on a narrow dirt path, surrounded by towering trees and a dense undergrowth of ferns and moss. Suddenly, a curious red fox emerges from the foliage, its bright orange fur contrasting against the verdant backdrop. The fox pauses, looking directly at the children with intelligent eyes, as if sharing a silent moment of connection. The children, undeterred and full of wonder, continue their journey, leaving the fox to watch them from the safety of the woods, creating a heartwarming and enchanting moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Bad. The child's hands and feet, and the red fox's head and paws were generated incorrectly in the video."
}
] |
seed42_2691
|
videos/HRA_part0/2691.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a yellow jumpsuit with a tool belt, crawls through the dimly lit, narrow maintenance corridor of a spaceship, preparing for a hyperspace jump. The ship's interior is filled with pipes and wires, and the engineer's headlamp illuminates the complex machinery around him. He checks various components, ensuring everything is secure before the critical maneuver, his face a mask of concentration under the harsh, industrial lighting of the engineering section.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_197
|
videos/HRA_part1/197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary director, wearing a dark jacket and shirt, sits in a dimly lit room with neon accents, contemplating the concept of light-speed travel. He gently caresses a futuristic, spherical object, possibly a holographic model, as he ponders the intricacies of time and space. The camera captures his focused gaze and the intimate interaction with the sphere, symbolizing the connection between human creativity and the mysteries of the universe. The scene is set against a backdrop of high-tech, sci-fi inspired visuals, enhancing the theme of exploring the unknown.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1448
|
videos/HRA_part0/1448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room with large windows, a brown bear cub stands on its hind legs, curiously exploring its surroundings at the Space Education Center, filled with educational displays about astronomy. The bear is spotted wiping its nose with a paw, drawing attention to its adorable antics among the exhibits. The scene is set against a backdrop of a large, round, gray planetarium screen, adding a cosmic touch to the unexpected encounter between wildlife and space knowledge.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the brown bear cub standing on its hind legs."
}
] |
seed46_1327
|
videos/HRA_part2/1327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gerbil with white patches stands on its hind legs, curiously observing a miniature robot astronaut figure. The robot, designed with intricate details including bolts and a clear helmet, takes a step forward on the wooden surface, seemingly on a mission. The gerbil, positioned next to a moss-covered stone, watches intently as the robot continues its journey across the textured table, creating an imaginative and whimsical scene.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's legs appear deformed, with extra legs showing when it moves."
}
] |
seed42_1901
|
videos/HRA_part0/1901.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing rectangular glasses and a blue button-down shirt with a maroon sweater, sits at a desk in a classroom filled with wooden desks and chairs. She leans over to replace the batteries in a digital timer used for classroom activities, demonstrating resourcefulness and attention to detail. The room is decorated with a whiteboard covered in colorful marker scribbles and motivational posters, adding a vibrant touch to the educational environment. The teacher's focused expression and the act of replacing the batteries in the timer, which is placed next to a stack of papers, highlight her commitment to ensuring the smooth operation of classroom tools.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's face and hand generation in the video have issues."
}
] |
seed44_2799
|
videos/HRA_part1/2799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark green jacket, beige shirt, and brown trousers, is seen on set with a weasel perched on his shoulder. The weasel, with its sleek body and curious eyes, suddenly leaps off the director's shoulder, mid-air, creating a moment of unexpected levity. The director, maintaining his composure, watches the weasel's acrobatic jump with a mix of amusement and surprise, all captured against the backdrop of a bustling movie set.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2232
|
videos/HRA_part0/2232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 green apron over a gray shirt and dark pants, runs down a dimly lit corridor in a large cinema complex. The hall is lined with red carpeting and features a series of doors leading into various screening rooms. The man's facial hair and glasses are distinctive, and he carries a cleaning tool in his right hand. As he sprints, his eyes are set forward, and he passes by a sign with movie titles and showtimes, creating a sense of urgency in the vast, quiet space. The scene captures the hurried pace and isolated environment of the janitor's duties within the cinema.]"
},
{
"from": "gpt",
"value": "Normal. The man's legs are deformed, and his arms are also deformed."
}
] |
seed46_253
|
videos/HRA_part2/253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent peacock, resplendent in its vivid blue and green plumage, struts regally across a lush, verdant garden, the sunlight dappling its feathers in a mesmerizing play of light and shadow. Its proud head, adorned with a striking crest, swivels gracefully as it surveys its domain. Suddenly, the peacock spreads its spectacular tail, revealing an eye-popping display of iridescent ocelli that seem to shimmer with an otherworldly glow. The air is filled with the rich, earthy scents of the foliage surrounding the bird, adding depth to this enchanting scene.]"
},
{
"from": "gpt",
"value": "Bad. The peacock's feathers in the video are generated blurry, the face is distorted, and there are multiple legs generated."
}
] |
seed42_2179
|
videos/HRA_part0/2179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, donning a dark green winter jacket, gray gloves, and a matching hat, diligently shovels snow from a pathway in front of a red-brick building with a yellow door. Snowflakes continue to fall gently, accumulating on the ground and surrounding trees. The man, with a serious yet focused expression, works methodically, clearing the path section by section. His breath visible in the cold air, he pauses momentarily, looking up at the sky as if assessing the weather conditions, before resuming his task with renewed determination.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers and eyes in the video have generation issues."
}
] |
seed42_2205
|
videos/HRA_part0/2205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow sports bra, black leggings, and white running shoes, runs past a series of modern apartment complexes. She has a focused look on her face, her brown hair tied back in a ponytail, and wears a small backpack. The apartments feature large windows, balconies with plants, and are painted in shades of blue and green. The scene is set in the late afternoon, with the sun casting long shadows and highlighting the architectural details of the buildings. In the distance, lush trees provide a natural contrast to the urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's running in the video is very unsmooth, and her movements are uncoordinated."
}
] |
seed46_1283
|
videos/HRA_part2/1283.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man in casual attire, consisting of a gray t-shirt, dark pants, and brown shoes, stands on a green ladder propped against a brown house, engaged in the task of cleaning the rain gutters. He holds a white bucket in his right hand and uses his left hand to scoop out debris from the gutter. The scene is set against a clear blue sky and lush green foliage, with the man's focused expression and determined posture highlighting his commitment to completing the job. The house's exterior, featuring beige siding and brown trim, provides a backdrop for the man's efforts, emphasizing the domestic nature of the activity.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and arms are deformed."
}
] |
seed44_2168
|
videos/HRA_part1/2168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly rendered subtropical moist forest, a peculiar scene unfolds: a doctor, clad in a crisp white lab coat over khaki shorts and a blue polo shirt, kneels beside a serene pool. Nearby, a badger, unusually sporting a tiny red swim cap, paddles leisurely in the clear waters, its eyes closed in blissful enjoyment. The lush vegetation surrounds them, with sunlight filtering through the dense canopy, casting dappled shadows on the ground. This unexpected encounter between a human doctor and a swimming badger in the heart of a lush forest creates a captivating and surreal moment.]"
},
{
"from": "gpt",
"value": "Normal. The badger in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_2116
|
videos/HRA_part1/2116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinguished by his crisp, white button-down shirt and black apron, stands in a modern, minimalist living room with large windows and wooden floors. He is meticulously assembling a piece of furniture, focusing intently on aligning the components. The room is sparsely decorated, featuring a simple gray couch and a few abstract art pieces hanging on the walls. Natural light filters in from the windows, casting a warm glow on the scene as the waiter, now with sleeves rolled up, carefully tightens screws and fits parts together, demonstrating his unexpected handyman skills in a domestic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1229
|
videos/HRA_part1/1229.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter wearing a classic black suit and white shirt is seen playfully leaping over a miniature, cartoonish giraffe mascot positioned in the middle of a vibrant, bustling restaurant. The mascot, with its signature long neck and polka-dotted pattern, stands out against the lively backdrop of tables, chairs, and happy diners. The waiter's leap is captured mid-air, adding a touch of surreal humor to the composition. Behind him, the restaurant's interior is filled with patrons enjoying their meals, unaware of the unusual event unfolding before them.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are distorted, face is contorted, and legs are twisted."
}
] |
seed44_1777
|
videos/HRA_part1/1777.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city square, under the soft glow of streetlights and the clear night sky, a diverse group of individuals, including a man with a beard, a woman with glasses, and another woman with a ponytail, are all looking intently at something above them. Their postures and facial expressions convey a sense of awe and wonder, suggesting they are captivated by an extraordinary sight in the urban landscape. Among them, a man with a beard and a woman with glasses stand side by side, both gazing upwards with intense focus. Beside them, a woman with her hair in a ponytail also looks up, her face reflecting a mix of surprise and fascination. All around, the city continues its nightly activities, but these people remain transfixed, united in their shared attention to an unseen marvel overhead.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1260
|
videos/HRA_part2/1260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds where a woman, clad in a vibrant red swimsuit, is swimming alongside a chimpanzee in a serene, tropical pool enclosed by lush greenery. The chimpanzee, also adept in the water, playfully interacts with the woman, showcasing a unique bond between human and primate. Both share moments of laughter and joy, with the chimpanzee occasionally climbing onto a floating device designed for aquatic adventures. The woman's expressive face and engaging demeanor, coupled with the chimpanzee's animated expressions, create a heartwarming narrative of interspecies friendship in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The gorilla's hand undergoes a mutant deformity. The arm suddenly becomes longer."
}
] |
seed44_2116
|
videos/HRA_part1/2116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, distinguished by his crisp, white button-down shirt and black apron, stands in a modern, minimalist living room with large windows and wooden floors. He is meticulously assembling a piece of furniture, focusing intently on aligning the components. The room is sparsely decorated, featuring a simple gray couch and a few abstract art pieces hanging on the walls. Natural light filters in from the windows, casting a warm glow on the scene as the waiter, now with sleeves rolled up, carefully tightens screws and fits parts together, demonstrating his unexpected handyman skills in a domestic setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand appears deformed, and a wooden frame suddenly appears in his hand."
}
] |
seed46_2242
|
videos/HRA_part2/2242.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 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 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's head and hands, as well as the dog, have generation issues; the dog appears with two tails and distorted limbs in the middle frames."
}
] |
seed42_1086
|
videos/HRA_part0/1086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of an ibis's face, its piercing yellow eye set against a backdrop of dark feathers, commands attention. The bird's distinctive curved bill, a striking contrast to its plumage, adds character. Its textured feathers, a mix of brown and black, envelop the head, while the yellow iris and bill tip pop against the dark plumage. The ibis's head tilts slightly, revealing a patch of bare red skin, and its textured feathers frame the captivating facial features, capturing the essence of this unique bird species.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2459
|
videos/HRA_part0/2459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brightly lit classroom filled with educational toys and posters, a caring teacher, dressed in a yellow shirt and khaki pants, gently wipes the face of a young chimpanzee sitting attentively on a small chair. The chimpanzee, wearing a tiny blue cap, looks intently at the teacher, who uses a soft, white cloth to clean its face. The scene conveys a sense of nurturing and education, with the teacher's kind demeanor and the chimpanzee's attentive behavior highlighting the bond between them.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1693
|
videos/HRA_part0/1693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful red fox, standing on its hind legs in a grassy meadow under a twilight sky, wears a green bow tie and a brown top hat, adding a whimsical touch to the scene. It dances energetically, with the focus on its expressive face, showing pure joy and playfulness. The fox continues to dance, now surrounded by a group of admiring woodland creatures, including rabbits, squirrels, and birds, all watching in delight from the edge of a dense forest. The fox performs a final dance move, leaping into the air with its front paws raised, against the backdrop of the setting sun, casting a warm golden glow over the entire meadow.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_3155
|
videos/HRA_part1/3155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a red jacket and black pants, is scaling an indoor climbing wall with intense focus, framed by a large window that bathes the scene in natural light. The gymnasium's high ceiling and climbing wall provide a spacious setting, while motivational posters and equipment add context to the environment. The climber's left hand grips a green hold, their right hand poised to grab a blue hold, and both feet are firmly planted on orange footholds, illustrating their progress up the wall. Their backpack rests on the floor, and a climbing harness and helmet ensure safety during the ascent.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2249
|
videos/HRA_part2/2249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, dressed in full gear except for a red chicken hat, crawls through a dimly lit, misty hot springs area. The water reflects the ambient light, creating an ethereal glow around the unique character. Surrounded by the steamy, rocky landscape of the hot springs, the firefighter continues to crawl, adding an element of intrigue to the surreal setting.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the firefighter in the video has issues."
}
] |
seed46_1192
|
videos/HRA_part2/1192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, dressed in a gray jacket and blue jeans, is seen crawling on the floor of a large, echoing space, perhaps a warehouse or a vast indoor market filled with various shops. His attention is riveted on an elephant figurine, intricately crafted and positioned nearby. The camera angle shifts to reveal the expansive ceiling and the bustling activity of shoppers in the background, adding a sense of scale and life to the composition. This juxtaposition of the focused janitor, the detailed elephant sculpture, and the lively shopping environment creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. There are crawling movements, but the limbs are uncoordinated, the person is sliding, the movements are not continuous."
}
] |
seed46_1944
|
videos/HRA_part2/1944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large silverback gorilla is depicted in a dense, lush forest, illuminated by patches of sunlight filtering through the canopy. Initially, it stands powerfully on all fours, its muscles rippling under its dark fur. It then charges forward, running with a burst of energy, showcasing its strength and agility. The gorilla's movement is captured in a series of dynamic poses, highlighting its powerful build and the determination in its eyes, set against the vibrant greenery of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The facial and limb generation of the silverback gorilla in the video is problematic."
}
] |
seed42_223
|
videos/HRA_part0/223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 interior resembling a bank, a muscular firefighter, now a space hero, crawls through a narrow air duct lit by blue emergency lights. Dressed in a high-tech firefighting suit with a red helmet, he stealthily moves forward on a mission. He continues crawling, his gear and determination evident, as the dimly lit vent and complex machinery surround him. Suddenly, the focus is on his intense face, showcasing his resolve through the visor of his helmet, as he prepares for action. Lastly, our hero is seen in a crouched position, ready to leap into danger, his advanced firefighting equipment at the ready, within the confined space of the air duct.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3209
|
videos/HRA_part2/3209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man in a red t-shirt and black shorts is depicted running alongside a kangaroo on a dusty trail surrounded by lush vegetation, both appearing energetic and engaged in the activity. They run together on a dirt path amidst dense greenery, the kangaroo bounding effortlessly beside the man, who maintains a steady pace. The scene captures the unique companionship between the man, dressed casually in a red top and dark shorts, and the kangaroo, as they traverse the natural environment together. The duo continues their run through the vibrant landscape, the kangaroo's powerful legs propelling it forward in sync with the man's strides, highlighting their shared rhythm and connection amidst the verdant scenery.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has missing limbs, a blurry face, and the kangaroo is deformed overall."
}
] |
seed44_1751
|
videos/HRA_part1/1751.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful 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": "Bad. The teacher's movements while bathing the dog in the video are very unsmooth and uncoordinated."
}
] |
seed44_1508
|
videos/HRA_part1/1508.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint beachside store, a young cashier, wearing a red apron over a white t-shirt and blue jeans, interacts with customers against a backdrop of ocean views through the window. Moments later, the focus is on the cashier, who is attentively counting change for a customer, with the sound of the ocean subtly heard in the background. Then, the cashier is shown organizing items on the counter, the ocean's calming presence visible outside. Lastly, the scene captures the cashier's hands as they handle transactions, the ocean view providing a serene backdrop throughout the interactions. Note: The term 'crawling' was not included as it does not fit naturally into the scene without causing confusion or requiring a scene transition, which is against the guidelines.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_201
|
videos/HRA_part0/201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black panther is filmed in high definition, gently caressing a log with its paw in a lush, green rainforest. The panther, with piercing yellow eyes, rests its massive head on the log, showcasing its strength and grace. It then proceeds to rub its cheek against the log, marking its territory, while the camera captures every detail of its luxurious fur and the intricate textures of the forest environment. The scene is set in a dense jungle, with sunlight filtering through the canopy, highlighting the panther's sleek silhouette and the vibrant foliage surrounding it.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1771
|
videos/HRA_part0/1771.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 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, 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": "Bad. The police officer's movements are not smooth, and the dog's walking movements in the video are also not smooth."
}
] |
seed42_2382
|
videos/HRA_part0/2382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and name tag, is fixing a mountain bike in a community center. The space is filled with various tools hanging from the walls, and the officer is seen working intently on the bike's rear wheel. He wears a utility belt with a radio and other equipment, emphasizing his official role. The bicycle, with its vibrant red frame, is partially disassembled, showing the officer's commitment to helping the community beyond his law enforcement duties. The scene takes place indoors, with fluorescent lights casting a warm glow on the officer and the bike, highlighting the act of service in a public space.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are deformed, the arm is generated with problems, and the bicycle is also deformed."
}
] |
seed46_1965
|
videos/HRA_part2/1965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully against a vivid blue sky, its keen eyes scanning the terrain below for prey. Its compact body, clad in brown and gray plumage, cuts through the air with agility. The bird's hooked beak and sharp talons are prominent as it banks sharply, casting a fleeting shadow on the green landscape. Against the clear, cloudless sky, the sparrowhawk's silhouette is framed by the distant horizon, highlighting its strength and freedom in flight.]"
},
{
"from": "gpt",
"value": "Normal. The sparrowhawk's flight in the video is basically normal, with only slightly uncoordinated movements."
}
] |
seed44_1627
|
videos/HRA_part1/1627.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 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 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": "Bad. The character's face and limbs generation in the video have issues."
}
] |
seed44_2828
|
videos/HRA_part1/2828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 uniformed police officer, donning a navy blue cap and sunglasses, runs along the sandy shore of a bustling beach resort, where vibrant umbrellas and lively beachgoers fill the background. His attire includes a navy blue shirt with badge, navy blue trousers, and black shoes. The setting is a crowded beach during daytime, with the officer's movement capturing the essence of duty amidst leisure. He sprints past colorful umbrellas and animated vacationers, highlighting the contrast between his purposeful stride and the relaxed atmosphere of the resort.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's facial features in the video are generated blurry, hands and feet are deformed, the hands and feet of the police officer suddenly disappear or appear in the middle frames, and the sunshade umbrellas and vacationers in the background are generated blurry."
}
] |
seed44_1943
|
videos/HRA_part1/1943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vibrant green lizard with intricate patterns adorns its skin, positioned on a dry, cracked earth surface under a bright, cloud-dappled sky. It appears to dance, flicking its tongue and swaying its body in a manner that suggests movement to an unseen beat. The lizard's movements are fluid and energetic, its tail swishing and its limbs moving gracefully as if it's performing a choreographed routine. Despite the arid environment, the lizard's dance brings a sense of lively energy to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and tail of the lizard in the video are missing, and the head is not fully generated."
}
] |
seed44_2996
|
videos/HRA_part1/2996.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A director, wearing a black puffer jacket and dark cap, oversees a futuristic space sports event. He is surrounded by a vast, otherworldly landscape, with distant celestial bodies visible in the sky. Athletes in high-tech gear compete in zero-gravity, performing acrobatic maneuvers against the backdrop of a grandstand filled with spectators. The scene is dynamic, featuring fast-paced action and dramatic wipe transitions between shots, capturing the intensity and spectacle of the extraterrestrial competition.]"
},
{
"from": "gpt",
"value": "Bad. The director's movements can be seen in the video, but they are not continuous and smooth, there is a lack of coordination."
}
] |
seed46_2604
|
videos/HRA_part2/2604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown leather jacket and stylish glasses, stands confidently at the edge of a swimming pool, meticulously observing an ibex gracefully swimming underwater. The ibex, a sure-footed mountain-dwelling mammal, is shown in a surreal scene, effortlessly gliding through the clear blue water, its horns visible above its head. The director's focused gaze and the ibex's unusual aquatic activity create a captivating and thought-provoking visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_1042
|
videos/HRA_part1/1042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tied in a ponytail engages in a fall activity, raking leaves in her spacious backyard. Dressed in a blue shirt, denim jacket, and brown gloves, she meticulously gathers the autumn foliage. The scene is set in late afternoon, as indicated by the soft, golden light filtering through the trees. She pauses to look up, her expression one of determination mixed with a sense of accomplishment, surrounded by piles of leaves and a red wheelbarrow nearby, emblematic of the season's chores and the beauty of nature's transition.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is deformed, the leaves are flying, and the person has their eyes closed the entire time."
}
] |
seed42_154
|
videos/HRA_part0/154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a sharp navy suit, white shirt, and patterned tie, stands in a futuristic, minimalist setting, possibly a space station or advanced laboratory. She gently caresses a small, spherical piece of space debris, which is encased in a clear, protective glove, highlighting the delicate yet important task of space garbage cleanup. The gravity-defying environment adds a unique dimension to the scene, emphasizing the lawyer's role in tackling legal issues related to outer space endeavors. The background features sleek, metallic surfaces and digital screens displaying data, reinforcing the high-tech context of the cleanup operation.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2988
|
videos/HRA_part0/2988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a slender gazelle, elegantly attired in a black apron and cap, diligently wipes down a wooden countertop with a green cloth. The setting is a quaint, rustic grocery store, filled with shelves of produce and goods. The gazelle, with its distinctive horns and graceful demeanor, performs the task with meticulous care, embodying an unexpected yet captivating scenario behind the register.]"
},
{
"from": "gpt",
"value": "Normal. The antelope can be clearly seen using a green cloth to wipe the wooden counter in the video, with basically normal movements, but there is some lack of coordination."
}
] |
seed46_1204
|
videos/HRA_part2/1204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 muscular man wearing a beige tank top and khaki cargo shorts jumps powerfully into the air, set against the vivid backdrop of a subtropical desert. The scene captures him mid-leap, showcasing his athletic prowess, with the desert landscape featuring rocky outcroppings and distant mountain ranges bathed in the golden hues of the setting sun. The man's intense focus and the stark beauty of the desert environment combine to create a striking visual narrative, highlighting the contrast between human strength and the vastness of nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1912
|
videos/HRA_part2/1912.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished, bald musician, donning a black turtleneck, focuses intently on fixing a leaky faucet in an upscale bathroom with marble countertops. Initially, he looks thoughtful, holding a wrench and examining the faucet. Moments later, he is seen tightening the faucet with the tool, his sleeves rolled up, revealing a tattoo on his arm. He then tests the faucet, turning it on and off, ensuring no leaks remain. Finally, he wipes his hands on a towel, looking satisfied with his handiwork, all set against the backdrop of a luxurious bathroom with a marble sink and countertop.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes, and the hands appear deformed. The faucet and hand appear deformed."
}
] |
seed42_2136
|
videos/HRA_part0/2136.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 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 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": "Good. No obvious issues."
}
] |
seed42_1653
|
videos/HRA_part0/1653.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged director, balding with graying hair, stands on a vibrant red carpet at a film festival, his eyes welling up with tears. He wears a classic black tuxedo, complete with a bow tie and a white pocket square, his attire reflecting the formal event. In the next scene, he is seen wiping away tears with a handkerchief, his emotional response to a significant moment captured in high definition. Throughout the footage, the director's facial expressions convey a range of emotions, from initial composure to visible vulnerability, all set against the backdrop of the glamorous film festival setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated, there are issues with the eyes, and the paper in his hand is generated unreasonably."
}
] |
seed46_2355
|
videos/HRA_part2/2355.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman in a yellow swimsuit, adorned with a floral-printed headscarf, laughs joyously as she swims in a clear blue pool, surrounded by lush greenery. Accompanied by a playful golden retriever, who energetically paddles alongside her, they both exude pure delight. The woman's infectious laughter and the dog's wagging tail encapsulate the essence of their shared aquatic adventure, set against a backdrop of swaying palm trees and bright sunlight filtering through the leaves, casting dappled shadows on the water's surface.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1361
|
videos/HRA_part2/1361.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space opera setting, a cashier, dressed in a metallic green costume with silver accents, is seen crawling across a high-tech stage filled with holographic displays and neon lights. The cashier, wearing a helmet with a transparent visor, moves slowly and deliberately, as if navigating through a complex transaction or performing a ritualistic dance. The background is filled with an audience of alien species, all watching intently as the cashier completes their task, emphasizing the unique blend of everyday life and dramatic performance in this cosmic environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's arms are twisted, hands are distorted, face is contorted, and legs are deformed."
}
] |
seed46_2301
|
videos/HRA_part2/2301.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful 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. The man's hand and fork both became deformed and distorted."
}
] |
seed44_303
|
videos/HRA_part1/303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, open ocean scene where sunlight filters through the water's surface, illuminating a majestic manta ray as it glides effortlessly through the clear blue depths. The manta ray, with its impressive wingspan, showcases its graceful movements, framed against the vibrant coral reef below. Its dark dorsal side contrasts sharply with the lighter underbelly, creating a stunning visual as it maneuvers with fluidity. Nearby, smaller fish swim alongside the manta ray, highlighting the peaceful coexistence in the underwater ecosystem. The scene is serene and captivating, offering a rare glimpse into the beauty of marine life.]"
},
{
"from": "gpt",
"value": "Normal. The manta ray's fins in the video are deformed, and the eyes have not been generated."
}
] |
seed42_2639
|
videos/HRA_part0/2639.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical scene, a costumed individual, dressed as a rhinoceros, leaps dynamically across a vast, cosmic landscape, dotted with floating celestial orbs. Simultaneously, in a corner of this otherworldly setting, a solemn, space-themed funeral procession takes place, with attendees dressed in futuristic attire, paying their respects. Amidst this surreal backdrop, a figure, dressed as a stereotypical grocery store cashier, complete with a checkered shirt and name tag, stands at an unconventional checkout counter, processing transactions for the peculiar gathering, adding an element of mundanity to the extraordinary event.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2281
|
videos/HRA_part1/2281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a cosmic event unfolds as a theoretical white hole explosion is depicted with vibrant colors and swirling celestial patterns, forming an ethereal, mesmerizing spectacle in the background. In the foreground, a graceful woman, wearing a flowing white dress, gently caresses an abstract representation of the universe, symbolized by a large, luminous orb, evoking a sense of connection and reverence for the mysteries of the cosmos. The woman's serene expression and delicate touch convey a message of harmony and unity between humanity and the infinite expanse of space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3071
|
videos/HRA_part2/3071.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut, clad in a spacesuit adorned with patches and equipped with a jetpack, orbits the Earth while holding a moose, its antlers visible. Below, on a pristine planet, a worker in a blue uniform tends to a pool, where a moose swims leisurely, its large frame gliding through the crystal-clear water. The worker, wearing a blue cap, looks up at the space-suited figure and the orbiting moose, a sense of wonder in their eyes. This juxtaposition of scenes captures the surreal and unexpected elements of life in space and on Earth.]"
},
{
"from": "gpt",
"value": "Normal. Missing the pool and the character in the blue uniform."
}
] |
seed42_1692
|
videos/HRA_part0/1692.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, donning a black vest and bow tie, stands in an opulent dining room, his hand gently caressing the mane of a majestic lion, which sits calmly beside an elaborately set table. The room is richly decorated with ornate chandeliers, paintings, and plush red curtains, creating a surreal juxtaposition between the wild animal and the refined setting. The lion, appearing relaxed and almost domesticated, looks up at the waiter with a sense of trust, as if it is a cherished pet in this unusual environment.]"
},
{
"from": "gpt",
"value": "Bad. The server's movements while petting the male lion in the video are not smooth and coordinated."
}
] |
seed42_1072
|
videos/HRA_part0/1072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, donning a casual gray shirt and black cap, is shown engaged in an unexpected task: unclogging a drain. In the first scene, he is kneeling on a hardwood floor, attentively examining a drain with a serious look on his face. Next, he is seen plunging the clogged drain with a red plunger, demonstrating his hands-on approach to problem-solving. Following this, the director is depicted using a drain snake to clear the blockage, his expression one of determination. Lastly, he inspects the drain once more, now clean, with a look of satisfaction, his casual attire contrasting with his professional role.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_23
|
videos/HRA_part2/23.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, tropical dry forest, a small, slender weasel with golden-brown fur and a long, bushy tail is seen interacting with its environment. It gently caresses the rough bark of a tree with its nose, then playfully sniffs and rubs against a vibrant green leaf, showcasing its curious nature. The weasel then explores the forest floor, sniffing at various plants and twigs, before it tenderly touches a fallen branch with its paw, as if showing affection to its natural habitat. Throughout the scene, the rich textures of the forest, from the rugged tree trunks to the lush foliage, are captured in stunning detail, providing a vivid backdrop for the weasel's intimate moments.]"
},
{
"from": "gpt",
"value": "Normal. The weasel's paws in the video have generation issues, with the front paws twisting and deforming in the middle frames."
}
] |
seed44_2858
|
videos/HRA_part1/2858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh cod fish is presented on a bed of ice, its body glistening under bright lights. The fish has a distinct silver hue, with large, clear eyes and tightly closed gills, indicating its freshness. Its scales reflect the light, and the texture of the skin is smooth yet firm. In the background, other seafood items can be seen, hinting at a bustling market setting where various fish are displayed on ice. The focus remains on the cod, which takes center stage, showcasing its size and quality in vivid detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1993
|
videos/HRA_part2/1993.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Caspian tern, the largest species, soars over a coastal landscape, its gray and white plumage gleaming under the sun. It has a bright orange-red bill with a black tip, and its wingspan stretches wide as it glides over the water. Perched on a sandy shore, the bird preens its feathers, revealing its distinctive black crest and elegant posture. In flight again, the tern's powerful wings propel it forward, and it banks sharply, showcasing its agility against a backdrop of rolling clouds and shimmering sea. Finally, diving gracefully into the water, it emerges triumphant with a small fish in its beak, demonstrating its hunting prowess in stunning detail.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions that the terns perch on the beach and fly to the sea with small fish surfacing, but this is not shown in the video."
}
] |
seed42_1419
|
videos/HRA_part0/1419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a helmet, is sprinting with intense focus through a lush, green park. He's gripping a fire hose as he runs beside a serene lake, where ducks are seen swimming in the background. The scene conveys a sense of urgency and determination, with the firefighter's muscular physique straining against his equipment. The park is filled with vibrant greenery and tall trees, providing a stark contrast to the firefighter's urgent mission. As he races past a wooden bench and a playground, the peaceful setting underscores the potential danger lurking nearby.]"
},
{
"from": "gpt",
"value": "Bad. Hands and arms suddenly disappear, becoming deformed, and the legs also deform while running."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.