video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1192
|
videos/HRA_part0/1192.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 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 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": "Good. No obvious problems."
}
] |
seed46_1368
|
videos/HRA_part2/1368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 attractive male actor, reminiscent of Chris Hemsworth, is seen in a modern, minimalistic living room with large windows and plenty of natural light. He wears a navy blue t-shirt, dark jeans, and a wedding band, giving him an approachable, everyman appeal. The actor is intently focused on assembling a piece of flat-pack furniture, such as an IKEA dresser, using a screwdriver and following the instruction manual. The scene conveys a sense of relatability and domesticity, as the celebrity navigates the familiar challenge of putting together home furnishings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1081
|
videos/HRA_part1/1081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil orchard setting, lush greenery surrounds a badger as it curiously explores its environment. The badger, with its distinctive black and white striped face, sniffs the air, then gently caresses the bark of an old apple tree with its paw. The camera captures the badger's actions in detail, focusing on the texture of the tree bark and the animal's fur. The scene is peaceful, with the soft sounds of nature providing a soothing soundtrack to the badger's gentle interaction with its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2678
|
videos/HRA_part1/2678.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, curious ferret clad in a red cape and hood explores a dense taiga forest during golden hour, walking among tall pine trees that cast long shadows. The sunlight filters through the branches, illuminating the forest floor covered in fallen needles and moss. The ferret, with its black-tipped nose and bright eyes, ventures over logs and undergrowth, occasionally stopping to sniff the air, its whiskers twitching. Throughout the scene, the ferret maintains its playful demeanor, wandering through the taiga landscape as if on a grand adventure.]"
},
{
"from": "gpt",
"value": "Normal. The ferret in the video walks very awkwardly, with uncoordinated movements."
}
] |
seed46_1213
|
videos/HRA_part2/1213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic, casually dressed woman walks down a city street, passing by various urban elements such as a fire hydrant, a streetlight, and a parked car, all while maintaining a confident stride. She wears a brown jacket, blue jeans, and black shoes, with her hair tied back in a bun, showcasing her energetic yet relaxed demeanor. The cityscape includes a yellow taxi in the background, adding to the bustling atmosphere. As she continues her journey, the urban environment unfolds around her, capturing the essence of city life.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2203
|
videos/HRA_part0/2203.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic man named Jay, donning a gray blazer, black t-shirt, and jeans, stands in a dimly lit room with a warm color tone. Initially, he is seen in profile, gazing into the distance with a reflective look. Jay then turns to face the camera, his expression conveying a sense of determination and strength. Next, he smiles warmly, exuding confidence and approachability. Finally, Jay closes his eyes, appearing to savor a private moment of joy, all while the ambient lighting enhances the intimate atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1703
|
videos/HRA_part2/1703.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, rustic kitchen, two young children, a boy and a girl, both wearing colorful aprons over their clothes, stand on small wooden stools to reach the sink. The girl, with her hair tied in pigtails, holds a wrench with determination while looking intently at the faucet. The boy, wearing glasses, assists by shining a flashlight on the dripping tap, their teamwork highlighted by the warm, golden glow of the overhead lights. The sink is surrounded by decorative tiles, adding a homely touch to the scene. Tools and parts are neatly arranged on the countertop beside them, emphasizing the organized approach to fixing the leaky faucet.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2187
|
videos/HRA_part1/2187.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse 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": "Good. Basically no issues."
}
] |
seed42_1716
|
videos/HRA_part0/1716.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush temperate deciduous forest during autumn, two people, a woman in a green jacket and a man in a brown vest, are observed sitting on a blanket, engaged in a relaxed conversation. Beside them, a capybara crawls slowly across the blanket, its large size and docile nature evident. The forest floor is covered in a mosaic of fallen leaves, while the trees stand tall with their branches partially denuded, creating a dappled sunlight effect. The overall atmosphere is one of peaceful coexistence between humans and wildlife in the natural habitat of the capybara.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1009
|
videos/HRA_part2/1009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man, donning a black leather jacket, dark jeans, and a white T-shirt, is seen energetically dancing in a vast, open space, backlit by the golden hour sun. Amidst his lively moves, a tiny vole emerges from the grass, its small, curious eyes fixated on the man. The man continues to dance, oblivious to the vole's presence, his movements casting dynamic shadows across the grassy landscape. The vole watches from a safe distance, seemingly fascinated by the man's animated performance under the warm, evening light.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not fluid, and the limbs are uncoordinated."
}
] |
seed44_1185
|
videos/HRA_part1/1185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning kingfisher bird perches regally on a weathered branch that extends over a serene body of water, its vibrant blue and orange feathers glistening in the sunlight. The bird's piercing gaze is fixed on the water below, hinting at its hunting prowess. Suddenly, it takes flight, its wings a blur of color against the tranquil backdrop of the pond, surrounded by lush green foliage. As it hovers above the water, about to dive, the scene captures the kingfisher's agility and the beauty of nature in a single, captivating moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_190
|
videos/HRA_part2/190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jaguar, marked by its distinctive black spots on tawny fur, walks purposefully across a lush, green savanna landscape under the dappled shade of scattered trees. Its powerful muscles ripple beneath its coat as it strides with feline grace, the camera capturing every detail in high definition. The surroundings are alive with the sounds of nature, from chirping birds to the distant call of other wildlife, creating an immersive environment that highlights the beauty and power of this wild cat in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2067
|
videos/HRA_part2/2067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown bat with intricate wing details is seen crawling along a cave floor, illuminated by a soft, ambient light. It slowly makes its way across the rocky terrain, revealing its unique features in close-up. Meanwhile, in the distance, the planet Venus can be seen as a bright spot in the night sky, providing a celestial contrast to the terrestrial scene below. The bat's movements are deliberate and methodical, highlighting its adaptation to navigating dark environments, while Venus' presence adds a cosmic element to the composition.]"
},
{
"from": "gpt",
"value": "Bad. The bat's movements are uncoordinated."
}
] |
seed44_2785
|
videos/HRA_part1/2785.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 desert landscape, a well-dressed doctor, wearing a white coat, blue shirt, and khaki pants, stands next to a camel. The scene is set near traditional African villages, with huts visible in the background. The doctor, sporting a beard and glasses, holds a rope attached to the camel, which is adorned with red and blue blankets. Suddenly, the camel leaps into the air, its hind legs kicking up sand, while the doctor watches intently. The village scenery, complete with palm trees and thatched-roof huts, adds a cultural touch to this dynamic scene.]"
},
{
"from": "gpt",
"value": "Bad. The camel in the video was generated abnormally, with its limbs twisted and deformed in the middle frames, and the video does not conform to reality overall."
}
] |
seed44_1893
|
videos/HRA_part1/1893.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, spacious room filled with smoke and vibrant lights, two individuals, a man in a dark green shirt and a woman in a black top, are dancing enthusiastically. Suddenly, they stop, looking startled as a beam of green light illuminates them. An alien creature, with large, expressive eyes and a smooth, gray skin tone, descends from above, capturing their attention. The extraterrestrial being, adorned with a metallic, futuristic outfit, lands gracefully beside them, prompting the humans to react with a mix of fear and curiosity. Despite the initial shock, the trio begins to move in unison, engaging in an otherworldly dance, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1246
|
videos/HRA_part0/1246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 full uniform complete with a hat, rests peacefully on a bench in a quiet, empty city park during the daytime. The serene atmosphere is highlighted by the soft play of sunlight filtering through the trees, casting dappled shadows on the ground. The officer's hat is tilted down, partially obscuring their face, while they lean back against the wooden slats of the bench, their body language conveying a sense of well-deserved rest. Beside them, a water bottle sits on the bench, and in the distance, the peaceful urban landscape is visible, punctuated by the occasional passerby and the gentle sway of tree branches.]"
},
{
"from": "gpt",
"value": "Normal. The proportions of the police officer's hand in the video are not well balanced."
}
] |
seed44_1095
|
videos/HRA_part1/1095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 through a clear blue sky, its sleek silhouette framed against the horizon. It dives sharply, wings tight to its body, chasing an unseen prey across the vast expanse. Its sharp eyes, focused and intense, scan the terrain below for any hint of movement. The bird then lands on a branch, its feathers ruffled by the wind, revealing a striking pattern of brown and white. It sits still, perched regally, surveying its domain with a fierce gaze, a true ruler of the skies.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, and there is a sudden change."
}
] |
seed42_308
|
videos/HRA_part0/308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, with distinctive tufted ears and a rufous-colored coat, leaps from a rocky outcropping, its body arched and legs extended, showcasing its agility and power. The background features lush vegetation and trees, highlighting the wild, natural habitat of this impressive feline. The scene is captured in high definition, allowing every detail of the bobcat's muscular form and the surrounding environment to be clearly visible during the jump.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2312
|
videos/HRA_part0/2312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male chef, donning a white chef's uniform with black stripes and a matching cap, meticulously washes dishes in a commercial kitchen. The room is illuminated by bright overhead lights, casting a glow on the stainless steel sink and countertops. Steam rises from the hot water, creating a misty atmosphere. The chef's sleeves are rolled up to his elbows, revealing tattoos, as he focuses intently on cleaning each plate with precision and care. In the background, the bustling kitchen is visible, with other chefs preparing meals and the sounds of clattering pots and sizzling pans adding to the lively ambiance.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1433
|
videos/HRA_part2/1433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene, two children, a boy and a girl, sprint across a grassy area with wide smiles, dressed in casual play clothes—a red T-shirt and blue shorts for the boy, and a floral dress for the girl. Suddenly, the focus is on the boy as he runs with gleeful determination. Then, the girl takes center stage, her pigtails bouncing as she races forward. The action culminates with both children laughing and running together, their eyes filled with joy, all while a gorilla statue stands watchfully in the background, adding a touch of whimsy to the playful atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The little girl's legs and hands show deformities."
}
] |
seed44_1994
|
videos/HRA_part1/1994.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged female nurse sits on a wooden chair in a cozy, softly lit room, wearing a light blue scrubs top and black pants. She crochets a vibrant, multicolored blanket with yellow, orange, and red hues, her hands moving skillfully as she focuses on her craft. The room is filled with the warm glow of a standing lamp, casting a gentle light on the scene. Behind her, a large window reveals a lush, green outdoor landscape, providing a serene backdrop for her meditative activity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2340
|
videos/HRA_part0/2340.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cashier, wearing a red apron over a casual outfit of a gray t-shirt and khaki pants, takes a break from his usual duties to fix a leaky faucet. He is shown kneeling before a bathroom sink, tools in hand, with a look of determination on his face. The scene is set in a small restroom, with beige walls and a window casting natural light onto the countertop. As he works, the camera captures his focused expression and the intricate details of the plumbing, highlighting the contrast between his customer service role and his unexpected handyman task.]"
},
{
"from": "gpt",
"value": "Bad. No tool was generated."
}
] |
seed46_1844
|
videos/HRA_part2/1844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a friendly-looking cashier, wearing a red apron with a name tag, works behind a counter at an airport gift shop. Unexpectedly, a small, playful ferret emerges from the pocket of the cashier's apron, peeking its head out curiously. The background features a bustling airport terminal with passengers and luggage, emphasizing the unusual combination of elements. Moments later, the focus shifts to a clear swimming pool, where the same cashier, now in swimwear, happily swims with the ferret floating nearby on a small inflatable raft, both enjoying a break from the busy airport environment.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the small ferret coming out of the cashier's apron pocket."
}
] |
seed44_134
|
videos/HRA_part1/134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, identifiable by their beret and smock, kneels on a lush, alien landscape, sketching a capybara. The capybara, depicted in a relaxed posture, is the focal point, sitting amidst Martian flora. The scene is illuminated by the vibrant hues of a Martian sunset, casting an ethereal glow across the terrain. The artist's concentrated expression and the capybara's calm demeanor create a sense of tranquility, enhanced by the distant, rugged Martian mountains and the unique atmospheric conditions of the planet, which contribute to the vivid sunset colors. The artist's tools, including a palette and brushes, are scattered nearby, adding to the creative atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2565
|
videos/HRA_part0/2565.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, a young female cashier, clad in a green jumpsuit with a name tag, works diligently at a market specializing in hydroponic produce. She crawls under the counter, surrounded by vibrant, healthy greens growing vertically against the back wall, illuminated by LED grow lights. The space agriculture setting is evident from the lush plants and the advanced technology used for cultivation. The cashier's actions are focused and purposeful, highlighting the unique challenges and innovations of farming in space, all within the confines of a bustling space station market.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are very unsmooth and uncoordinated."
}
] |
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 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 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": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2239
|
videos/HRA_part0/2239.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint, dimly lit restaurant, a neatly dressed waiter, wearing a black apron over a crisp white shirt and black trousers, is seen wiping a table with a white cloth. Unexpectedly, a playful gray cat emerges, rubbing against the waiter's leg. The waiter pauses, gently bending down to pet the friendly feline before resuming his task, the cat now seated beside him, seemingly enjoying the attention in the cozy dining space.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2104
|
videos/HRA_part0/2104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crisp white shirt and black vest, stands in a spacious living room with hardwood floors and a large window, engaging in an unusual task. He is diligently assembling a wooden table using various tools, demonstrating unexpected handyman skills. As the scene progresses, the fully assembled table is revealed, complete with a tablecloth and set for a meal, blending elements of his professional service role with a domestic setting. The waiter then proceeds to polish the silverware, juxtaposing his traditional duties with the earlier DIY activity, all within the same elegant residential space.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_2386
|
videos/HRA_part0/2386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, intricate fish with blue fins and a yellow body swims serenely in a clear, turquoise underwater environment, surrounded by lush green seaweed gently swaying in the current. Nearby, a school of smaller, silvery fish dart and weave, their movements synchronized and graceful, creating a mesmerizing display of aquatic life against the vivid backdrop of the underwater world. Above, rays of sunlight filter through the water's surface, casting dappled light on the scene below, highlighting the beauty and tranquility of the ocean depths.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1336
|
videos/HRA_part1/1336.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman, balding with a neatly trimmed beard, sits in a cozy library filled with bookshelves, wearing a brown jacket and a yellow shirt. He speaks animatedly about his writing process, gesturing expressively with his hands. Behind him, a large window frames a view of a lush garden, providing a picturesque backdrop. The room is illuminated by warm lighting, creating an inviting atmosphere that enhances the intimacy of the conversation. As he talks, his eyes sparkle with passion, conveying his deep connection to the art of storytelling.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has a hand that is not fully formed and there is something wrong with his eyes."
}
] |
seed46_1198
|
videos/HRA_part2/1198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A beautifully filmed close-up of a vibrant, pink-fleshed salmon fillet, glistening under bright lights on a clean, white plate. The salmon is artfully presented with a slice of lemon and a scattering of fresh dill sprigs, enhancing its visual appeal. In the next shot, the camera focuses on a whole salmon, its scales shimmering, resting on a bed of ice, surrounded by greenery, creating a fresh, market-like atmosphere. Finally, the video captures a chef expertly filleting a salmon with precise cuts, the knife gliding smoothly through the fish, accompanied by the soft sound of slicing, against a backdrop of a busy kitchen.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2615
|
videos/HRA_part1/2615.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, plump hedgehog with distinctively sharp, brown spines traverses a lush, green garden, walking determinedly over mossy stones. It pauses briefly, its round body and curious face framed by the vibrant greenery. The hedgehog continues its journey, navigating the garden's textured path, with a wooden fence and hanging ivy leaves providing a natural, earthy backdrop. Throughout the walk, the hedgehog's spines glisten under the sunlight, highlighting its unique texture against the verdant setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1666
|
videos/HRA_part0/1666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning round glasses and a yellow sweater, sits at a wooden table cluttered with writing tools and a laptop, knitting a vibrant red scarf with large needles. The scene is set in a cozy room with a rustic wooden floor and a large window, through which daylight softly illuminates the space. On the wall hangs a large, colorful painting, adding a touch of artistic flair. The writer's hands, adorned with rings and bracelets, skillfully manipulate the knitting needles as they work on the scarf, all while surrounded by the warm, inviting atmosphere of the room.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_190
|
videos/HRA_part1/190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic jaguar, marked by its distinctive black spots on tawny fur, walks purposefully across a lush, green savanna landscape under the dappled shade of scattered trees. Its powerful muscles ripple beneath its coat as it strides with feline grace, the camera capturing every detail in high definition. The surroundings are alive with the sounds of nature, from chirping birds to the distant call of other wildlife, creating an immersive environment that highlights the beauty and power of this wild cat in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The jaguar's walking movements in the video are not very smooth and coordinated."
}
] |
seed42_2942
|
videos/HRA_part0/2942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A strong, focused woman wearing a red helmet and climbing gear scales a towering rock face, the texture of the stone rough under her hands and feet. The camera captures her intense concentration, the strain in her muscles, and the determination in her eyes. Sunlight filters through wispy clouds, casting dramatic shadows on the cliffside as she ascends higher, leaving the green valley far below. The scene is framed by rugged terrain, emphasizing her solitary endeavor against the vast, natural landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1793
|
videos/HRA_part1/1793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic setting, a skilled musician, dressed in a black leather jacket, plays a gleaming silver electric guitar. Nearby, an enormous, friendly bear, adorned with a red bow tie, listens intently, its paw gently resting on the musician's shoulder in a gesture of companionship. Suddenly, a shimmering wormhole opens behind them, revealing a kaleidoscope of colors and swirling galaxies. The musician and the bear look into the wormhole, their expressions a mix of awe and curiosity, as they contemplate the mysteries of the universe together.]"
},
{
"from": "gpt",
"value": "Normal. The bear's movements in the video are not smooth."
}
] |
seed42_1619
|
videos/HRA_part0/1619.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking window cleaner, clad in a yellow high-visibility vest and dark pants, expertly maneuvers a squeegee across a large glass pane on a bright day. With a secure harness and helmet protecting him, he focuses intently on his task, ensuring crystal clear results. Perched on a platform lifted by a cherry picker, he cleans the exterior of a modern office building, the city skyline visible in the distance. As he moves, his confident posture and steady hand reveal his skill and dedication to leaving each window spotless.]"
},
{
"from": "gpt",
"value": "Bad. The hand and head of the character in the video have generation issues, with the hand passing through the character's head in middle frames."
}
] |
seed44_1065
|
videos/HRA_part1/1065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 illuminated by vibrant neon lights, a worker, dressed in a sleek gray jumpsuit and wearing protective goggles, gently caresses the metallic arm of a Robot astronaut. The Robot, clad in a polished silver spacesuit adorned with intricate wiring and glowing blue accents, stands motionless yet imposing against the backdrop of high-tech equipment and advanced machinery. The scene captures a tender moment of human-robot interaction, highlighting the bond between the worker and the Robot astronaut in the vast expanse of outer space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2152
|
videos/HRA_part1/2152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 small monkey wearing a red bow tie and a golden ring on its tail is leaping from one floating bookshelf to another in a vast space library. The shelves, filled with ancient books bound in brown leather, are suspended in zero gravity, illuminated by a warm, golden light. The monkey swings its arms in excitement as it jumps, revealing a joyful, playful spirit in the cosmic setting, surrounded by stars and galaxies. The library's architecture is grand, with arches and columns made of what appears to be stardust, adding to the surreal and magical atmosphere of this extraordinary space.]"
},
{
"from": "gpt",
"value": "Bad. The little monkey's movements in the video are not smooth."
}
] |
seed46_2289
|
videos/HRA_part2/2289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, donning a straw hat, a plaid shirt, and denim overalls, is shown exerting effort as he pulls on a rope tied to a stubborn old tractor stuck in a muddy farm field. The farmer's weathered hands grip the rope tightly, his face contorted with determination, while the lush greenery and distant rolling hills provide a picturesque rural setting. The scene highlights the farmer's resilience and hard work against the backdrop of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's fingers are deformed, and the face is blurry in the video."
}
] |
seed42_3070
|
videos/HRA_part0/3070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, dressed in a brown jumpsuit and cap, is playfully crawling on his hands and knees across a stable floor, chasing after a curious horse. The horse, with a full brown mane and tail, looks back at the janitor with a sense of amusement, its hooves stepping lightly on the straw-covered ground. The stable's wooden beams and stalls provide a rustic backdrop, while the janitor's playful demeanor adds a touch of unexpected humor to the otherwise ordinary task of cleaning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1478
|
videos/HRA_part2/1478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing her uniform consisting of a white collared shirt, black pants, and a name badge, takes a break from her duties to clean the gutters of the medical facility. She stands on a ladder, her gloved hands scooping out debris, with the sunny day highlighting her dedication beyond her regular responsibilities. The video showcases her multitasking abilities, as she balances her healthcare role with the practical needs of maintaining the clinic's infrastructure, all while dressed in her recognizable nursing attire.]"
},
{
"from": "gpt",
"value": "Bad. No ladder was generated."
}
] |
seed42_188
|
videos/HRA_part0/188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, a species of wild mountain goat, is shown crawling on all fours across a rocky terrain. The scene is set in a mountainous region, with steep cliffs and rugged landscape providing a challenging environment for the animal. The ibex is depicted in a vulnerable position, moving slowly and deliberately as it navigates the uneven surface. Its body is in a low, crawling stance, highlighting its agility and strength in adapting to harsh conditions. The camera captures this intimate moment in high definition, focusing solely on the ibex as it crawls, emphasizing the creature's resilience and survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2326
|
videos/HRA_part2/2326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen laboratory, a distinguished chef wearing a pristine white chef's jacket and black trousers walks purposefully toward a high-tech, glass-enclosed antimatter containment unit, which emits a soft, eerie glow. The chef's attire is impeccably clean, contrasting with the advanced technology surrounding him. He carries a small, sleek device in his right hand, possibly a tool for interacting with the antimatter. The room is filled with stainless steel counters and equipment, giving it a modern, industrial feel. The chef approaches the containment unit with determination, ready to harness the unique properties of antimatter for an extraordinary culinary creation.]"
},
{
"from": "gpt",
"value": "Normal. The man's limbs generation in the video has problems."
}
] |
seed46_2796
|
videos/HRA_part2/2796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a yellow high-visibility jacket and hard hat, stands near a bobcat excavator on a construction site. He wipes down the machinery with a cloth, revealing the brand name on the excavator's arm. The scene is set against a backdrop of dirt and gravel, with other construction equipment visible in the background. The engineer's actions showcase the maintenance aspect of his job, highlighting his commitment to keeping the equipment clean and operational.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video is not fully shown."
}
] |
seed46_1757
|
videos/HRA_part2/1757.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant woman wearing a green tank top and khaki shorts is playfully running in a spacious, grassy area under a clear blue sky, with a koala perched on her back. The koala, clinging to her shoulder, is holding a branch, adding a touch of whimsy to the scene. The woman's joyful expression and the koala's relaxed demeanor create a harmonious and delightful moment, encapsulating the essence of carefree fun and the unexpected companionship between human and animal.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs in the video have generation issues; her fingers are not fully formed, and her face is generated blurry. The koala's limbs are missing, and its facial features are not fully generated."
}
] |
seed46_2064
|
videos/HRA_part2/2064.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of people are gathered at a pristine lake nestled in the heart of a lush, green forest, engaging in various activities. Some are wiping their feet on a large, sandy beach, preparing to enter the clear, inviting waters. Others are seated on the shore, enjoying the serene surroundings as they wipe sand from their hands and feet. The scene is peaceful, with the sound of water lapping against the shore and birds singing in the trees overhead. The lake, framed by towering pines and dotted with small boats, provides a stunning backdrop for this tranquil moment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2436
|
videos/HRA_part0/2436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A meerkat, standing upright on its hind legs, surveys its surroundings in a suburban backyard, with a wooden deck, a lush lawn, and a swimming pool in the background. The meerkat, known for its striped brown fur and alert demeanor, appears curious and engaged with its new environment. It stands on a manicured green lawn, next to a wooden deck with patio furniture, and looks towards a large, clear swimming pool, where the water shimmers under the bright sunlight. The contrast between the wild creature and the domestic setting creates a unique and unexpected visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1402
|
videos/HRA_part1/1402.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with glasses, wearing a dark green sweater over a button-down shirt, stands on a chair to change a light bulb in a room with wooden floors and a desk filled with books and writing materials. He holds the new light bulb in his right hand while his left hand grasps the existing bulb, which is attached to a simple ceiling fixture. Behind him, a large window reveals a gray, rainy day outside. The room is dimly lit by a small lamp on the desk, illuminating the clutter of papers, notebooks, and a vintage typewriter. The writer's casual attire, including khaki pants and brown shoes, contrasts with the focused determination on his face as he completes this mundane task amidst his literary surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the hands are deformed, and the legs are twisted."
}
] |
seed46_2175
|
videos/HRA_part2/2175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, golden hamster in swimwear, including water goggles and a miniature life jacket, floats on a raft in a clear, gently flowing river surrounded by lush greenery. It paddles with its tiny paws, navigating through the serene waters with determination. The hamster then jumps into the river, swimming energetically, its little body moving gracefully through the water. Finally, it rests on a rock near the riverbank, basking in the sunlight, wearing a happy expression, all set against the peaceful backdrop of a forest and a calm river.]"
},
{
"from": "gpt",
"value": "Bad. The dwarf hamster's movements in the video are not smooth."
}
] |
seed44_1178
|
videos/HRA_part1/1178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a scene reminiscent of a futuristic sci-fi film, a CGI-generated cobra, adorned with bioluminescent patterns, slithers across a metallic, interstellar platform set against the backdrop of a cosmic wormhole. The snake's scales shimmer with neon colors, creating a mesmerizing contrast against the cold, metallic surface. As it moves, the cobra passes by a series of glowing control panels, hinting at advanced technology integrated into the environment. In the distance, the swirling vortex of the wormhole pulses with vibrant hues, adding an element of mystery and wonder to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The cobra's movements in the video are not smooth."
}
] |
seed42_2566
|
videos/HRA_part0/2566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, large clam is showcased on a white plate, its intricate shell patterns visible, set against a rustic wooden table. The clam's interior is slightly ajar, revealing its succulent meat within the half-shell. Surrounding the plate are various utensils, including a fork, knife, and spoon, laid out on the worn wood surface. In the background, a blurred view of a coastal landscape hints at the seafood's fresh origin, with seagulls flying overhead and the distant horizon merging sky and sea. The clam itself is illuminated by natural light, highlighting its natural beauty and the anticipation of a delicious meal.]"
},
{
"from": "gpt",
"value": "Normal. The seagull flying in the distant scene of the video has issues."
}
] |
seed44_1165
|
videos/HRA_part1/1165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jungle environment, two young boys, one wearing a yellow t-shirt and the other in a blue shirt, are seen interacting with a small monkey. The monkey, sitting on a branch at eye level with the children, reaches out to touch the hand of the boy in the yellow shirt, who gently caresses its head in return. The second child looks on with a smile, his hands resting on the branch, as they both share a tender moment with the curious primate, surrounded by the vibrant foliage of their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2357
|
videos/HRA_part1/2357.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 hare, donning a red apron and a name tag, works diligently as a cashier in a charming store nestled deep within a lush rainforest. The store's wooden shelves are stocked with unique items, including exotic fruits, colorful fabrics, and handmade crafts. Outside, the vibrant rainforest comes alive with the sounds of wildlife and the gentle patter of rain. Suddenly, the hare takes a break and ventures outside, where it encounters a serene natural pool, its clear waters inviting for a refreshing swim amidst the emerald greenery. The hare, now in swimming attire, joyfully splashes in the pool, surrounded by the lush foliage and the calming atmosphere of the rainforest.]"
},
{
"from": "gpt",
"value": "Bad. The scene of the wild rabbit working as a salesperson was not generated, and the wild rabbit's red apron and name tag were also not generated."
}
] |
seed44_2145
|
videos/HRA_part1/2145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a green swimsuit, sits on a sandy beach near a turquoise body of water, typing away on a laptop, while a small hedgehog perches on the writer's shoulder. The hedgehog has a tiny life jacket on, matching the writer's swimwear. In another scene, the writer is shown swimming in the clear waters, with the hedgehog floating alongside in its miniature life vest, both enjoying a peaceful day at the seaside under a bright, sunny sky.]"
},
{
"from": "gpt",
"value": "Normal. The small hedgehog in the video is not wearing a mini life jacket."
}
] |
seed42_1890
|
videos/HRA_part0/1890.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a green vest and khaki pants, walks purposefully down a dimly lit hallway, pushing a squeaky cleaning cart. On the wall, a badger mascot poster from a local college, Wausau Woodchucks, adds a touch of whimsy. The scene shifts slightly to reveal more of the hallway, showcasing the linoleum floor and overhead lights. The janitor continues his journey, passing a row of lockers adorned with stickers and graffiti, while the badger poster remains visible, adding a sense of character to the otherwise mundane setting. Finally, the focus is on the janitor's interaction with the environment, as he pushes the cart with determination, the badger poster serving as a silent observer in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_313
|
videos/HRA_part2/313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished male doctor, wearing a white lab coat over a navy blue shirt, khaki pants, and brown shoes, meticulously dusts antique furniture in a well-lit room with large windows. He carefully cleans a wooden dresser, revealing the care and attention to detail he applies to his task. The doctor then moves to dust a vintage chair, his movements deliberate and focused, showcasing his commitment to maintaining the cleanliness of his surroundings. Throughout the scene, the doctor's attire remains impeccable, underscoring the contrast between his professional role and the domestic activity he performs.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hands and arms are deformed and distorted."
}
] |
seed44_1379
|
videos/HRA_part1/1379.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned chef, donning a traditional white chef's uniform with a checkered bandana, performs a dynamic pizza toss in a bustling pizzeria kitchen. The dough stretches gracefully as it rotates in mid-air, illuminated by the warm glow of overhead lights. The chef's confident expression and practiced movements highlight his expertise, while the lively atmosphere of the kitchen, filled with the sounds of sizzling pans and cheerful chatter, adds to the vibrant scene. In the background, a row of wood-fired ovens and a team of chefs busily preparing various dishes complete the authentic pizzeria setting.]"
},
{
"from": "gpt",
"value": "Bad. The chef's actions in the video are not smooth and continuous, and the tossing of the dough is very uncoordinated."
}
] |
seed42_231
|
videos/HRA_part0/231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room illuminated by the soft glow of a Martian sunset, visible through a large window displaying the red planet's horizon, two young children sit cross-legged on a wooden floor. They gently caress a small, furry gerbil sitting on a colorful blanket, their faces reflecting expressions of pure delight and wonder, as they interact with the pet in the unique, alien environment.]"
},
{
"from": "gpt",
"value": "Bad. The facial expressions, hands, and legs of the hamster and child in the video were generated abnormally."
}
] |
seed46_291
|
videos/HRA_part2/291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed doctor, wearing a white button-down shirt and khaki shorts, leaps into the air on a pristine, sandy beach, with crystal-clear water visible in the background. The doctor, who has brown hair and glasses, is captured mid-jump, displaying a sense of freedom and joy. The scene is set against a stunning backdrop of palm trees and a clear blue sky, creating a perfect blend of professional and leisure elements. The doctor's relaxed attire and the idyllic beach setting convey a sense of balance between work and personal life.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2114
|
videos/HRA_part0/2114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a branch, its distinctive black-and-white plumage gleaming under the sunlight filtering through the leaves of a large tree. The bird's eyes are sharp and alert, its beak curved and ready to snatch any unsuspecting prey. Behind it, the lush green foliage of the forest provides a stark contrast to its striking feathers, while the soft chirping of other birds creates a peaceful atmosphere. Suddenly, the magpie takes flight, its wings beating gracefully as it soars through the air, leaving a trail of black and white behind it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3007
|
videos/HRA_part1/3007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male spruce grouse, perched on a branch in a dense forest, displays its vibrant plumage featuring shades of brown, gray, and white speckles. Its red eyelids stand out against the dark eye, while its yellow bill adds a striking contrast. The bird's feathers are ruffled, perhaps due to a breeze or during a display, and it is surrounded by lush green foliage, indicating a healthy habitat. The grouse is stationary, offering a clear view of its unique features against the backdrop of a richly textured forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the capercaillie's eyes in the video has issues."
}
] |
seed46_2673
|
videos/HRA_part2/2673.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in casual attire, leaps into the air against the backdrop of a vibrant village scene. The village is set amidst lush greenery, with colorful houses lining the cobblestone streets. The student, wearing a yellow t-shirt and denim shorts, is captured mid-jump, their arms spread wide in exhilaration. The scene is filled with natural beauty, from the verdant foliage to the clear blue sky above. As the student jumps, they seem to embody the spirit of youth and adventure, their face alight with joy and energy. Behind them, the village bustles with life, with locals going about their daily routines and children playing nearby. The overall effect is one of vitality and happiness, capturing a fleeting moment of pure delight in a picturesque village setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed46_3108
|
videos/HRA_part2/3108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged male nurse with short, dark hair and glasses, wearing a pale blue scrub top and pants, carefully lifts a frail elderly patient from a hospital bed. The patient, a thin woman with short gray hair, is dressed in a hospital gown and has an oxygen tube in her nose. The nurse, with a strong yet tender grip, supports her under her arms and legs, ensuring her comfort and safety throughout the transfer. The scene takes place in a well-lit, modern hospital room, with medical equipment and a window visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the male nurse in the video is uncoordinated, and his fingers are deformed; the patient's face is also distorted, and their fingers are deformed."
}
] |
seed46_2526
|
videos/HRA_part2/2526.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giraffe, distinguished by its dark, jagged spots, gently caresses a smaller giraffe with its head, creating a tender moment in the midst of a lush, green savanna landscape. The taller giraffe, with a weathered face and long eyelashes, shows affection toward the younger one, which has lighter, less pronounced markings, standing against a backdrop of tall grasses and distant trees under a bright, sunny sky. This intimate scene captures the essence of giraffe behavior in their natural habitat, emphasizing the bond between two individuals against a vivid, verdant setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1417
|
videos/HRA_part2/1417.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lone buzzard soars gracefully across a vast, cloud-dappled sky, its wings spread wide in a display of effortless flight. Its keen eyes scan the rugged terrain below, a patchwork of sunlit earth tones and deep shadows cast by towering rock formations. The bird's majesty is further highlighted by its striking profile, showcasing its hooked beak and sharp talons as it circles overhead, a silent sentinel surveying its domain from the heavens. Against the dramatic backdrop of a sunlit landscape, the buzzard embodies the untamed spirit of nature in its purest form.]"
},
{
"from": "gpt",
"value": "Normal. The eagle flying in the video is basically normal, but there is a slight lack of coordination in the movements."
}
] |
seed42_1814
|
videos/HRA_part0/1814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large moose, adorned with a red bow tie and a top hat, stands on a wooden boardwalk illuminated by warm, golden lights. It gracefully sways side to side, as if dancing to an invisible melody, under a starlit night sky. The boardwalk stretches into the distance, lined with quaint shops and twinkling lanterns, creating a surreal and enchanting atmosphere where reality and fantasy blend seamlessly.]"
},
{
"from": "gpt",
"value": "Normal. The moose's movements in the video are not smooth."
}
] |
seed44_2274
|
videos/HRA_part1/2274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, Mars-like landscape painted in shades of orange and red, a woman wearing a futuristic silver suit gently caresses a majestic bison, while a second bison stands nearby. Behind them, a man clad in a matching silver suit rides a robust, armored horse, creating a striking contrast against the barren, rocky terrain and the distant, hazy horizon. The woman's tender touch on the bison's fur and the man's confident posture on the horse convey a sense of harmony and adventure in this otherworldly setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are not smooth."
}
] |
seed42_1983
|
videos/HRA_part0/1983.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown bear, with its shaggy fur glistening in the sunlight, is seen swimming gracefully in a serene lake, surrounded by lush greenery and tall trees. Its powerful forearms propel it through the crystal-clear water, creating ripples that expand outward. The bear's alert eyes and nostrils are just above the waterline, showcasing its keen senses as it navigates the aquatic environment with ease. The peaceful setting, with the occasional splash and the gentle lapping of water against the shore, highlights the bear's natural ability to swim in its tranquil habitat.]"
},
{
"from": "gpt",
"value": "Normal. The brown bear's arm generation in the video has issues."
}
] |
seed46_1775
|
videos/HRA_part2/1775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown beaver, situated near water, performs a wiping motion with its right paw across its face, specifically from the eyes down to the mouth. The beaver is positioned with its back to the camera, offering a unique perspective. Its tail is submerged in the water, and the wiping action is repeated several times, emphasizing the creature's grooming habits in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's fingers and face in the video are not fully generated."
}
] |
seed42_1102
|
videos/HRA_part0/1102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a black jacket over a gray shirt and dark pants, is engaged in an intense scene where he skillfully catches a falling glass bottle with his right hand, displaying remarkable agility and precision. His focused gaze and the dynamic motion of the catch are highlighted against a dimly lit, gritty urban setting, adding to the dramatic effect of the moment. The scene is shot in high definition, capturing every detail of the actor's expression and the fluidity of his movements as he successfully intercepts the bottle mid-air.]"
},
{
"from": "gpt",
"value": "Normal. The right hand of the character in the video has generation issues."
}
] |
seed46_1147
|
videos/HRA_part2/1147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious brown monkey with a tuft of hair on its head sits upright on a lush green plant, holding a white napkin in its right hand. It begins wiping its mouth gently, revealing a small smile and a twinkle in its eye. As it continues, the monkey looks directly at the camera, showcasing its playful nature. The scene is set against a vibrant jungle backdrop, with sunlight filtering through the dense foliage, highlighting the monkey's actions and its environment.]"
},
{
"from": "gpt",
"value": "Bad. The monkey's movements in the video are uncoordinated."
}
] |
seed42_2393
|
videos/HRA_part0/2393.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A tiny, charming finch perches on a thin branch, its olive-green feathers blending harmoniously with the lush foliage of a tree set against a clear blue sky. The bird turns its head, revealing its distinct facial markings and vibrant yellow underbelly, before it takes flight, its wings beating rapidly against the crisp air. It lands gracefully on another branch, where it joins a group of similar finches, their chirping filling the serene atmosphere of the woodland scene.]"
},
{
"from": "gpt",
"value": "Normal. The bird's eyes in the video have generation issues, and the claws are partially missing."
}
] |
seed42_1095
|
videos/HRA_part0/1095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully through a clear blue sky, its sleek silhouette framed against the horizon. It dives sharply, wings tight to its body, chasing an unseen prey across the vast expanse. Its sharp eyes, focused and intense, scan the terrain below for any hint of movement. The bird then lands on a branch, its feathers ruffled by the wind, revealing a striking pattern of brown and white. It sits still, perched regally, surveying its domain with a fierce gaze, a true ruler of the skies.]"
},
{
"from": "gpt",
"value": "Normal. Missing the scene of birds landing on the branches."
}
] |
seed44_1935
|
videos/HRA_part1/1935.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 close-up shot of a large, sleek bass fish fills the screen, its body glistening with vibrant green and brown hues, accented by striking black spots. The fish's powerful form is emphasized as it swims within its natural freshwater habitat, surrounded by lush aquatic plants and a rocky bottom. The water's rippling surface occasionally comes into view, hinting at the bass's movements just beneath. The scene is captured in high definition, highlighting the intricate details of the fish's scales, fins, and eyes, offering a captivating glimpse into the underwater world of this formidable predator.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2764
|
videos/HRA_part2/2764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone penguin stands majestically on a frosty, ice-covered shore, its sleek black and white feathers glistening under the soft, diffused light of an overcast sky. The penguin, with its round body, small flippers, and distinctive tuxedo-like appearance, looks out to the vast, icy sea, creating a sense of solitude and resilience in the harsh Antarctic environment. The scene is framed by rugged, snow-capped mountains in the distance, emphasizing the penguin's natural habitat and the stark beauty of its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The penguin's eyes in the video have issues, the claws are deformed, and the wings are generated unreasonably."
}
] |
seed42_2040
|
videos/HRA_part0/2040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman named Martin, donning a gray coat, leans against a brick wall in a pensive pose, his right hand resting on his chin. The background is adorned with vibrant graffiti art, adding a splash of color to the urban setting. Martin's attire also includes black pants, a brown belt, and black shoes, complementing his sophisticated appearance. His facial hair, well-groomed and salt-and-pepper in color, frames his thoughtful expression. The scene captures Martin's contemplative nature amidst the lively backdrop of street art.]"
},
{
"from": "gpt",
"value": "Bad. The gentleman's hand generation in the video has issues."
}
] |
seed44_1566
|
videos/HRA_part1/1566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, with a ferret perched on his shoulder, floats weightlessly in a vast cosmic pool that mirrors Jupiter's Great Red Spot. Dressed in a dark wetsuit and goggles, he somersaults gracefully through the water, the ferret securely nestled and seemingly unfazed. The swirling red and white clouds of Jupiter envelop the scene, creating a surreal and captivating contrast to the serene swimming motion. Throughout, the ferret remains a constant presence, its curious gaze following the actor's every move in this otherworldly aquatic environment.]"
},
{
"from": "gpt",
"value": "Normal. The rolling action of the character in the water in the video is basically normal, with only slight awkwardness."
}
] |
seed42_1316
|
videos/HRA_part0/1316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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: [On a sandy beach, two smiling children, a boy and a girl, gently caress a small green lizard that rests on a patch of dry sand, surrounded by lush vegetation. The boy, wearing a blue t-shirt and blue swimming trunks, and the girl, clad in a pink dress, sit cross-legged as they tenderly pet the lizard. The scene is filled with warmth and sunlight, casting shadows of the children and the lizard onto the sandy ground. Moments later, the lizard scurries away into the foliage, and the children watch it go, their faces a mix of fascination and delight, embodying the innocence and wonder of childhood discovery.]"
},
{
"from": "gpt",
"value": "Bad. The video has an extra child wearing pink pants, and it fails to generate the action of the lizard quickly darting into the vegetation."
}
] |
seed46_1777
|
videos/HRA_part2/1777.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": "Bad. A woman with a ponytail is missing beside."
}
] |
seed42_3105
|
videos/HRA_part0/3105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature woman with graying hair, wearing a brown jacket over a peach-colored top, stands against a blurry background, gesturing with her right index finger pointed outward. Moments later, she points emphatically toward the right side of the frame, her face expressing determination. She then points upward with both hands, her eyes following the direction of her gesture, suggesting a moment of revelation or realization. Finally, she points straight ahead with her right index finger, her body language conveying authority and command, all against a softly blurred backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the woman pointing with her left hand or her eyes following the direction of her gesture to indicate a moment of revelation or realization."
}
] |
seed42_1403
|
videos/HRA_part0/1403.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a grey hoodie, beige khakis, and brown boots, runs across a grassy field under a clear blue sky, holding a remote control. Nearby, a squirrel scampers along the ground, its bushy tail bouncing. In the distance, an AI-piloted drone hovers, capturing aerial footage. The engineer occasionally glances upwards, monitoring the drone's position as it flies, while the squirrel continues its journey among the trees. The scene is set in a suburban park, with houses visible in the background, highlighting the integration of technology and nature in everyday life.]"
},
{
"from": "gpt",
"value": "Bad. The video does not contain any squirrels."
}
] |
seed42_1348
|
videos/HRA_part0/1348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman stands tall in the middle of a crosswalk in a bustling city, clad in a long, camel-colored coat that reaches her knees, dark trousers, and high-heeled boots. Her outfit is complemented by a brown leather handbag hanging from her right shoulder. The cityscape behind her, featuring pedestrians, traffic lights, and urban architecture, adds to the dynamic setting. Her confident stance and the urban environment create a captivating scene, with the woman at the center, embodying poise and independence.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted."
}
] |
seed42_1319
|
videos/HRA_part0/1319.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, wearing a gray jacket and jeans, sits cross-legged on a wooden deck by a lake, gently stroking a small brown beaver. The scene is set during the golden hour, with the student's face showing affection and the beaver seemingly comfortable with the interaction. The student, with tousled hair and a warm smile, holds the beaver with both hands, providing a sense of safety and care, while the creature, with its distinctive flat tail and sharp teeth, appears relaxed and unafraid in this peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1400
|
videos/HRA_part0/1400.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 European badger, with its distinct black and white striped face and grey fur, is seen in a natural woodland setting. It stands on its hind legs, using its front paws to wipe its face meticulously, cleaning itself in the early morning light. The action is repeated several times, emphasizing the creature's grooming habits, all while surrounded by lush green foliage and undergrowth, giving a sense of the animal's natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2903
|
videos/HRA_part1/2903.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young 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": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_1703
|
videos/HRA_part1/1703.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, rustic kitchen, two young children, a boy and a girl, both wearing colorful aprons over their clothes, stand on small wooden stools to reach the sink. The girl, with her hair tied in pigtails, holds a wrench with determination while looking intently at the faucet. The boy, wearing glasses, assists by shining a flashlight on the dripping tap, their teamwork highlighted by the warm, golden glow of the overhead lights. The sink is surrounded by decorative tiles, adding a homely touch to the scene. Tools and parts are neatly arranged on the countertop beside them, emphasizing the organized approach to fixing the leaky faucet.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_265
|
videos/HRA_part2/265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit chaparral landscape, a seasoned farmer wearing a wide-brimmed straw hat, denim overalls, and a plaid shirt is seen joyfully dancing. In the background, a jackal curiously observes from a distance, standing near a weathered wooden fence. The farmer, embodying the spirit of the land, performs lively dance moves, celebrating the beauty of nature around him, with the jackal occasionally mirroring his movements in a playful manner. The chaparral vegetation, characterized by shrubs and small trees, forms a picturesque setting for this unexpected dance performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1875
|
videos/HRA_part0/1875.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, 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 movements in the video are very unsmooth and uncoordinated."
}
] |
seed44_1637
|
videos/HRA_part1/1637.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A golden retriever, framed against a vibrant green meadow under a clear blue sky, experiences a unique perception of time as it runs. Initially, the dog is seen standing still, looking forward with anticipation. It then starts running, its legs blurring as if time has accelerated for the viewer. Next, the dog leaps into the air, seemingly frozen in mid-air, giving the impression of time slowing down. Finally, the dog bounds across the field, its motion smooth and unhurried, conveying a sense of normal time flow, all while the lush green landscape and clear blue sky provide a serene backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The dog in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed42_1322
|
videos/HRA_part0/1322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a neatly trimmed beard, wearing a dark blue chef's jacket, white chef's pants, and a brown apron, is kneeling in a lush, green garden. He is digging with a small, silver shovel, uncovering fresh vegetables and herbs. The chef's focused expression conveys his passion for sourcing ingredients directly from nature, while the vibrant greenery and earthy tones of the soil create a rich, natural backdrop for this culinary endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The shovel in the character's hand is distorted in the video."
}
] |
seed44_2186
|
videos/HRA_part1/2186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 gazelle, marked with distinctive black chevrons on its rump, sprints across the frame, its hooves kicking up mist from a bubbling hot spring. The background features a vast, arid savanna with distant mountains and sparse vegetation. The gazelle, its coat a sandy brown hue, bounds over the water's edge, sending plumes of steam into the air with each leap. In the foreground, the hot spring's milky, turquoise waters simmer and bubble, contrasting starkly with the dry landscape. The sky above is a vivid orange, indicating either sunrise or sunset, casting a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3181
|
videos/HRA_part1/3181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an underwater scene illuminated by natural light filtering through the water's surface, a school of vibrant, multicolored fish swim together in unison. The fish display a range of hues, including orange, yellow, and blue, with intricate patterns adorning their scales. They gracefully navigate the aquatic environment, surrounded by lush green seaweed gently swaying in the current. The detailed textures of the fish's bodies and the vivid colors of their surroundings create a captivating and serene underwater world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1302
|
videos/HRA_part2/1302.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his chiseled jawline and wearing a gray blazer, navy shirt, and dark jeans, is seen walking on a path in a park. In the background, a squirrel sits upright, seemingly intrigued by the actor's presence. As the scene progresses, the actor continues walking, maintaining his confident demeanor. Suddenly, the sky above catches his attention; a Venus flyby, a rare celestial event, is visible, adding a cosmic touch to the otherwise ordinary scene. The actor stops to observe the spectacle, his gaze fixed upward, while the squirrel remains alert nearby, both subjects unaware of the extraordinary alignment of events.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, and the hands are twisted."
}
] |
seed42_2749
|
videos/HRA_part0/2749.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown pelican with a large, distinctive orange pouch flies low over the surface of a calm bay, its wings spread wide against the vivid blue sky. It gracefully swoops down, diving into the water to catch fish, its body momentarily submerged before it resurfaces, triumphant. The pelican then floats on the water, preening its feathers with a meticulous beak, showcasing its survival skills in the serene coastal environment. Against the backdrop of a clear sky and calm waters, the pelican's flight and feeding habits are highlighted, emphasizing its unique features and behaviors in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The pelican's movements in the video are not smooth, and the wing-spreading action is uncoordinated."
}
] |
seed44_1521
|
videos/HRA_part1/1521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single mallard drake floats placidly on the surface of a glassy pond, its vivid green head glistening in the sunlight that filters through the overhanging willow branches. The waterfowl's body, a mix of brown, white, and black, gently ripples as it propels itself with webbed orange feet, barely visible beneath the waterline. Its alert eyes, set in a face that is the epitome of avian grace, scan the surroundings as it navigates the serene waters, unbothered by the tranquility that envelops the scene.]"
},
{
"from": "gpt",
"value": "Good. The swimming movements of the mallard in the video are basically normal."
}
] |
seed46_1217
|
videos/HRA_part2/1217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying a rugged yet sensitive character, is depicted in a subtropical desert landscape, where sparse vegetation clings to life among sand dunes and rocky outcrops. The scene opens with a close-up of the actor's hand gently caressing the weathered bark of a mesquite tree, conveying a sense of connection with nature. Moments later, he is shown standing still, eyes closed, face uplifted, feeling the warm desert breeze on his skin, wearing a simple linen shirt and trousers that blend with the earthy tones of the surroundings. The camera then captures him walking barefoot across the sandy terrain, leaving faint footprints that quickly disappear under the shifting sands, highlighting the transient beauty of the desert. Finally, he sits cross-legged, hands resting on his knees, in a meditative pose, his face reflecting inner peace, as the sun begins to set, casting long shadows and painting the sky in hues of orange and pink.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_2000
|
videos/HRA_part2/2000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished man with salt-and-pepper hair and a neatly trimmed beard speaks passionately, gesturing with his hands to emphasize his points. Dressed in a navy suit with a crisp white shirt and a red tie, he commands attention against a backdrop of city lights and a blurred crowd. His animated expressions and dynamic body language convey the intensity of his conversation, drawing the viewer into the engaging dialogue taking place in this urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video were not fully generated, and his facial features were slightly distorted."
}
] |
seed44_1213
|
videos/HRA_part1/1213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic, casually dressed woman walks down a city street, passing by various urban elements such as a fire hydrant, a streetlight, and a parked car, all while maintaining a confident stride. She wears a brown jacket, blue jeans, and black shoes, with her hair tied back in a bun, showcasing her energetic yet relaxed demeanor. The cityscape includes a yellow taxi in the background, adding to the bustling atmosphere. As she continues her journey, the urban environment unfolds around her, capturing the essence of city life.]"
},
{
"from": "gpt",
"value": "Normal. The woman's limbs in the video are missing, and her face is distorted."
}
] |
seed44_2261
|
videos/HRA_part1/2261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an array of colorful fish. The grouper, with its distinctive spotted pattern and wide, flat head, explores its surroundings with a slow, methodical motion. Its eyes, fixed on the camera, seem to convey intelligence and awareness. The water is crystal clear, allowing every detail of the grouper's body and the intricate ecosystem it inhabits to be visible. The scene is illuminated by natural sunlight filtering through the surface, casting dappled light on the sandy seabed and the marine life above.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the grouper's head and fins in the video has problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.