video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1564
|
videos/HRA_part1/1564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a white shirt and brown trousers, leads a llama on a leash through the verdant pathways of a zoological park, surrounded by lush greenery and exotic plants. The llama, adorned with a decorative blanket and colorful tassels, follows obediently as the farmer guides it past various enclosures housing different species. They walk alongside a water feature, such as a pond or stream, adding to the tranquil atmosphere of the park. The farmer's attire complements the natural surroundings, creating a harmonious scene as they navigate the scenic route together.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2379
|
videos/HRA_part1/2379.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a gray suit, sits at a desk cluttered with law books and papers, attentively reading a document. He momentarily pauses, lifting a fork loaded with pasta to his mouth, revealing his multitasking nature. The room is illuminated by the warm glow of a table lamp, casting a soft light on the busy scene. A cup of coffee and a glass of water sit nearby, within easy reach for this hardworking legal professional as he sustains himself through his demanding workday.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted, the face is slightly distorted, and the object in the person's hand is distorted."
}
] |
seed42_2664
|
videos/HRA_part0/2664.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a brown jacket over a white shirt and khaki pants, walks through a temperate deciduous forest during autumn. The trees are predominantly bare, with scattered leaves covering the ground. The forest floor is carpeted with a thick layer of dry, brown leaves, creating a crunching sound underfoot. The doctor occasionally stops to observe his surroundings, showcasing his appreciation for nature. Throughout the scene, the forest remains dense and the trees tall, with occasional glimpses of sunlight filtering through the canopy, highlighting the serenity of the environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1040
|
videos/HRA_part0/1040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic scene set against the backdrop of a bustling harbor, a snake charmer dressed in traditional attire, complete with a red turban and colorful vest, plays an enchanting melody on his pungi. The cobra, coiled and alert, rises from its basket, swaying hypnotically to the music under the golden glow of the setting sun. The charmer's skilled hands guide the snake into a mesmerizing dance, captivating the audience gathered around the harbor, where boats gently rock in the water and seagulls circle overhead. The cobra's movements, synchronized with the charmer's music, create a powerful display of control and grace against the maritime setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2783
|
videos/HRA_part0/2783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage girl sits at a wooden desk in a classroom, diligently hemming a pair of khaki pants using a sewing machine, her focus unwavering. She wears a yellow blouse, and her hair is tied back in a ponytail, highlighting her concentration. On the desk, a tape measure, scissors, pins, and a spool of thread are neatly arranged. Beside her, a bulletin board displays various fabric swatches and design sketches, adding context to her task. The room is illuminated by natural light from a window, casting a warm glow over her industrious endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video uses the sewing machine basically normally, but her movements are slightly uncoordinated."
}
] |
seed46_2136
|
videos/HRA_part2/2136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A costumed character, resembling a panda with black-rimmed eyes and a friendly smile, walks down a bustling city street. Dressed in a full-body panda suit, they navigate the urban landscape, passing by pedestrians and city structures. The panda mascot's outfit includes large, padded paws and a fuzzy, rounded silhouette, adding to the whimsical nature of the scene. As they stroll, the surrounding environment, filled with buildings and people going about their day, contrasts with the playful presence of the panda.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2780
|
videos/HRA_part0/2780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, portraying a member of a nanobot repair crew, leaps dramatically across a futuristic, metallic platform. Dressed in a silver jumpsuit, complete with utility belts and pouches, he soars through the air with intense focus. His movements are agile and purposeful, suggesting urgency in his mission. As he lands, ready to tackle the next task, the background features complex machinery and glowing panels, immersing the viewer in a high-tech, sci-fi environment.]"
},
{
"from": "gpt",
"value": "Bad. The actor's movements in the video are not smooth."
}
] |
seed46_2906
|
videos/HRA_part2/2906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished, middle-aged man wearing a white lab coat over a crisp blue shirt and khaki trousers walks his golden retriever on a leash in a lush, green park. The sun filters through the leaves, casting dappled light on the path. The doctor, with salt-and-pepper hair and glasses, smiles warmly as he interacts with his dog, which bounds joyfully ahead, exploring the surroundings. The two stroll past other park-goers, who exchange friendly nods, creating a scene of community and companionship in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1728
|
videos/HRA_part0/1728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female barista, wearing a gray apron over a black shirt, completes a transaction with a customer at a contemporary coffee shop. The cafe features wooden floors, a glass cooler, and a large digital menu display. After the sale, she turns to prepare a coffee beverage, carefully measuring ingredients into a French press. With practiced movements, she adds hot water from a stainless steel kettle and stirs the mixture. The barista then pours the freshly brewed coffee into a white ceramic cup, adding a touch of foam art on top before presenting it to the customer with a warm smile. Throughout the process, the cafe's modern decor, including high-top tables and minimalist chairs, provides a backdrop to the barista's efficient and skilled routine.]"
},
{
"from": "gpt",
"value": "Bad. The arms of the character in the video are twisted, the hands are distorted, and the water cup and kettle are also distorted."
}
] |
seed46_1973
|
videos/HRA_part2/1973.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric artist with a shaved head, donning a mustard yellow turtleneck sweater and khaki pants, stands on a dark green chair, changing a light bulb in his dimly lit studio. The space is filled with artistic clutter, including an easel with a half-finished painting, a large wooden table covered in art supplies, and various sculptures scattered throughout. The artist, with a hint of frustration, reaches up to screw in the new light bulb, casting dramatic shadows across his face and the surrounding objects. The scene is captured in high definition, allowing every detail of the artist's struggle and the eclectic studio to come to life.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2851
|
videos/HRA_part2/2851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown monkey walks purposefully across a lush green forest floor, sunlight filtering through the dense foliage above, casting dappled shadows on the ground. The monkey, with its fur ruffled by a gentle breeze, carries a small object in its mouth, possibly food, as it navigates the underbrush with agile movements. Its eyes, alert and curious, scan the surroundings, showcasing its adaptability in the wild. The scene is set against a backdrop of verdant vegetation, with the occasional sound of rustling leaves and chirping birds adding to the natural ambiance.]"
},
{
"from": "gpt",
"value": "Bad. The small object mentioned in the caption that the monkey is holding in its mouth does not appear in the video."
}
] |
seed46_2989
|
videos/HRA_part2/2989.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen illuminated by neon lights, a chef wearing a sleek, silver uniform and gravity-defying boots stands aboard an anti-gravity vehicle. The vehicle, resembling a levitating platform with intricate, glowing circuitry, hovers above a metallic countertop cluttered with advanced cooking gadgets. The chef, with a focused gaze, wipes a stainless steel utensil with a microfiber cloth, preparing for culinary innovation amidst the backdrop of a high-tech, floating workstation.]"
},
{
"from": "gpt",
"value": "Bad. The chef's movements in the video are not smooth."
}
] |
seed44_2032
|
videos/HRA_part1/2032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red kangaroo, distinguishable by its ruddy fur, bounds across a vast, arid landscape under a cloud-dappled sky, showcasing its powerful hind legs and long, muscular tail for balance. It leaps gracefully over the terrain, highlighting its natural agility and strength in motion. The kangaroo's focused gaze and determined posture emphasize its purposeful sprint across the open, scrubland environment, with distant hills providing a scenic backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's jumping movements in the video are not continuous, with abrupt changes."
}
] |
seed44_2604
|
videos/HRA_part1/2604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 film director, clad in a brown leather jacket and stylish glasses, stands confidently at the edge of a swimming pool, meticulously observing an ibex gracefully swimming underwater. The ibex, a sure-footed mountain-dwelling mammal, is shown in a surreal scene, effortlessly gliding through the clear blue water, its horns visible above its head. The director's focused gaze and the ibex's unusual aquatic activity create a captivating and thought-provoking visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The sheep's head and the director's hand in the video have generation issues."
}
] |
seed42_1070
|
videos/HRA_part0/1070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural, grassy setting under a partly cloudy sky, two boys wearing a red shirt and a gray shirt work together to mend a broken wooden fence, using tools and materials at their disposal. They are focused on the task, with one boy hammering a nail into the wood while the other steadies the fence post. The atmosphere is cooperative and industrious, with the boys' clothes and hands getting dirty from the work. Nearby, a small barn and additional fencing can be seen, adding to the pastoral scene. The boys' dedication to fixing the fence is evident in their determined expressions and the progress they've made so far.]"
},
{
"from": "gpt",
"value": "Bad. The boys' hands in the video have generation issues."
}
] |
seed42_181
|
videos/HRA_part0/181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A visionary director, wearing a brown jacket, sits on a chair, intently operating a camera, capturing footage of a rhinoceros in a barren desert landscape, with a massive white hole explosion occurring in the distance. The rhinoceros, filmed in extreme close-up, slowly crawls across the sandy terrain, its textured skin and concentrated gaze highlighting its determination. The director, now seen from behind, continues to film the rhinoceros as it traverses the challenging environment, with the white hole explosion's brilliant light illuminating the scene, creating a surreal and captivating contrast between the earthbound creature and the cosmic event.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the hands are twisted, the rhinoceros body is deformed, and the legs are twisted."
}
] |
seed46_1324
|
videos/HRA_part2/1324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded man with glasses and a gray beanie, wearing a dark jacket, leans into the soil with a green-handled shovel, his wedding band glinting in the light. He pauses to wipe sweat from his brow, revealing a determined look. Moments later, he is joined by another man, both digging in unison, the second man dressed in a brown jacket, jeans, and a white t-shirt. The scene transitions to the first man, now shirtless and covered in dirt, continuing to dig with intense focus, highlighting the hard labor involved. Finally, the two men stand back, shovels resting on their shoulders, surveying their deep, freshly-dug hole, a sense of accomplishment evident in their satisfied expressions. Throughout the scene, the man with the beanie remains the central figure, his actions and expressions conveying the physical and emotional demands of the task.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_2441
|
videos/HRA_part0/2441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A giant panda, identifiable by its distinctive black and white fur, engages in a leisurely stroll through a lush, green bamboo forest, its round body moving gracefully despite its bulk. It then proceeds to crawl, using its front paws to pull itself forward in a slow, deliberate motion, highlighting its unique method of navigating its environment. The panda's movements are unhurried and methodical, showcasing its relaxed demeanor as it explores its verdant surroundings. Throughout the scene, the panda remains the central focus, with the vibrant greenery of the bamboo forest providing a vivid contrast to its striking fur pattern.]"
},
{
"from": "gpt",
"value": "Normal. The panda's walking and crawling movements in the video are not smooth and coordinated."
}
] |
seed42_1090
|
videos/HRA_part0/1090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, finch perches on a branch, its vibrant yellow feathers contrasting beautifully against the lush green foliage. The bird's eyes sparkle with curiosity as it tilts its head, listening to the distant sounds of nature. Its beak, perfectly shaped for cracking seeds, opens slightly as it lets out a melodic chirp, filling the air with its song. The sunlight filters through the leaves, casting dappled shadows onto the finch, highlighting the intricate patterns on its wings. In the background, the outline of a wooden cabin can be seen, nestled among the trees, adding a touch of rustic charm to the serene forest scene.]"
},
{
"from": "gpt",
"value": "Normal. The bird's movements in the video are basically normal, with slight inconsistency."
}
] |
seed46_1804
|
videos/HRA_part2/1804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, donning a red jacket and black clothing, runs through the interior of a historic theater, illuminated by warm lights, with plush red seats and intricate ceiling details in view. He sprints past rows of empty seats, his movement contrasting with the static elegance of the venue. The camera captures his dynamic figure as he dashes across the stage, the ornate architecture of the theater framing him, evoking a sense of urgency within the grand setting. Throughout, the red of his jacket pops against the rich, dark tones of the theater's interior, highlighting his energetic run.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2376
|
videos/HRA_part0/2376.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vibrant green lizard with intricate patterns on its back traverses slowly across a dry, cracked earth surface, its movements deliberate and methodical. The terrain is peppered with small rocks and tufts of sparse vegetation, providing contrast against the lizard's vivid coloring. Sunlight filters down, casting dappled shadows and highlighting the texture of the lizard's skin as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Normal. The lizard in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed44_207
|
videos/HRA_part1/207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zero gravity, a whimsical scene unfolds where a small, brown porcupine floats, performing a delightful dance. It gracefully pirouettes against a backdrop of stars and the vast cosmos, its quills gently swaying in the absence of gravity. The porcupine then leaps playfully, executing mid-air flips and twists with an infectious joy, its quills shimmering under celestial lights. Throughout the dance, the porcupine's movements are fluid and weightless, embodying the freedom and fun of dancing in space, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2055
|
videos/HRA_part0/2055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 train station, a middle-aged doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, carries a brown leather bag. He walks purposefully past a massive, lifelike mammoth skeleton displayed as a scientific exhibit, the structure towering above the busy commuters. The scene captures the juxtaposition of the prehistoric and the modern, with the well-lit, contemporary train station bustling with people going about their day, while the imposing mammoth skeleton looms as a reminder of Earth's ancient past.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1681
|
videos/HRA_part0/1681.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, snow-covered tundra landscape, a small, furry badger emerges from its burrow, the entrance barely visible among the icy terrain. It cautiously crawls out, its round body and short legs moving slowly against the stark white backdrop. The badger, with its distinct black and white striped face, looks around with beady eyes, alert and ready to retreat at any sign of danger. Its movements are deliberate and measured as it explores the frigid environment, searching for food beneath the snow. The scene is framed by the endless expanse of the tundra, dotted with sparse, low-lying shrubs and ice formations, creating a sense of isolation and survival in the harsh wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the hedgehog in the video have generation issues."
}
] |
seed44_2558
|
videos/HRA_part1/2558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a green shirt and khaki shorts, walks through a savanna landscape, holding a book bag, with a hyena casually following at a distance. The student, in casual attire suitable for warm weather, continues walking along a dirt path, with the hyena maintaining a parallel path some distance away. As they move, the student occasionally glances back at the hyena, which returns the look, both seemingly unafraid and unperturbed by each other's presence, set against a backdrop of dry grasses and scattered trees typical of a savanna environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, arms, hands, feet, and legs are distorted in the video, as well as the hyena's body, head, feet, and legs."
}
] |
seed44_1499
|
videos/HRA_part1/1499.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space-themed library, a group of diverse individuals, including a bison cosplayer wearing a full-body brown fur costume, gather for a book club meeting. The cosplayer sits attentively among the members, who are seated on cozy armchairs and couches arranged in a circle. The room features high-tech elements, such as holographic book covers floating above each person, indicating their current reads. The bison cosplayer listens intently, occasionally nodding and gesturing with enthusiasm, while the other members engage in lively discussion about their latest sci-fi novel. In the background, a large window reveals the vastness of outer space, with stars twinkling and galaxies swirling in the distance. Suddenly, the bison cosplayer leaps up and begins to run in place, demonstrating the agility and strength of their chosen animal, much to the amusement of the other book club members.]"
},
{
"from": "gpt",
"value": "Bad. The bison actor's body is twisted, face distorted, arms twisted, legs twisted, head twisted, arms twisted, and legs twisted."
}
] |
seed44_1538
|
videos/HRA_part1/1538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and unexpected scene, a dedicated teacher, wearing a vibrant yellow swimsuit and cap, instructs a curious jackal pup, who dons a miniature life jacket, in the art of swimming. They are in a serene, clear blue pool surrounded by lush greenery, creating a harmonious blend of nature and learning. The teacher gently supports the jackal pup, both displaying expressions of concentration and determination as they navigate the water together, embodying an unconventional yet touching teaching moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1949
|
videos/HRA_part2/1949.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, appearing to be in his thirties, with short brown hair and wearing a grey t-shirt and black pants, is shown in a close-up shot. He exhibits signs of severe trembling, with beads of sweat visible on his forehead, indicating intense physical or emotional distress. The shaky movement is the focal point, capturing the viewer's attention and conveying a sense of urgency and concern. The background is blurred, keeping the emphasis solely on the man's shaking figure, which fills the screen, making his distress the central theme of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The facial generation in the video's post-production is blurry."
}
] |
seed46_154
|
videos/HRA_part2/154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a sharp navy suit, white shirt, and patterned tie, stands in a futuristic, minimalist setting, possibly a space station or advanced laboratory. She gently caresses a small, spherical piece of space debris, which is encased in a clear, protective glove, highlighting the delicate yet important task of space garbage cleanup. The gravity-defying environment adds a unique dimension to the scene, emphasizing the lawyer's role in tackling legal issues related to outer space endeavors. The background features sleek, metallic surfaces and digital screens displaying data, reinforcing the high-tech context of the cleanup operation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2070
|
videos/HRA_part2/2070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, iridescent green and purple, hovers near a red feeder, its wings a blur of motion against a clear blue sky, set against the backdrop of a lush garden filled with various flowers and greenery. The tiny bird's red beak is extended toward the feeder, while its body remains remarkably still despite the rapid wing beats. Its vibrant feathers catch the sunlight, creating a shimmering effect as it feeds, encapsulating the beauty and agility of nature in this serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The birds flying in the video is basically normal, but there is slight inconsistency in the movements."
}
] |
seed42_1305
|
videos/HRA_part0/1305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek black panther leaps majestically across a moonlit savannah, its muscles rippling beneath dark fur that shimmers under the celestial glow. The powerful feline bounds over tall grasses, leaving a trail of disturbed foliage in its wake, as it propels itself forward with a burst of speed and grace. Upon landing, the panther crouches low, ready for its next spring, against the backdrop of a vast landscape, dotted with distant trees and illuminated by the silvery light of the full moon.]"
},
{
"from": "gpt",
"value": "Bad. Feline exhibits morphological mutations. The body shows deformities."
}
] |
seed42_2168
|
videos/HRA_part0/2168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vividly rendered subtropical moist forest, a peculiar scene unfolds: a doctor, clad in a crisp white lab coat over khaki shorts and a blue polo shirt, kneels beside a serene pool. Nearby, a badger, unusually sporting a tiny red swim cap, paddles leisurely in the clear waters, its eyes closed in blissful enjoyment. The lush vegetation surrounds them, with sunlight filtering through the dense canopy, casting dappled shadows on the ground. This unexpected encounter between a human doctor and a swimming badger in the heart of a lush forest creates a captivating and surreal moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_26
|
videos/HRA_part2/26.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a bustling metropolis, a sleek, black cat is gently caressed by a young woman wearing a blue shirt and glasses. The cat, adorned with a red ribbon, sits atop a wooden crate, surrounded by urban elements like a fire hydrant, a green trash can, and a street sign. The woman, with her hair tied back in a bun, interacts affectionately with the cat, which responds with a content gaze. Behind them, the vibrant cityscape is visible, featuring tall buildings, a busy sidewalk, and a red traffic light, capturing the unique connection between human, animal, and urban environment.]"
},
{
"from": "gpt",
"value": "Good. The woman's movements while petting the cat in the video are basically normal."
}
] |
seed42_1133
|
videos/HRA_part0/1133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single dromedary camel, marked with dark spots, runs across a barren desert landscape under a hazy sky, its large, leathery feet kicking up puffs of sand with each stride. It wears a simple, rustic saddle adorned with red and white striped fabric, fluttering in the wind as the camel sprints. In the distance, the outlines of shrubs and distant mountains provide a sense of scale, emphasizing the vastness of the desert environment. The camel's powerful legs and muscular build are highlighted as it maintains its steady, fast pace through the sandy terrain.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3043
|
videos/HRA_part2/3043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, attired in a crisp white shirt, black vest, and trousers, strolls through dense, lush green thickets, carrying an empty silver tray. The vibrant flora envelops him as he walks, the sunlight filtering through the leaves creating a dappled effect on his path. The setting, reminiscent of an English garden, is filled with various plants and trees, providing a rich, textured backdrop for his leisurely walk. Despite the wild surroundings, the waiter maintains a professional demeanor, his attire and posture suggesting a formal occasion amidst nature's embrace.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1076
|
videos/HRA_part1/1076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, vivid scene, a janitor, dressed in a traditional uniform with a helmet, rides a majestic jaguar across a Mars-like landscape filled with orange sand dunes under a pinkish-red sky. The jaguar, adorned with a decorative saddle and reins, gallops gracefully, leading the viewer into a dreamlike world. The janitor then dismounts, exchanging the jaguar for a spirited Martian horse, which has a reddish-brown coat and carries him across the alien terrain with ease. The action shifts to a close-up of the janitor crawling on the Martian soil, examining the unique rock formations and textures of this extraterrestrial environment with fascination and curiosity.]"
},
{
"from": "gpt",
"value": "Bad. The leopard has an extra leg, and the legs are twisted, as well as the character's face."
}
] |
seed46_2092
|
videos/HRA_part2/2092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, wearing a sleek black suit and tie, performs an elegant dance move against a backdrop of Saturn's magnificent ring system, which glimmers with ethereal beauty in the distance. His confident posture and engaging smile captivate the viewer, while the celestial wonder behind him adds a touch of grandeur to the scene. The actor's polished shoes and well-groomed appearance contrast with the vastness of space, creating a unique juxtaposition between human artistry and cosmic splendor.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs are missing in the video, and his face is distorted."
}
] |
seed44_1294
|
videos/HRA_part1/1294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a red jacket and black cap, ascends a rocky cliff face with intense concentration, showcasing determination against a dramatic, cloudy sky. He pauses to rest, surveying the landscape below, revealing a secluded cabin surrounded by dense forest, hinting at his remote writing retreat. Continuing his ascent, he reaches for a sturdy rock hold, highlighting his physical strength and mental fortitude. At the summit, he pauses to write in a small notebook, capturing inspiration from the vast, misty valley below, embodying the adventurous spirit of an author seeking solitude and muse.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers appear deformed, and the notebook floating in the air is unrealistic."
}
] |
seed44_1385
|
videos/HRA_part1/1385.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a whole, raw Atlantic cod fish, eyes glassy and intact, laid upon a bed of ice chips, its skin shimmering under bright market lights. The fish is sizable, with a length suggesting it weighs several pounds, and is presented head-on, showcasing its freshness in a fishmonger's display. The setting is a bustling, open-air market, with other seafood visible in the background, emphasizing the variety and vibrancy of the scene. The cod's mouth is slightly agape, and its body lies across the ice, evoking the traditional presentation of fresh catches in coastal communities.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1257
|
videos/HRA_part0/1257.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a red jacket, gray beanie, and blue jeans, hikes through a dense forest with sunlight filtering through the trees, casting dappled shadows on the trail. They pause to observe a small stream, the water gently flowing over rocks, before continuing on the path, notebook in hand, ready to capture inspiration from nature's beauty. The scene focuses on the writer's contemplative gaze, the vibrant colors of autumn leaves surrounding them, and the peaceful atmosphere of the woodland setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1181
|
videos/HRA_part0/1181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, showcasing its distinctive golden fur patterned with black rosettes, swims through a clear, sun-dappled body of water, its muscular body cutting through the liquid with surprising grace and strength. Its piercing eyes remain focused, and its ears are flattened against its head as it propels itself forward with powerful strokes, defying the typical terrestrial nature of its kind in this aquatic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1078
|
videos/HRA_part1/1078.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A musician, dressed in a dark green shirt and black jeans, is seen wiping perspiration from his brow with a red bandana, standing amidst a lush orchard filled with apple trees bearing ripe fruit. The scene is set during a sunny day, with the musician's weathered guitar leaning against a tree trunk, strings glistening under the golden afternoon light. In another shot, he wipes his hands on his jeans, perhaps after having picked some apples, his face reflecting a sense of peace and contentment among the bountiful orchard surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The person is not wiping their forehead with a red handkerchief."
}
] |
seed42_1132
|
videos/HRA_part0/1132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 middle-aged janitor, dressed in a gray jacket and khaki pants, gently caresses the trunk of a small, friendly mammoth. The creature, with its baby-blue fur and tiny tusks, stands docilely in a brightly lit room filled with cleaning supplies. The janitor, with a caring smile and a mop in one hand, tenderly strokes the mammoth's trunk, creating an unlikely yet heartwarming bond between the two. The room is warm and welcoming, with sunlight streaming in from a large window, casting a golden glow over the unlikely pair.]"
},
{
"from": "gpt",
"value": "Bad. The character's caressing motion in the video is not smooth."
}
] |
seed44_2103
|
videos/HRA_part1/2103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, clad in a spacesuit with a NASA logo, stands against the striking backdrop of a Martian sunset, characterized by its pinkish-blue hue. The director is captured mid-jump, with one arm raised in triumph, against the dramatic landscape of Mars. The sandy terrain stretches into the distance, dotted with rocks and craters, providing a stark contrast to the vibrant colors of the sunset. The director's silhouette is outlined by the warm glow of the setting sun, creating a powerful visual representation of human exploration and the beauty of the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_241
|
videos/HRA_part2/241.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a tropical dry forest, golden light filters through the canopy, spotlighting a graceful gazelle. It prances and leaps in an open glade, its movements almost choreographed, as if dancing to an unheard melody. The gazelle, adorned with a shimmering gold collar that catches the sunlight, seems to perform for an audience of lush greenery and scattered wildflowers. Its elegant leaps and bounds are mirrored by the swaying branches above, creating a harmonious dance between predator and prey, all set against the vibrant backdrop of the dry forest's flora.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1230
|
videos/HRA_part0/1230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene urban park during daytime, a spotted bobcat crouches low on the lush grass, its ears perked and eyes alert, showcasing its wild nature in an unexpected setting. Moments later, it wipes its face with its paw, an intimate grooming gesture, revealing its untamed yet vulnerable side. The bobcat then pauses, sitting upright with its tail curled, offering a rare glimpse into its daily life. It continues to groom itself, licking its paw and wiping its face again, all while surrounded by the peaceful atmosphere of the park, highlighting the juxtaposition of wilderness and civilization.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth."
}
] |
seed42_270
|
videos/HRA_part0/270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 musician, wearing a red bandana, black leather jacket, and dark jeans, walks through an abandoned mine with caution. He carries a vintage guitar case, adding to his rugged, artistic persona. The mine, filled with debris and old machinery, provides a stark, industrial backdrop. The musician's confident stride and the detailed textures of the mine walls and floor convey a sense of exploration and mystery. As he moves deeper into the mine, the dim lighting highlights his silhouette, creating a dramatic effect. Throughout the video, the focus remains on the musician's journey, emphasizing his presence and the unique setting.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video walks basically normally, but there is slight uncoordination in the movements."
}
] |
seed42_1052
|
videos/HRA_part0/1052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid outdoor scene, three young children sprint across a vast, sunlit chaparral landscape, their movements captured in slow motion to emphasize their carefree joy. Dressed in a red shirt, blue shorts, and black shoes, one child leads the pack, arms outstretched like wings. Another child, wearing a yellow top, green shorts, and brown sandals, follows closely behind, laughing gleefully. Trailing just behind, a third child in a purple dress and pink sneakers completes the trio, their faces alight with excitement as they race beneath the clear blue sky. The chaparral vegetation, with its rugged shrubs and distant mountain backdrop, provides a natural, textured setting for their energetic play.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2174
|
videos/HRA_part0/2174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, wearing a classic white chef's jacket, black pants, and a black apron, stands on a wooden stool, engaged in the unexpected task of cleaning windows. He uses a squeegee and a bucket of soapy water to methodically clean the glass, revealing the bright, sunny day outside. Despite his professional attire, he tackles the chore with the same dedication he would show in the kitchen, creating an amusing juxtaposition between his culinary expertise and domestic duties. The scene is set against the backdrop of a bustling city street, visible through the window, adding a layer of urban life to the otherwise mundane activity.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_1266
|
videos/HRA_part0/1266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, donning a gray beanie, black jacket, and blue jeans, stands on the weathered wooden planks of a dock by the water's edge, with a vibrant cityscape visible across the bay. The artist leaps into the air, capturing the essence of freedom, while holding a sketchbook, which hints at their creative pursuits. The scene is bathed in golden hour sunlight, casting a warm glow over the figure and the urban landscape, creating a sense of serenity and inspiration.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1766
|
videos/HRA_part1/1766.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray turtleneck sweater and brown corduroy pants, sits at a wooden desk in a rustic cabin, surrounded by nature. Suddenly, the scene changes to reveal a graceful gazelle leaping over a wooden fence in slow motion, its muscles straining against the force of the jump. The gazelle lands softly on the ground and continues to run, its movements fluid and effortless. The writer, inspired by the sight, begins to type furiously on a vintage typewriter, capturing the essence of the gazelle's leap in a beautifully written passage. The camera zooms in on the writer's face, showing the intense concentration and inspiration on their face as they bring the scene to life through their words. Throughout the video, the focus remains on the gazelle's powerful leap and the writer's artistic interpretation of it, with no additional distractions or scene transitions.]"
},
{
"from": "gpt",
"value": "Normal. No scene of the writer typing on a vintage typewriter was generated, and the wooden fence in the video was not consistent with the \"wooden desk\" mentioned in the caption."
}
] |
seed44_3089
|
videos/HRA_part1/3089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, colorful scene unfolds where a person dressed in a black cape and white shirt, reminiscent of a bat, engages in an energetic dance. Their movements are fluid and dynamic, capturing the essence of nocturnal flight against a dark, starry sky. As they spin and leap, the cape billows dramatically, creating dramatic silhouettes against the twinkling celestial backdrop. The dancer's face is painted in black and white, accentuating the bat-like features, adding to the theatricality of the performance. Throughout the dance, the focus remains on the captivating interplay between the dancer's bat-inspired costume and the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2551
|
videos/HRA_part0/2551.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a flowing white robe with gold trim, stands in a vast, dimly lit space chamber, holding a fluffy rabbit gently against her chest. The chamber is filled with rows of benches, each occupied by similarly dressed figures, all facing an altar adorned with candles and space-themed decorations. The student caresses the rabbit lovingly, her face expressing deep reverence and peace, as the soft light from the candles illuminates the scene, casting a warm glow on everyone present. The rabbit, seemingly aware of its significant role, remains calm and still, adding a sense of serenity to the unique religious ceremony taking place among the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2632
|
videos/HRA_part1/2632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, temperate shrubland during the golden hour, a capybara, the world's largest rodent, is seen running energetically across the landscape. The shrubland is dotted with various green shrubs and low-lying vegetation, providing a natural habitat for the capybara. The animal, with its brown fur and distinctive rodent features, bounds gracefully over the terrain, highlighting its agility and speed. As it moves, the capybara leaves a trail of displaced grass and dust, showcasing its vitality in this serene environment.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the capybara jumping and running, but the movements are not very continuous and smooth, and there is a lack of coordination."
}
] |
seed42_1488
|
videos/HRA_part0/1488.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a yellow fire-resistant jacket, stands against the backdrop of a blazing inferno, his helmet askew to reveal a focused gaze. Amidst the chaos, he stares intently at the raging fire, his face a mask of determination and resolve. His eyes, shielded by a clear protective visor, never waver from the flames, conveying a sense of duty and bravery in the face of danger. Behind him, the fire rages on, casting an orange glow on his figure, highlighting his steadfast stare and unwavering commitment to extinguishing the blaze.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2440
|
videos/HRA_part2/2440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 domestic chicken, featuring brown and white feathers, is shown swimming in a small, clear body of water, surrounded by green grass and foliage. It paddles energetically with its feet, creating ripples on the water's surface, while its head remains dry above the waterline. The chicken's unique activity is captured in a series of shots that showcase its unexpected aquatic adventure in a natural, backyard setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_114
|
videos/HRA_part1/114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a red jacket and gray pants, dances joyfully on a mountain trail, surrounded by lush greenery and towering trees. The scene is set in the afternoon, with the sunlight filtering through the leaves, casting dappled shadows on the ground. The student performs a series of energetic dance moves, twirling and leaping across the rocky path, their face beaming with happiness and freedom. The mountain range looms majestically in the background, providing a breathtaking backdrop to this spontaneous dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The video shows students dancing with missing limbs and fingers, and there are issues with the facial generation."
}
] |
seed42_3095
|
videos/HRA_part0/3095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a yellow top and blue jeans is attentively cleaning a large, rectangular fish tank. She is seen smiling while scrubbing the glass with a sponge, ensuring a clear view of the colorful fish and underwater plants inside. The tank is illuminated by overhead lights, highlighting the woman's focused efforts. Her movements are gentle yet thorough, maintaining the aquatic environment's health and beauty. Throughout the process, the fish swim calmly around her, undisturbed by her presence, as she works diligently to keep their home pristine.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_17
|
videos/HRA_part1/17.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated teacher, wearing a vibrant yellow raincoat and matching boots, stands in the shallow waters of a lush wetland, surrounded by cattails and water lilies. She holds a large, transparent jar filled with water and aquatic insects, engagingly teaching a group of students who sit cross-legged nearby, dressed in waterproof jackets and pants. The students attentively listen, some with binoculars around their necks, as they learn about the wetland ecosystem. The teacher then leads the students in a safe, supervised activity where they wade into the water, using nets to catch and examine small fish and plants, all while standing in the calm, knee-deep water of the wetland.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's hand generation in the video is problematic, and the students sitting cross-legged and listening to the lecture suddenly disappear in the middle frame."
}
] |
seed46_1027
|
videos/HRA_part2/1027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young writer, clad in a red jacket, blue jeans, and black running shoes, races through the bustling city streets at night, passing by a diverse array of shops and restaurants. The urban landscape is illuminated by the glow of neon signs and streetlights, casting dynamic shadows as the runner weaves through the crowd. The scene captures the energy and vibrancy of city life, with the writer's determination and focus highlighted by the motion blur of the passing scenery. The narrative unfolds as the runner passes landmarks like a movie theater, a busy crosswalk, and a street food vendor, all contributing to the vivid tapestry of the urban environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1980
|
videos/HRA_part0/1980.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sandy desert under a cloudless blue sky, a lone brown camel slowly crawls across the dunes, its large, expressive eyes looking straight ahead. The animal's body is positioned low to the ground, its right front leg extended forward in a crawling motion, and its left hind leg bent beneath it. The texture of the camel's fur is detailed, showing the natural variations in color and the dryness of the skin. The sand dunes form dramatic curves and ridges, with soft shadows highlighting the contours created by the sun's light. In the distance, more dunes stretch to the horizon, emphasizing the camel's solitary journey through this expansive landscape.]"
},
{
"from": "gpt",
"value": "Normal. The camel's movements are not smooth."
}
] |
seed42_1609
|
videos/HRA_part0/1609.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student with a messy bun, wearing a white t-shirt and grey sweatpants, stands in a small dorm kitchen. She measures coffee grounds into a filter, her movements practiced and efficient. Next, she pours water from a bottle into the coffee maker, the light catching the droplets as they fall. Then, she pushes the start button on the machine, her face lighting up with anticipation. Lastly, she adds a splash of milk to her mug, stirring it slowly as steam rises, ready to enjoy her well-deserved break amidst the stacks of books and papers on her desk.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand generation in the video has issues."
}
] |
seed46_2171
|
videos/HRA_part2/2171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African savanna, a herd of majestic Cape buffaloes gathers near a watering hole. The scene opens with a panoramic view of the landscape, emphasizing the natural habitat. A buffalo, its body glistening with water droplets, emerges from the watering hole and begins to rub against a tree, its large horns and muscular frame highlighted. Another buffalo, also wet, vigorously shakes its head, spraying water around. The herd grazes peacefully nearby, showcasing their daily routine in the wild, with the watering hole as a central point, surrounded by tall grasses and scattered acacia trees.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2851
|
videos/HRA_part2/2851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 monkey walks purposefully across a lush green forest floor, sunlight filtering through the dense foliage above, casting dappled shadows on the ground. The monkey, with its fur ruffled by a gentle breeze, carries a small object in its mouth, possibly food, as it navigates the underbrush with agile movements. Its eyes, alert and curious, scan the surroundings, showcasing its adaptability in the wild. The scene is set against a backdrop of verdant vegetation, with the occasional sound of rustling leaves and chirping birds adding to the natural ambiance.]"
},
{
"from": "gpt",
"value": "Normal. The monkey's walking in the video is basically normal, but there is slight coordination issue."
}
] |
seed42_32
|
videos/HRA_part0/32.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, complete with a tailored suit, tie, and leather briefcase, finds himself in an unexpected scenario: cleaning windows. With a microfiber cloth in hand, he meticulously wipes a large, clear window pane, revealing a cityscape beyond. The scene is set in a spacious office with modern decor, where natural light illuminates the room, highlighting the lawyer's dedication to detail in an unconventional task. Despite his professional attire, he approaches the chore with the same seriousness and precision as his legal work.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's face in the video is generated blurry, fingers are deformed, and there is a frame showing three hands."
}
] |
seed46_205
|
videos/HRA_part2/205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 renowned actor, wearing a brown costume resembling a moose, dances gleefully in a large, empty studio with high ceilings and exposed pipes. The overhead lights cast a warm glow on the wooden floor, highlighting the actor's animated expressions and exaggerated movements. The studio walls are adorned with abstract paintings and vintage movie posters, adding a whimsical touch to the scene. As the actor continues to dance, their enthusiasm is contagious, bringing a sense of joy and playfulness to the space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1504
|
videos/HRA_part2/1504.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a gray shirt and dark pants, sits cross-legged on a green yoga mat placed atop a lush lawn, gently caressing a small vole. She holds the tiny creature in her right hand, her face reflecting warmth and care, as she looks down at it lovingly. The vole, nestled in her palm, seems relaxed and comfortable, its presence offering a tender moment of connection between human and nature, under the shade of a large tree.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2835
|
videos/HRA_part0/2835.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising yet tender scene, a large brown bear gently caresses a smaller, lighter-brown bear against the backdrop of a vast savanna landscape. The two bears sit on the golden grass, under a clear blue sky dotted with a few white clouds. The big bear has its arm around the smaller one, while the other paw is softly stroking the smaller bear's head. Both bears wear collars, indicating they might be part of a conservation program. This heartwarming interaction unfolds in a protected area of the savanna, where wildlife coexists in harmony.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the brown bear's paws in the video has problems."
}
] |
seed44_2521
|
videos/HRA_part1/2521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, donning a black hat and dressed in a brown jacket over a white shirt, plays a wind instrument passionately in an art gallery filled with contemporary art pieces. Suddenly, a gazelle, a symbol of grace and freedom, jumps into the frame from the right side, leaping over a low sculpture, adding an unexpected yet harmonious element to the scene. The focus remains on the musician and the gazelle, with the vibrant artwork providing a stimulating backdrop, all captured in a single, continuous shot.]"
},
{
"from": "gpt",
"value": "Bad. The musician's eyes and hands, the playing of the instrument, and the head of the antelope were generated abnormally in the video."
}
] |
seed44_1487
|
videos/HRA_part1/1487.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 realistic zebra, complete with black and white stripes, finds itself crawling under a barrier typically found at train stations. The striped animal moves slowly and carefully, its body almost touching the ground, as it navigates beneath the yellow and black-striped barrier. The train station's typical features, such as tracks, platforms, and overhead signs, are visible in the background, adding to the surreal nature of the scene. The zebra's unusual behavior in this urban setting creates a striking and memorable image.]"
},
{
"from": "gpt",
"value": "Normal. The zebra's movements are not smooth."
}
] |
seed46_2244
|
videos/HRA_part2/2244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 peaceful woodland setting, a small, curious badger is shown gently caressing the nose of another badger, likely its mate, with its forepaw, conveying a tender moment of connection between the two creatures. The scene is illuminated by a soft, golden light filtering through the trees, casting a warm glow on the badgers as they engage in this intimate gesture. Their fur is depicted in rich, earthy tones, and the surrounding foliage provides a lush, natural backdrop that enhances the serene atmosphere of this unique encounter.]"
},
{
"from": "gpt",
"value": "Bad. The badger's paws and mouth generation in the video have issues."
}
] |
seed44_1593
|
videos/HRA_part1/1593.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray shirt and blue jeans stands on a green ladder, cleaning out debris from the clogged gutters of a two-story house with a red roof, set against a clear blue sky. His focus is intense as he uses a small garden trowel to scoop out leaves and dirt. The house facade, painted in a warm beige hue, contrasts with the lush greenery surrounding it. A pile of removed debris sits on the ground beneath him, indicating progress in his task. His gray shirt and blue jeans are slightly soiled from the work, highlighting the effort and dedication put into maintaining the home's exterior.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2027
|
videos/HRA_part1/2027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green swamp environment teeming with life, two young children, a boy and a girl, are seen energetically running and exploring. The boy wears a red t-shirt and khaki shorts, while the girl dons a yellow dress, both dressed appropriately for the outdoors. They splash through shallow water, their faces lit up with joy and wonder, surrounded by tall cattails and lily pads. A wooden bridge can be glimpsed in the background, adding to the sense of adventure in this vibrant natural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_255
|
videos/HRA_part2/255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a navy suit, white shirt, and patterned tie, sits on a pier with a mongoose resting on his shoulder. The lawyer gently caresses the mongoose, which is adorned with a small red bowtie, as they both look out over the calm waters. The scene is set during the golden hour, with the warm sunlight casting a serene glow over the water and the pier. The lawyer's attire and demeanor suggest a successful career, while the presence of the mongoose adds an unexpected touch of whimsy to the composition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1955
|
videos/HRA_part1/1955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant supermarket, a diverse group of people, including a young woman with long brown hair tied in a bun, wearing a black jacket over a gray shirt and black leggings, and a man in a red shirt and blue jeans, are joyfully dancing to an upbeat tune. Amidst the aisles filled with groceries, a person dressed in a comical weasel costume joins the impromptu dance party, adding to the festive atmosphere. The weasel, with its oversized head and expressive features, moves energetically among the dancers, who are all smiling and enjoying the spontaneous fun in the brightly lit store.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2435
|
videos/HRA_part0/2435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stork, distinguished by its gray feathers and black wingtips, is captured in a series of poses. Initially, it stands tall on a grassy bank, legs firmly planted, looking alert. Then, it spreads its wings wide, ready for flight, with a serene lake and lush greenery serving as a backdrop. Next, the bird is seen in mid-flight, gracefully soaring over the water's surface, with its wings fully extended and head held high. Finally, it lands elegantly, tucking its wings and extending its long legs, touching down on the grass near the water's edge, completing the sequence of its daily activities by the lakeside.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_16
|
videos/HRA_part0/16.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ferret, wearing a red bow tie and small glasses, jumps joyfully on a miniature roller coaster car at a whimsical animal-sized amusement park. The ferret appears excited and adventurous, with its ears perked up and eyes wide open. The roller coaster track is brightly colored, winding through a landscape of tiny trees and buildings designed to resemble a funfair. Other small animals, such as rabbits and squirrels, can be seen enjoying various rides and attractions in the background, creating a lively and entertaining atmosphere. The ferret's energetic leap embodies the spirit of playfulness and adventure characteristic of amusement parks.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's movements in the video are not smooth."
}
] |
seed46_2635
|
videos/HRA_part2/2635.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, wearing a traditional white chef's uniform with a name tag, unloads a commercial-grade stainless steel dishwasher in a busy restaurant kitchen. He is surrounded by various kitchen tools and appliances, including a large stand mixer, a high-performance stove, and multiple pots and pans. The chef efficiently removes clean dishes, stacking plates and placing utensils in their designated areas. Throughout the process, the bustling environment of the kitchen is evident, with other chefs and staff working diligently in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1757
|
videos/HRA_part1/1757.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman 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 in the video runs unsmoothly and her movements are uncoordinated."
}
] |
seed44_1059
|
videos/HRA_part1/1059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, adorned in a red jacket, blue jeans, and a white t-shirt, explores the vibrant streets of Tokyo, holding a sketchbook and pencil. The bustling cityscape surrounds him, featuring neon signs, crowded sidewalks, and eclectic architecture. Suddenly, the scene shifts to a serene indoor swimming pool, where the same artist is seen diving into the water, the reflection of the pool lights creating a mesmerizing pattern on the ceiling. The artist swims with grace and determination, their red swim cap standing out against the blue water, encapsulating a moment of tranquility amidst the urban chaos.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms, legs, and head are deformed in the video."
}
] |
seed46_223
|
videos/HRA_part2/223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station interior resembling a bank, a muscular firefighter, now a space hero, crawls through a narrow air duct lit by blue emergency lights. Dressed in a high-tech firefighting suit with a red helmet, he stealthily moves forward on a mission. He continues crawling, his gear and determination evident, as the dimly lit vent and complex machinery surround him. Suddenly, the focus is on his intense face, showcasing his resolve through the visor of his helmet, as he prepares for action. Lastly, our hero is seen in a crouched position, ready to leap into danger, his advanced firefighting equipment at the ready, within the confined space of the air duct.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1984
|
videos/HRA_part2/1984.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station newsroom, illuminated by soft blue and orange lights, a realistic animated rabbit, wearing a small suit and tie, sits at a sleek desk. The room is filled with high-tech equipment and screens displaying galactic maps and data. The rabbit, with a serious expression, reads from a teleprompter, delivering the latest space news. Suddenly, the scene changes to the same rabbit running energetically on a treadmill, surrounded by floating zero-gravity objects, including a pen, a book, and a coffee cup, all set against the backdrop of the Earth through a large window.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_238
|
videos/HRA_part2/238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, donning a red flannel shirt, blue jeans, and brown work boots, rakes a large pile of autumn leaves in his backyard, surrounded by lush greenery and vibrant fall foliage. He pauses to play a harmonica, his joyful expression and the warm, golden sunlight highlighting his love for music and the outdoors. Continuing his task, he rakes the colorful leaves into a sizable heap, his movements energetic and rhythmic, embodying the spirit of the season. Occasionally, he stops to strum his acoustic guitar, the leaves forming a picturesque backdrop, capturing the essence of a musician enjoying the simple pleasures of life amidst nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_104
|
videos/HRA_part0/104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, wearing a gray jacket and blue jeans, walks through the lush greenery of a botanical garden, surrounded by vibrant flowers and towering trees. They pause to examine a particularly interesting plant, their backpack resting on the ground beside them. The sunlight filters through the leaves overhead, casting dappled shadows on the path. In the background, the serene sound of a nearby fountain can be heard, adding to the peaceful atmosphere of the scene. The student continues on their leisurely stroll, taking in the beauty of nature around them.]"
},
{
"from": "gpt",
"value": "Normal. The character's body is twisted, the face is distorted, and the arms are twisted."
}
] |
seed42_3153
|
videos/HRA_part0/3153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and blue jeans, walks along a wooden path near a lake, holding a green notebook. An otter swims in the foreground, its head occasionally popping up from the water, mirroring the writer's pace. The writer stops, looking thoughtful, then continues walking, passing a wooden post and a tree with orange leaves, suggesting an autumn day. The otter follows suit, diving under the water and reappearing alongside the writer, who now looks down at the playful creature, sharing a moment of connection in nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1413
|
videos/HRA_part0/1413.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of enthusiastic students, clad in casual attire with gardening gloves and hats, gather around a lush, green community garden. They engage in various gardening activities, such as planting seedlings, watering plants, and weeding the soil, under the guidance of an adult supervisor. The scene is set against a backdrop of clear blue skies and the vibrant colors of nature, with the students' joyful expressions and teamwork highlighting the educational and social benefits of outdoor learning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1015
|
videos/HRA_part0/1015.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional nurse, clad in a light blue scrubs top and dark blue scrubs pants, sits at a desk with a name badge visible on her chest. She types diligently on a desktop computer keyboard, her focus unwavering. Behind her, a hospital room is visible, featuring a bed with crisp white sheets and a patient resting peacefully under a blanket. Medical equipment lines the walls, including an IV stand and a monitor displaying vital signs, while a window allows natural light to illuminate the space. The nurse's posture and concentration convey her dedication to her work in this healthcare setting.]"
},
{
"from": "gpt",
"value": "Normal. The actions are basically normal, but there is slight inconsistency in the movements."
}
] |
seed44_2524
|
videos/HRA_part1/2524.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising juxtaposition, a young, cheerful cashier, wearing a green apron over a striped shirt, is seen enjoying a swim in a clear, tranquil body of water surrounded by scrublands. The cashier, with short, wavy hair and a nose ring, alternates between swimming and floating on the water's surface, showcasing a sense of freedom and relaxation. The scrublands, with their sparse vegetation and sandy soil, provide a stark contrast to the refreshing water, creating a unique and captivating scene. Throughout, the cashier's attire remains consistent, featuring the green apron and striped shirt, as they immerse themselves in the peaceful environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2407
|
videos/HRA_part0/2407.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red-tailed hawk soars gracefully through a clear blue sky, its powerful wings outstretched against the backdrop of a lush, green forest below. The hawk's piercing golden eyes scan the landscape for prey, its sharp talons ready to strike. The camera captures the intricate feather patterns on its broad wings and tail, highlighting the beauty and strength of this avian predator. As it glides effortlessly, the wind ruffles its feathers, and the sunlight reflects off its body, creating a mesmerizing display of nature's majesty.]"
},
{
"from": "gpt",
"value": "Bad. The red-tailed hawk in the video is abnormally distorted."
}
] |
seed46_2040
|
videos/HRA_part2/2040.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished 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": "Good. No obvious problems."
}
] |
seed44_2489
|
videos/HRA_part1/2489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative juxtaposition, a male cashier, clad in a gray shirt and black pants, is seen sprinting energetically across a vast, open space, reminiscent of a track field. Behind him, an enormous screen displays a stunning, high-definition image of Jupiter's iconic Great Red Spot, creating a surreal and captivating visual contrast between the terrestrial and the celestial. The cashier's focused expression and determined stride add a sense of urgency and dynamism to the scene, while the imposing presence of the gas giant's storm serves as a dramatic and awe-inspiring backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed46_2913
|
videos/HRA_part2/2913.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 police officer, clad in a navy uniform with a badge and black tactical gear, is seen in a residential backyard with green grass and trees in the background. He kneels beside a golden retriever, gently washing it with a hose and a sponge. The dog, wearing a red collar, happily shakes off water, splashing the officer who laughs good-naturedly. The scene conveys a heartwarming moment of care and connection between the officer and the dog, set against a backdrop of blue skies and lush greenery.]"
},
{
"from": "gpt",
"value": "Bad. The water pipe mentioned in the caption does not appear in the video."
}
] |
seed44_2353
|
videos/HRA_part1/2353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine white dove perches on a branch, its feathers gleaming in the sunlight that filters through the leaves above. The bird turns its head, revealing one bright, alert eye. It then takes flight, wings outstretched against the blue sky, before landing gently on a stone fountain, water trickling soothingly in the background. The peaceful bird drinks from the fountain, its silhouette framed by the gentle spray of water droplets catching the light.]"
},
{
"from": "gpt",
"value": "Bad. The pigeon's claws were not generated completely, and there were issues with the wings."
}
] |
seed46_3154
|
videos/HRA_part2/3154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful female teacher, wearing a green shirt and black pants, is seen in a classroom with a high ceiling, assembling a wooden table. The room is filled with natural light from large windows, illuminating the space. She is kneeling on the floor, carefully screwing in a leg of the table with a screwdriver, demonstrating a practical skill to her attentive students, who watch from a distance. The teacher's patience and focus are evident as she meticulously puts together the piece of furniture, providing a valuable learning experience in a bright and welcoming environment.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher's action of tightening the screw is not smooth."
}
] |
seed42_1714
|
videos/HRA_part0/1714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the midst of arid scrublands, a spotted hyena, characterized by its distinctive spots and robust build, is unexpectedly seen swimming across a shallow, sunlit waterhole. Its head held high above the clear water, the hyena propels itself forward with powerful strokes, showcasing its rarely observed aquatic abilities. The serene environment is punctuated by the distant silhouette of a lone tree, highlighting the surprising scene unfolding in this typically dry habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1481
|
videos/HRA_part1/1481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a large bird of prey with brownish-black and white plumage, soars majestically over a serene lake at sunset, its piercing yellow eyes scanning the water below for fish. The bird, with its distinctive head pattern and curved beak, effortlessly glides through the air, its wings spread wide, casting a shadow on the calm water. Suddenly, it dives into the lake with remarkable speed and precision, emerging moments later with a wriggling fish clasped firmly in its talons. As the osprey ascends back into the sky, the fading sunlight illuminates its powerful form, highlighting the intricate feather patterns and the determination in its eyes.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_12
|
videos/HRA_part2/12.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and gun holster, leaps into the air in the middle of a vast, temperate grassland. The landscape is dominated by knee-high green grasses and a few scattered oak trees, with the horizon stretching far into the distance. The officer's feet leave the ground, capturing a moment of action and energy, as the rolling hills and clear blue sky provide a serene contrast to the dynamic scene. The officer's movements are sharp and decisive, embodying the spirit of law enforcement in the open, wild environment of the grasslands.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_125
|
videos/HRA_part0/125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful woman wearing a vibrant yellow apron over a casual outfit of a gray t-shirt and black leggings, her brown hair tied back in a ponytail, is seen cooking in a modern kitchen. She expertly chops vegetables on a wooden cutting board using a sharp knife, the overhead lights reflecting off the stainless-steel appliances behind her. Her hands, adorned with rings, move with practiced ease as she seasons the ingredients in a large skillet on a gas stove, steam gently rising from the pan. Throughout, she maintains a warm smile, occasionally glancing up from her task, creating an inviting atmosphere in the well-lit kitchen space.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted, and the knife is twisted and deformed."
}
] |
seed44_2697
|
videos/HRA_part1/2697.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique and whimsical scene, a cheerful nurse, clad in a traditional white uniform and cap, finds herself frolicking in a shallow, clear water body situated amidst vast temperate grasslands. The lush, green landscape stretches far into the horizon, dotted with swaying grasses and a few scattered trees. The nurse, enjoying a spontaneous moment of leisure, splashes water joyfully, her white attire contrasting beautifully against the natural setting. The sunlight filters through partly cloudy skies, casting a warm glow over the entire scene, highlighting the serenity of the temperate grasslands and the nurse's playful spirit.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's head and hands in the video are generated abnormally, and the nurse's movements suddenly deform and gradually disappear in the middle frames."
}
] |
seed46_1389
|
videos/HRA_part2/1389.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a compassionate nurse, clad in a blue uniform and wearing a stethoscope around her neck, leaps with exhilaration against a cosmic backdrop featuring an artist's impression of a recently discovered exoplanet. Simultaneously, a cobra, coiled and ready to strike, mimics the action of jumping, adding an unexpected element to the scene. Both figures, the nurse and the cobra, are captured mid-leap, their silhouettes outlined against the star-studded universe, creating a vivid contrast between human emotion and the raw power of nature, all set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, hands are twisted, legs are twisted, and the cobra's body is twisted."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.