video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1441
|
videos/HRA_part1/1441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, nestled in the fork of a lush eucalyptus tree, gently caresses its companion with a fuzzy paw, both enveloped in the verdant embrace of their arboreal home. The koala, with its round face and endearing expression, tenderly touches another koala, showcasing a heartwarming display of affection. Their interaction is set against the vibrant green foliage, highlighting the tenderness of their connection. As they engage in this intimate gesture, their soft fur and the intricate details of the eucalyptus leaves create a visually captivating scene. Throughout, the two koalas remain in this loving embrace, emphasizing the emotional bond between them.]"
},
{
"from": "gpt",
"value": "Bad. The koala's paw generation in the video has issues, with one hand disappearing in the middle frame."
}
] |
seed42_3084
|
videos/HRA_part0/3084.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, wearing a traditional white chef's uniform and black pants, stands outdoors in a garden, holding a shovel. He is surrounded by various plants, including leafy greens, carrots, and herbs like rosemary, thyme, and sage. The chef has short brown hair and a neatly trimmed beard, and he is digging into the rich soil with determination, perhaps searching for fresh ingredients for his culinary creations. The scene is set against a backdrop of wooden crates and greenery, with a hint of sunlight filtering through the trees, casting dappled shadows on the chef and his gardening endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The man's actions of digging soil are discontinuous, there are sudden changes."
}
] |
seed44_1216
|
videos/HRA_part1/1216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal and imaginative scene, a compassionate nurse, clad in a crisp white uniform, tends to a gentle rhinoceros, who is swimming effortlessly in a vast, crystal-clear pool. Surrounding them, a series of industrial factories loom in the distance, their smoky chimneys juxtaposing the serenity of the water. The nurse's caring hands support the rhino's underwater navigation, creating a harmonious bond between human and animal amidst an unlikely urban landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1577
|
videos/HRA_part0/1577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant classroom decorated with colorful posters and student artwork, a passionate teacher, wearing a dark green shirt and khaki pants, is seen in the act of catching a ball, demonstrating a physics lesson on motion and gravity. The students, seated at their desks, watch intently as the teacher, with a lively expression, skillfully catches the ball mid-air, illustrating the principles of force and motion in an engaging and interactive manner.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's arms and hands undergo deformation and mutation. The ball also disappears and reappears at times."
}
] |
seed44_1310
|
videos/HRA_part1/1310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, distinguished by its brown fur, white underbelly, and tufted ears, stealthily crawls across a sandy surface in a suburban town, near wooden fences and lush greenery. It pauses to sniff the air, displaying its sharp teeth and alert demeanor. The feline then continues its crawl, passing by a stone wall and wooden planks, indicating the proximity to human habitation. Throughout the scene, the bobcat's cautious and curious nature is evident as it explores its surroundings in the town's outskirts.]"
},
{
"from": "gpt",
"value": "Bad. The lynx in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed44_1845
|
videos/HRA_part1/1845.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, cavernous space, a small, brown bat gently caresses another bat with its wing, creating a tender, intimate moment. The bats are perched upside-down on a rocky surface, with water droplets visible in the background, adding to the natural, subterranean atmosphere. The scene is illuminated by a soft, warm light that highlights the texture of the bats' fur and wings, emphasizing the caring interaction between the two creatures.]"
},
{
"from": "gpt",
"value": "Bad. The bat's body is twisted, its claws are distorted, and its face is contorted."
}
] |
seed46_2485
|
videos/HRA_part2/2485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a black cap and a blue flannel shirt, is seen painting an antelope on a large canvas set against a background of lush greenery. The canvas is placed on an easel, and the artist, with a concentrated look, applies vibrant orange paint to depict the animal. The antelope, depicted as running with its head turned back, is captured mid-stride, its movement and grace highlighted by the artist's brushstrokes. The setting sun casts a warm glow over the scene, illuminating the artist's silhouette and the vivid depiction of the antelope in motion.]"
},
{
"from": "gpt",
"value": "Bad. The artist in the video paints very unsmoothly, with uncoordinated movements."
}
] |
seed46_1486
|
videos/HRA_part2/1486.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, lush green forest setting, two young boys, one wearing a red t-shirt and shorts, and the other in a blue shirt and shorts, are seen interacting with a pair of deer. One boy gently wipes mud off a deer's leg using a cloth, showing care and concern, while the other observes intently. The deer stand calmly, trusting the boys' presence. The scene captures a tender moment of compassion and connection between children and nature. The forest backdrop, with its tall trees and dappled sunlight, adds to the peaceful atmosphere, highlighting the innocence and beauty of the interaction.]"
},
{
"from": "gpt",
"value": "Bad. The child's hand appears deformed, and the towel in their hand is also distorted."
}
] |
seed46_1835
|
videos/HRA_part2/1835.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [On a futuristic space movie set, a life-size animatronic moose, sporting a metallic silver spacesuit, is being wiped down by a crew member in a pristine white lab coat. The set is dominated by a large, circular spaceship door with hexagonal bolts, and features a control panel with green buttons and switches. The moose, with its antlers adorned with blinking red lights, stands against a backdrop of sleek, metallic walls and a floor grid, creating a surreal juxtaposition of nature and sci-fi technology. The crew member meticulously wipes the moose's suit, ensuring it's ready for its intergalactic scene, while the set's high-tech details add to the otherworldly atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The head and claws of the mechanical moose, as well as the heads and hands of the staff, were generated abnormally in the video."
}
] |
seed42_1962
|
videos/HRA_part0/1962.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two young children, a boy and a girl, both wearing red jackets, are seen walking together with a realistic, animated beaver on a wooden path in a park during daytime. The beaver, positioned between the children, is slightly ahead, leading the way as if guiding them, while the girl looks down at it with a smile. The trio continues walking on the wooden trail, surrounded by lush greenery, with the beaver still in the lead, its bushy tail swaying side-to-side, and the children following closely behind, engaged in a joyful outdoor adventure.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's movements in the video are not smooth."
}
] |
seed42_2040
|
videos/HRA_part0/2040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 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": "Normal. Did not generate black shoes."
}
] |
seed44_2597
|
videos/HRA_part1/2597.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, brown vole walks purposefully across a lush, green meadow, its round body and short legs visible as it moves through the tall grass. The scene is set against a backdrop of vibrant flora, with the vole's movement drawing attention to its determination. Its fur is textured and rich in detail, and its eyes are alert and curious as it navigates the natural landscape. The vole's path is unobstructed, allowing for a clear view of its journey through the verdant field.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2715
|
videos/HRA_part1/2715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 great blue heron stands tall and majestic in a serene marshland setting, its feathers gleaming under the soft sunlight. The heron's piercing yellow eyes scan the waters intently, its long, sharp bill poised for action. Nearby, lush green vegetation provides a vibrant contrast to the heron's stately form. Suddenly, the heron takes flight, its broad wings gracefully propelling it through the air, against a backdrop of calm water and a clear blue sky dotted with fluffy white clouds. As it soars, the heron's silhouette is beautifully framed by the natural beauty of its marshland habitat.]"
},
{
"from": "gpt",
"value": "Bad. The blue heron's body is deformed when it flies in the video."
}
] |
seed44_2509
|
videos/HRA_part1/2509.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, wearing a gray shirt and blue jeans, is seen laughing heartily, holding a black electric guitar. The scene is set against a dark background with bright, colorful lights illuminating the musician from behind, adding a vibrant touch to the joyful moment. The musician's laughter is contagious, creating a warm and inviting atmosphere that captures the essence of pure happiness and the love for music.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1334
|
videos/HRA_part2/1334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is presented on a clean, white plate, its textured surface and irregular shape contrasting against the smooth, pristine background. The fish's left side faces upward, revealing its distinct dark brown coloration on top and lighter underside. Its eyes are both positioned on the darker left side, glistening and intact, indicating its freshness. The halibut's skin bears a natural pattern of spots and lines, and its mouth is slightly open, showing its small teeth. The setting is simple and unadorned, allowing the fish to be the focal point, perfect for a culinary or educational video feature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2043
|
videos/HRA_part0/2043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a gray jacket and dark pants, walks down a clean hallway illuminated by bright overhead lights, holding a small, active gerbil in a transparent plastic ball. The gerbil, running energetically on its wheel inside the ball, seems unfazed by the movement. The janitor navigates around a corner, continuing his journey with the gerbil in tow, the clean environment and well-lit corridor reflecting the diligence of his custodial duties.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2129
|
videos/HRA_part2/2129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 muscular man with a shaved head, wearing a black wetsuit, emerges from a pool on a space station, the water dripping from his body as he looks determined. The futuristic prison, with its high-tech security systems and alien guards, is visible in the background. The man, an inmate, uses his skills as a competitive swimmer to escape through the station's aquatic ventilation system, propelling himself through water-filled tunnels with powerful strokes. He reaches a critical junction, where he must hold his breath and navigate a complex series of underwater passages to avoid detection by the guards. Finally, he breaks the surface in an outdoor area, gasping for air and celebrating his hard-won freedom under the stars.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_3099
|
videos/HRA_part1/3099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sunlit savannah dotted with distant acacia trees, a large herd of African cape buffaloes gathers. The scene opens with a panoramic view of the herd, then zooms in on two buffaloes standing face-to-face, seemingly engaged in a dance-like interaction. The dominant male, with massive horns and a thick mane, takes a step forward, while the other male responds with a matching step, creating a rhythmic pattern. They continue this 'dance', mirroring each other's movements against the serene backdrop of the savannah, the clear blue sky, and the distant horizon, evoking a sense of primal connection and ritual within the herd.]"
},
{
"from": "gpt",
"value": "Normal. The wildebeest's legs are slightly deformed."
}
] |
seed42_3108
|
videos/HRA_part0/3108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged male nurse with short, dark hair and glasses, wearing a pale blue scrub top and pants, carefully lifts a frail elderly patient from a hospital bed. The patient, a thin woman with short gray hair, is dressed in a hospital gown and has an oxygen tube in her nose. The nurse, with a strong yet tender grip, supports her under her arms and legs, ensuring her comfort and safety throughout the transfer. The scene takes place in a well-lit, modern hospital room, with medical equipment and a window visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The male nurse's face generation is distorted, fingers are deformed, and the patient's face is incompletely generated."
}
] |
seed46_1048
|
videos/HRA_part2/1048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prison, a rugged man with a shaved head, dressed in a torn orange jumpsuit, stealthily caresses a metallic wall panel, searching for a hidden mechanism. His intense eyes scan the surroundings, alert for any sign of danger. He gently touches the cold surface, feeling for inconsistencies. Suddenly, his fingers find a concealed switch, and he looks relieved yet cautious. With a quick glance over his shoulder, he presses the button, triggering a sequence that promises his daring escape from the confined, sterile prison cell.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2955
|
videos/HRA_part2/2955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a yellow fire-resistant jacket, is kneeling by a blocked drain on a rainy day, amidst urban surroundings. He wields a long, coiled hose and a specialized tool, methodically working to unclog the drain. His focused expression and the rain-soaked environment underscore the challenging task at hand. Moments later, he pulls the clog from the drain, revealing a mix of debris, while water begins to flow freely again, thanks to his diligent efforts. Throughout, the firefighter's protective gear and the wet cityscape provide context to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1405
|
videos/HRA_part1/1405.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, curious ferret clad in a tiny green jacket ambles along a wooden floor, its alert eyes scanning its surroundings. It pauses for a moment, seemingly considering its next move, before continuing its journey. The ferret then stops again, standing on its hind legs with its front paws raised, revealing the white fur beneath the jacket. Its head turns to look directly at the camera, a mischievous glint in its eyes, before it resumes walking, the green jacket swaying with each step. Throughout the video, the ferret's movements are unhurried and deliberate, as it explores its environment with a mix of caution and curiosity.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2385
|
videos/HRA_part2/2385.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in a yellow shirt, green vest, and brown shorts leaps into the air with his arms extended above his head, against a backdrop of dense subtropical forest. The lush green foliage, including palm fronds and ferns, provides a vibrant setting. In another frame, he jumps again, this time with his arms wide open, wearing a white cap, dark sunglasses, and a smile, against a similar background of rich, verdant trees. Throughout the sequence, the man's joyful expressions and dynamic poses capture the essence of his energetic exploration within the vibrant subtropical woodland environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2183
|
videos/HRA_part1/2183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a yellow vest and khaki pants, takes a break from cleaning the vast, empty stadium to joyfully dance alone under the bright lights. With a mop in his right hand and a bucket nearby, he moves across the polished concrete floor, surrounded by rows of blue seats. The overhead view captures his spontaneous dance moves, highlighting the contrast between his work and play in the expansive, quiet stadium. His movements, set against the backdrop of the stadium's architecture and the night sky visible through the open roof, convey a sense of freedom and self-expression.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's limbs are missing in the video, and the face is generated blurily."
}
] |
seed44_1215
|
videos/HRA_part1/1215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a stethoscope around her neck and a name badge on her scrubs, speaks earnestly with a concerned patient in a hospital room. The nurse, with her brown hair pulled back into a bun, leans forward attentively, making direct eye contact, while holding a clipboard with medical records. Moments later, she smiles warmly, offering reassurance and hope, as she continues the conversation. Throughout, the setting remains within the sterile, yet comforting environment of the hospital room, with machines beeping softly in the background.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2742
|
videos/HRA_part0/2742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, temperate rainforest, a janitor, dressed in a yellow vest and dark green pants, leaps over a fallen log with surprising agility. Surrounded by towering trees and dense foliage, he lands gracefully on the mossy ground, his movements deft and sure. As he continues his unlikely journey, bounding from one natural obstacle to another, the vibrant greens of the forest serve as a striking contrast to his utilitarian attire. Throughout this unexpected scene, the janitor's expression is one of focused determination, his form mid-jump captured against the backdrop of the rainforest's rich biodiversity.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_1523
|
videos/HRA_part1/1523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a gray suit, white shirt, and red tie, is seen in a wide office space, mopping the floor with a green mop and bucket. The office features a large window, a desk with a computer, and a bookshelf filled with law books, creating a professional atmosphere. The lawyer, with short brown hair and glasses, demonstrates an unexpected side as he diligently cleans the floor, highlighting the versatility and hardworking nature of legal professionals.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, legs are deformed, and feet are contorted."
}
] |
seed42_2417
|
videos/HRA_part0/2417.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, golden cheetah crawls under a low-hanging, silver photon sail, its eyes fixated ahead, muscles rippling beneath its spotted coat, set against a backdrop of a futuristic, metallic landscape. The sail, towering above, reflects beams of sunlight, creating an ethereal glow around the big cat. The cheetah, with its distinctive black tear markings and piercing green eyes, moves gracefully, its body positioned low to the ground, as if stalking prey, while the sail's advanced technology hints at a world beyond nature.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's movements in the video are not smooth."
}
] |
seed46_2507
|
videos/HRA_part2/2507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 swordfish, distinguished by its elongated bill resembling a sword, swims gracefully through the clear blue waters of the ocean. Its body, a sleek silver hue with a dark blue back, glides effortlessly as it navigates the aquatic environment. Sunlight filters through the water, casting shimmering highlights on the fish's streamlined form. The surrounding marine life, including schools of smaller fish scattering in its presence, underscores the swordfish's dominance in its habitat. Against the vast, open sea, the swordfish embodies power and agility, its unique appearance and behavior captivating the viewer in this underwater scene.]"
},
{
"from": "gpt",
"value": "Normal. The sailfish's fins and mouth generation in the video have 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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional 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": "Good. Basically correct."
}
] |
seed42_2614
|
videos/HRA_part0/2614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a muscular build, wearing a black tank top and blue jeans, pushes against a large, gray boulder in the middle of a lush forest. His face contorts with effort, highlighting his determination. The scene is set in a dense woodland area, with sunlight filtering through the trees and casting dappled shadows on the ground. The man's strong physique and focused expression convey a sense of strength and perseverance as he exerts himself against the immovable object.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2930
|
videos/HRA_part0/2930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a gray T-shirt and black cargo pants, methodically mops the floor of a modern industrial space, surrounded by sleek machinery and equipment. His attire includes a name badge and a pair of safety glasses hanging around his neck, signifying his professional role. The scene is lit by bright overhead lights, casting shadows that emphasize the rhythmic motion of the mop. The engineer's focused gaze and steady hand convey a sense of duty and precision as he tackles the mundane task of cleaning, set against the backdrop of a high-tech environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1768
|
videos/HRA_part0/1768.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid, close-up shot, a sleek, black king cobra emerges from the underbrush, its distinctive hood fully spread as it propels itself forward with surprising speed. Its body, covered in smooth scales, undulates gracefully over the forest floor, showcasing the powerful muscles beneath. The cobra's intense, amber eyes remain fixed ahead, conveying a sense of purpose and determination as it navigates the complex terrain with agility and precision. The lush greenery and dappled sunlight create a dynamic contrast against the snake's dark form, highlighting the primal energy of this extraordinary creature in motion.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2623
|
videos/HRA_part0/2623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vastness of space, two astronauts clad in advanced EVA suits, adorned with NASA logos, meticulously perform repairs on the International Space Station, crawling along the exterior with focused determination. Sunlight glints off their helmet visors, highlighting their concentration, as they carry out their critical tasks against the backdrop of Earth's horizon, showcasing the isolation and gravity of their mission.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2193
|
videos/HRA_part0/2193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman with brown hair tied back in a ponytail, wearing a gray cardigan over a white blouse and jeans, meticulously dusts furniture in a classroom. She moves with precision, her facial expression one of concentration. The room is filled with sunlight, illuminating the specks of dust floating in the air. She pauses for a moment, her hands on her hips, surveying her work before continuing. The classroom is mostly empty, save for a few desks and chairs, giving the impression of a quiet, orderly space. Throughout the scene, she remains focused on her task, her movements deliberate and efficient.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand in the video has generation issues."
}
] |
seed42_1832
|
videos/HRA_part0/1832.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scenario, an astronaut wearing a gray spacesuit walks on an asteroid's surface, which is rich in minerals, while in the background, an unexpected sight unfolds: a full-grown moose, also wearing a spacesuit, roams freely, seemingly adapted to zero gravity. The astronaut, equipped with a helmet and backpack, explores the rocky terrain, while the moose, with its large antlers and hefty frame, adds an element of surrealism to the scene. Both figures are set against the backdrop of space, with distant stars and galaxies visible in the vast emptiness.]"
},
{
"from": "gpt",
"value": "Normal. The adult moose's movements in the video are not smooth."
}
] |
seed42_3005
|
videos/HRA_part0/3005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, complete with a gray suit, red tie, and glasses, is kneeling in a whimsical scene beside a meerkat standing upright. The lawyer gently wipes the meerkat's face with a white cloth, both figures set against a vibrant green grassy background under a clear blue sky, creating an unusual yet captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2083
|
videos/HRA_part0/2083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter with neatly combed brown hair and a black uniform serves a couple seated at a beachside table, the ocean's horizon providing a romantic backdrop. He carefully places two plates of food on the table, his hands displaying a gentle, caressing motion, as if cherishing the art of serving. The couple looks on appreciatively, the man wearing a gray T-shirt and glasses, the woman adorned in a black dress with a plunging neckline. The scene is set during the golden hour, with the sun's rays casting a warm glow over the ocean and the couple, encapsulating a moment of intimate dining by the sea.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand appears deformed, and a white plate suddenly appears in his hand."
}
] |
seed44_2915
|
videos/HRA_part1/2915.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent cheetah, embodying grace and power, rests on a dry, grassy savanna, its body curved in a relaxed position. It turns its head, using its paw to wipe its face, showcasing a natural, intimate grooming moment. The cheetah's distinctive black spots stand out against its tan fur, while its piercing eyes and pronounced facial features add depth to the scene. This close-up shot captures the animal's wild beauty and the serene environment surrounding it, with distant trees adding a sense of place to the composition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2631
|
videos/HRA_part0/2631.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, evident from his refined facial features and confident posture, rakes leaves in an autumn backyard. He wears a brown jacket over a crisp white shirt, paired with khaki trousers, and brown shoes, presenting a polished appearance. The lush green grass, vibrant red leaves scattered about, and a large tree with a tire swing in the background create a warm, inviting atmosphere. The lawyer, possibly taking a break from his legal work, enjoys the simple pleasure of outdoor chores, his face expressing satisfaction and tranquility amidst the rich colors of fall.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's fingers and feet are missing in the video, the face is generated blurriy, and the cleaning tool in hand is distorted."
}
] |
seed44_1869
|
videos/HRA_part1/1869.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a red, white, and blue superhero costume, runs across a vast, rocky terrain that resembles the surface of Jupiter's moon, Io. In the background, the ominous and massive Great Red Spot of Jupiter looms, its swirling storm clouds dominating the planet's atmosphere. The actor's cape billows behind him as he sprints, his muscular physique and determined facial expression conveying strength and purpose. Despite the alien landscape and the daunting natural phenomenon in the distance, he maintains his focus, highlighting the human element in this cosmic setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's running in the video is very unsmooth, and his movements are not coordinated."
}
] |
seed44_1113
|
videos/HRA_part1/1113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, its fur thick and weathered, crawls through a dense forest underbrush, navigating beneath low-hanging branches and over decaying logs. The wolf, exhibiting signs of fatigue or stealth, moves slowly and deliberately, its eyes alert and ears perked, indicating heightened senses. The camera captures this intimate moment from a low angle, emphasizing the wolf's determination and resilience in its natural habitat. The wolf's body language suggests it may be injured or engaged in a cautious hunt, adding to the dramatic tension of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The gray wolf in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed42_1900
|
videos/HRA_part0/1900.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, wearing a small backpack adorned with patches, walks purposefully across a barren lunar landscape under a star-studded sky, holding a well-thumbed copy of a science fiction novel in its mouth. Its eyes, filled with curiosity and determination, reflect the distant stars. It passes by a small, glowing campfire, hinting at a recent gathering of fellow space book club members, who have presumably shared tales from their latest galactic reads. The fox continues its journey, the book's title, \"Cosmic Chronicles,\" visible as it strides forward into the cosmic night, leaving footprints on the moon's dusty surface.]"
},
{
"from": "gpt",
"value": "Bad. The red fox in the video generates abnormally, with its body gradually distorting and deforming in the middle frames."
}
] |
seed44_317
|
videos/HRA_part1/317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a fantastical scene, two small children wearing vibrant space suits crawl across the rugged terrain of Pluto's icy mountains, their movements slow and deliberate due to the planet's low gravity. The landscape is dominated by towering, sparkling ice formations that reflect the dim, alien sunlight. One child looks back with wide-eyed wonder, their helmet visor fogging slightly from their breath. Beside them, a robust rover equipped with large wheels and advanced scientific instruments sits idle, providing a sense of scale to the vast, icy environment. The overall atmosphere is one of awe-inspiring isolation and the pure joy of exploration, encapsulated in the children's expressions and the vast, untouched beauty of Pluto's surface.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2390
|
videos/HRA_part0/2390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and unexpected scene, a waiter wearing a traditional French uniform, complete with a black vest, white shirt, black bow tie, and black pants, is shown running alongside a full-grown rhinoceros. Both are moving at a steady pace across a lush, green grassland, under a bright blue sky dotted with white clouds. The waiter maintains a focused expression, while the rhinoceros runs with its head held high, creating a surreal and comical juxtaposition of elegance and wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, and legs are distorted in the video, as well as the rhinoceros's legs."
}
] |
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 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, 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": "Bad. The dromedary's body and legs are twisted in the video."
}
] |
seed42_1036
|
videos/HRA_part0/1036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crow perches on a thin branch, set against a vivid orange sunset, its silhouette stark and striking. The bird has ruffled feathers, indicating a recent bout of activity, and it looks directly at the camera with one intense eye. Its beak is slightly open, as if about to call out into the dusky sky, which is ablaze with fiery hues of red and gold, casting a warm glow on the crow's form. The branch it rests on is delicate, barely able to support its weight, adding a sense of precarious balance to the scene. Behind the crow, the last rays of sunlight filter through the gaps in the bare tree branches, creating a dramatic interplay of light and shadow.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1917
|
videos/HRA_part1/1917.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully cooked piece of salmon, expertly seared to achieve a perfect golden crust, sits center stage on a white ceramic plate. The salmon boasts a vibrant orange-pink interior, flaky yet moist, with a hint of dill sprinkled over it. Surrounding the fish are vibrant green asparagus spears, steamed to retain their crisp texture and natural color. Completing the dish is a drizzle of creamy sauce, likely a blend of lemon, butter, and capers, adding a touch of elegance and flavor. The plate is garnished with a sprig of parsley, enhancing the visual appeal of this exquisite salmon dish.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2134
|
videos/HRA_part1/2134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus, its body a rich tapestry of brown and orange hues, sprawls across a rocky reef, each of its eight muscular arms adorned with a series of suckers. Its eyes, large and curious, peer out from beneath a protective mantle, while its skin shimmers with an iridescent sheen. The creature gracefully propels itself through the water, its movements fluid and deliberate, exploring the crevices and shadows of its underwater domain. Surrounded by a vibrant ecosystem of coral and marine life, the octopus showcases its intelligence and adaptability, a true master of its environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2658
|
videos/HRA_part1/2658.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a dark green shirt, beige shorts, and a brown belt, is seen meticulously dusting vintage furniture within a grand room filled with antique artifacts. He pauses to adjust his glasses, revealing a look of deep concentration. His gaze then shifts to a large painting hanging on the wall, as if contemplating its significance. The director continues his task, now focusing on a wooden cabinet, his movements deliberate and precise, demonstrating his attention to detail. Lastly, he inspects a polished table, his reflection visible in its gleaming surface, as he ensures every inch is free from dust, all the while remaining in the same room with its collection of cherished items.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2643
|
videos/HRA_part0/2643.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic, space-themed setting, a chef wearing a white uniform and a red bandana stands out against the metallic walls of what appears to be a bank interior. He walks purposefully, holding a large, clear bag filled with currency, suggesting a daring robbery. The chef's attire, which includes a white chef's jacket, black pants, and a red bandana, contrasts sharply with the cold, metallic environment. The scene is set in a space bank with curved, silver walls and a floor covered in scattered bills, as the chef strides away, his unique occupation and bold actions creating a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_1513
|
videos/HRA_part1/1513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 conservation worker, dressed in a brown long-sleeved shirt and khaki cargo pants, is crawling on his hands and knees across the grassy terrain of a historical site. He meticulously examines the ancient stone structures, his focus intense as he searches for signs of wear or damage needing repair. The historical site, a series of weathered stone ruins set against a backdrop of lush greenery, is both his workplace and passion. His dedication to preserving history is evident in every careful movement, as he works under the open sky, surrounded by the remnants of the past.]"
},
{
"from": "gpt",
"value": "Bad. The face and hands of the worker in the video have generation issues."
}
] |
seed44_255
|
videos/HRA_part1/255.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 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, 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": "Bad. The meerkat's neck and facial features were generated incorrectly, the claws were deformed, the ears were missing, the bow tie was deformed, the forelimbs were too long, and the man's ears were generated incorrectly."
}
] |
seed46_1835
|
videos/HRA_part2/1835.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a futuristic space movie set, a life-size animatronic moose, sporting a metallic silver spacesuit, is being wiped down by a crew member in a pristine white lab coat. The set is dominated by a large, circular spaceship door with hexagonal bolts, and features a control panel with green buttons and switches. The moose, with its antlers adorned with blinking red lights, stands against a backdrop of sleek, metallic walls and a floor grid, creating a surreal juxtaposition of nature and sci-fi technology. The crew member meticulously wipes the moose's suit, ensuring it's ready for its intergalactic scene, while the set's high-tech details add to the otherworldly atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the staff wiping the mechanical moose in the video are not smooth and very uncoordinated."
}
] |
seed42_302
|
videos/HRA_part0/302.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a yellow apron over his gray shirt and dark pants, diligently scrubs a bathroom floor with a green cleaning solution, using a large, round scrub brush. The bathroom is modern, featuring white walls, a white toilet, and a white sink. The man's focused expression and the steam from the hot water convey his determination to clean. In the next shot, he is seen squeezing out the dirty water from the mop into a large, rectangular bucket. Finally, he pauses to wipe his forehead with a red cloth, revealing his dedication to maintaining cleanliness in the restroom.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_3004
|
videos/HRA_part2/3004.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a dark suit with a crisp white shirt and maroon tie, stands in a modern kitchen with gray cabinets and countertops. He attentively loads dishes into a high-end stainless steel dishwasher, demonstrating domestic skills alongside his professional demeanor. His attire, complete with a tailored jacket and neatly folded sleeves, contrasts with the mundane household task, creating an intriguing juxtaposition of professional and personal life. Throughout the scene, the lawyer's focused expression and meticulous movements highlight his commitment to detail, whether in the courtroom or at home.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's movements in the video are slightly unsmooth."
}
] |
seed46_2856
|
videos/HRA_part2/2856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, wearing a yellow blouse and khaki pants, is seen joyfully dancing in a classroom decorated with educational posters. On a nearby desk sits a small, curious gerbil, nibbling on a piece of wood inside its cage. The teacher's energetic movements and warm smile create a vibrant atmosphere, while the gerbil's playful antics add a touch of whimsy to the scene. The camera captures the dynamic interaction between the dancing teacher and the fascinated gerbil, highlighting the unique bond they share within the educational environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1638
|
videos/HRA_part1/1638.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, wearing a black vest and bow tie, is seen playfully crawling on his hands and knees across a wooden floor, following a small, adorable hamster. The hamster, enclosed in a clear plastic ball, rolls ahead of him, creating a comical and heartwarming interaction between the two. The setting is a tidy room with a hardwood floor, adding to the charm of this unexpected pairing.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's rolling and the person's crawling movements in the video are not smooth and coordinated."
}
] |
seed42_1783
|
videos/HRA_part0/1783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, costumed in a vibrant green shirt and brown pants, strolls alongside a life-sized, realistic hippopotamus puppet, which is operated by two puppeteers dressed in all-black attire. The trio walks across a grassy field under a clear blue sky, creating a whimsical and unexpected scene. The actor, with a bemused smile, interacts with the puppet, which responds with lifelike movements and expressions, adding to the surreal atmosphere of the outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2064
|
videos/HRA_part2/2064.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 people are gathered at a pristine lake nestled in the heart of a lush, green forest, engaging in various activities. Some are wiping their feet on a large, sandy beach, preparing to enter the clear, inviting waters. Others are seated on the shore, enjoying the serene surroundings as they wipe sand from their hands and feet. The scene is peaceful, with the sound of water lapping against the shore and birds singing in the trees overhead. The lake, framed by towering pines and dotted with small boats, provides a stunning backdrop for this tranquil moment.]"
},
{
"from": "gpt",
"value": "Bad. The small boat did not appear in the video."
}
] |
seed42_3038
|
videos/HRA_part0/3038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with complex machinery and computer screens displaying intricate data, a lone scientist in a white lab coat meticulously examines a vial containing a mysterious, shimmering liquid, believed to be a sample of dark matter. Meanwhile, in a contrasting scene, a majestic gray wolf, its fur glistening under the moonlight, leaps gracefully from a rock into a serene, moonlit lake, creating ripples that spread across the water's surface. The juxtaposition of these two scenes highlights the intriguing connection between the enigmatic world of dark matter research and the primal, untamed beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The video only shows the lake surface slightly moving, with the gray wolf completely still."
}
] |
seed46_2769
|
videos/HRA_part2/2769.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a charcoal gray suit, white shirt, and red tie, sits at a large wooden desk in a traditional law office setting, which includes a bookcase filled with legal books and documents. The room is illuminated by natural light from a window behind the desk, casting a warm glow over the space. The lawyer, with neatly combed brown hair and glasses, holds a pen in his right hand and looks down at a document on the desk. Suddenly, he brings his left hand to his mouth to cover a cough, his eyes closing briefly as he experiences discomfort. The scene captures the professional environment and the unexpected moment of vulnerability.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's fingers in the video have generation issues, the glasses are deformed, and at the end of the video, when the lawyer's fingers are placed on the face, the overall generation is deformed."
}
] |
seed42_2757
|
videos/HRA_part0/2757.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical cartoon style, a cheerful nurse with rosy cheeks, bright eyes, and a traditional uniform is depicted mid-jump, with a small, friendly rat leaping alongside her. Both the nurse and the rat display exaggerated expressions of joy and excitement, capturing a sense of playful camaraderie. The nurse's outfit is crisp and clean, adding to the overall upbeat and carefree atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted, and the arm is twisted."
}
] |
seed44_1159
|
videos/HRA_part1/1159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned janitor, clad in a brown jacket and blue jeans, meticulously rakes a pile of autumn leaves into a neat heap on a school campus, his weathered hands gripping the wooden handle of the rake. The scene is set against a backdrop of a large, red-brick school building, with a signpost nearby. He pauses to wipe sweat from his brow, revealing a determined look, before resuming his task with renewed vigor, the golden afternoon sunlight casting long shadows across the leaf-strewn grounds.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is twisted, the face is distorted, and the hoe in the hand is also twisted."
}
] |
seed42_2287
|
videos/HRA_part0/2287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rugged firefighter, complete with helmet and heavy-duty gear, takes a break from the norm as he meticulously vacuums a cozy living room, adorned with a plush sofa, rustic wooden coffee table, and vibrant houseplants. The scene opens with a close-up of the vacuum cleaner, a stark contrast to the typical firefighting tools, before panning to reveal the dedicated firefighter, hose in hand, methodically cleaning the carpet. The camera then captures the firefighter's gloved hands guiding the vacuum, followed by a shot of him standing upright, holding the vacuum hose, and looking content amidst a tidy room, where a tidy bookshelf and comfortable armchair complete the domestic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1718
|
videos/HRA_part0/1718.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches on a thin branch, its vibrant plumage of green, blue, and orange feathers catching the sunlight. It has a slender body, a long, pointed tail, and a distinctive, curved beak. The bird's eyes are alert, scanning the surroundings for potential prey. Suddenly, it takes flight, its wings a blur of motion as it darts through the air, chasing after an unsuspecting insect. The scene is set against a backdrop of lush vegetation and clear blue skies, capturing the bird's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3052
|
videos/HRA_part0/3052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 art gallery filled with contemporary paintings and sculptures, a distinguished film director, wearing a gray suit with a blue shirt and tie, passionately discusses a project with two colleagues. Suddenly, he breaks into an impromptu dance, spinning and moving with joyful abandon. The gallery space, illuminated by spotlights highlighting the artwork, becomes his stage, with onlookers smiling and watching his spontaneous performance. Throughout, the director's animated expressions and gestures convey his enthusiasm and creativity, all captured in high-definition detail.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2067
|
videos/HRA_part1/2067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown bat with intricate wing details is seen crawling along a cave floor, illuminated by a soft, ambient light. It slowly makes its way across the rocky terrain, revealing its unique features in close-up. Meanwhile, in the distance, the planet Venus can be seen as a bright spot in the night sky, providing a celestial contrast to the terrestrial scene below. The bat's movements are deliberate and methodical, highlighting its adaptation to navigating dark environments, while Venus' presence adds a cosmic element to the composition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1523
|
videos/HRA_part2/1523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a gray suit, white shirt, and red tie, is seen in a wide office space, mopping the floor with a green mop and bucket. The office features a large window, a desk with a computer, and a bookshelf filled with law books, creating a professional atmosphere. The lawyer, with short brown hair and glasses, demonstrates an unexpected side as he diligently cleans the floor, highlighting the versatility and hardworking nature of legal professionals.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2959
|
videos/HRA_part0/2959.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished with salt-and-pepper hair and a trimmed beard, stands in a dimly lit, cluttered bathroom. Dressed casually in a gray t-shirt, dark jeans, and a black jacket, he focuses intently on unclogging a blocked sink drain. His right hand grips a metal tool, while his left hand steadies the sink's rim. The scene captures his determination, with the bathroom's sparse details - a white toilet, a beige wall, and a small window - adding context to his solitary task. The director's serious demeanor and the bathroom's functional design emphasize the mundane yet necessary act of home maintenance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1642
|
videos/HRA_part0/1642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in a brown jacket and beige pants is seen crawling on his hands and knees through a lush, green forest, with ferns and mossy rocks surrounding him. Moments later, a large moose with a majestic rack of antlers stands tall and vigilant nearby, observing the man's unusual behavior. The scene then focuses on the man's face, showing his determination and focus, while the moose continues to watch from a distance, its presence adding a sense of wildness and unpredictability to the forest setting. Finally, the man and the moose share a silent moment of connection, both existing in harmony within the natural world, the man still crawling and the moose standing tall, creating a unique and unexpected encounter in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Normal. The man's face and the moose's head in the video have generation issues."
}
] |
seed46_2325
|
videos/HRA_part2/2325.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a button-down shirt and khaki pants, rearranges the furniture in a modern living room. He first adjusts a wooden table, pushing it closer to a brown leather sofa. Next, he moves a gray armchair, placing it at an angle near the sofa, creating a cozy seating arrangement. The doctor then fine-tunes the position of a glass coffee table, centering it between the sofa and armchair. Lastly, he adds a touch of greenery by positioning a potted plant next to the armchair, completing the refreshed layout of the room.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_276
|
videos/HRA_part2/276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, two people clad in sportswear run side by side down a vibrant street, passing by towering skyscrapers that glisten under the bright sunlight. The runners, a man in a red shirt and black shorts, and a woman in a purple tank top and gray leggings, navigate through the urban landscape with ease. Pedestrians, some in business attire and others casually dressed, walk alongside them, creating a dynamic atmosphere. The towering buildings, adorned with reflective glass, cast long shadows across the street, adding depth and contrast to the urban setting. Throughout the video, the runners maintain their pace, their determination evident as they weave through the crowd and continue their journey among the impressive cityscape.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, and the leg is twisted."
}
] |
seed42_237
|
videos/HRA_part0/237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush subtropical moist forest, a young, athletic female cashier, donning a green vest and khaki shorts, is depicted running with intense focus, her eyes fixed ahead. Suddenly, a cobra slithers across her path, its hood dramatically spread. Unfazed, she leaps gracefully over the snake, her action capturing a powerful moment of survival instinct. As she continues her run, the dense vegetation and towering trees of the subtropical environment envelop her, highlighting her determination and agility amidst the wild setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3216
|
videos/HRA_part1/3216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray jacket and blue jeans, runs with a determined look across a desolate industrial landscape dominated by oil refineries. The scene opens with him striding purposefully, his gaze fixed ahead. Next, he's seen mid-stride, his right arm extended forward, the refineries' towering structures and billowing smokestacks looming behind him. Then, he's captured in motion, his left foot lifting from the ground, the industrial backdrop providing a stark contrast to his vibrant attire. Finally, the artist continues his run, his silhouette framed against the imposing oil refinery complex, embodying resilience and movement in an urban-industrial setting.]"
},
{
"from": "gpt",
"value": "Bad. The artist's running motion in the video is not smooth."
}
] |
seed42_3006
|
videos/HRA_part0/3006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green environment, a small brown mouse stands on the edge of a natural pool, surrounded by dense shrubbery and tall grass, creating an intricate network of thickets. The mouse looks intently at the water, its ears perked and body alert. Suddenly, it bravely leaps into the clear, shimmering pool, swimming with surprising agility, its tiny paws propelling it through the water. As it swims, the camera captures the ripples created by its movement, highlighting the contrast between the busy activity of the mouse and the stillness of the thickets surrounding the pool.]"
},
{
"from": "gpt",
"value": "Bad. The brown mouse in the video is generally malformed."
}
] |
seed44_2570
|
videos/HRA_part1/2570.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit theater, an elegant lawyer, attired in a black suit, white shirt, and red tie, sits pensively with his hands clasped. Beside him, a taxidermied jackal wearing a miniature lawyer outfit sits upright on a chair, adding a surreal touch. The lawyer then wipes his brow with a handkerchief, appearing relieved yet cautious, as if contemplating a significant decision. The scene maintains a consistent setting within the theater, focusing on the lawyer's expressions and the unusual presence of the costumed jackal.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1005
|
videos/HRA_part1/1005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a crisp white uniform and a colorful stethoscope, finds herself at the edge of a vast, shimmering ocean, where the sand meets the water. In her arms, she holds a small, fluffy rabbit, its ears perked up in curiosity. Together, they watch as a group of rabbits, similarly white and fluffy, leap and jump playfully across the sandy shore, the waves gently lapping at the background, creating a serene and whimsical scene.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's jumping movements on the beach are not smooth and continuous. The nurse and the rabbit in her hands make extra movements."
}
] |
seed46_2658
|
videos/HRA_part2/2658.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a dark green shirt, beige shorts, and a brown belt, is seen meticulously dusting vintage furniture within a grand room filled with antique artifacts. He pauses to adjust his glasses, revealing a look of deep concentration. His gaze then shifts to a large painting hanging on the wall, as if contemplating its significance. The director continues his task, now focusing on a wooden cabinet, his movements deliberate and precise, demonstrating his attention to detail. Lastly, he inspects a polished table, his reflection visible in its gleaming surface, as he ensures every inch is free from dust, all the while remaining in the same room with its collection of cherished items.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_3000
|
videos/HRA_part2/3000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a neatly trimmed beard, sits pensively on a vintage brown leather couch, wearing a blue checked shirt, dark pants, and brown shoes. Suddenly, he holds his chest and coughs intensely, his eyes squeezed shut, indicating discomfort. The scene is set in a warmly lit room with wooden walls, showcasing a rustic environment. As the coughing fit subsides, he looks concerned, placing his hand back on his chest, suggesting a moment of reflection on his health, all while maintaining the same attire and setting.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the man clutching his chest, closing his eyes tightly, and coughing violently. The actions are basically normal but there is some lack of coordination."
}
] |
seed44_2724
|
videos/HRA_part1/2724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red flannel shirt, beige pants, and brown suspenders, stands at a white sink in a rustic kitchen. He is washing dishes by hand using a sponge, with a wooden cutting board and a bowl of fruit visible nearby. The farmer, who has short brown hair and a neatly trimmed beard, demonstrates his commitment to household chores with a focused expression. The kitchen is warm and inviting, with wood-paneled walls, a white refrigerator, and a window above the sink offering a view of green fields. The farmer's strong hands, calloused from years of working the land, now deftly clean plates and utensils, showcasing the versatility of his daily tasks.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's eyes in the video have generation issues, the fingers are deformed, and the plate is distorted."
}
] |
seed44_1036
|
videos/HRA_part1/1036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crow perches on a thin branch, set against a vivid orange sunset, its silhouette stark and striking. The bird has ruffled feathers, indicating a recent bout of activity, and it looks directly at the camera with one intense eye. Its beak is slightly open, as if about to call out into the dusky sky, which is ablaze with fiery hues of red and gold, casting a warm glow on the crow's form. The branch it rests on is delicate, barely able to support its weight, adding a sense of precarious balance to the scene. Behind the crow, the last rays of sunlight filter through the gaps in the bare tree branches, creating a dramatic interplay of light and shadow.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1586
|
videos/HRA_part0/1586.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station habitat, illuminated by soft, ambient lighting, a caring teacher, wearing a navy blue jumpsuit with silver accents, gently caresses the head of a young student seated at a desk. The student, dressed in a matching uniform, looks up with wide eyes, feeling comfort and support. Behind them, a large window reveals the stunning view of Earth, while various educational tools and floating objects fill the zero-gravity environment, creating an immersive learning atmosphere. The teacher's compassionate touch and the unique setting emphasize the nurturing bond between educator and pupil in this extraordinary space classroom.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2881
|
videos/HRA_part2/2881.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in casual attire consisting of a gray hoodie, blue jeans, and white sneakers, diligently scrubs the bathroom floor with a green cleaning rag. The bathroom is modern, featuring sleek white tiles and fixtures, with a hint of daylight filtering in from a nearby window. The student's focused expression and the repetitive motion of scrubbing convey a sense of determination and responsibility. The scene is set in a clean, well-lit space, emphasizing the student's hard work and attention to detail in maintaining the cleanliness of the bathroom environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1577
|
videos/HRA_part1/1577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant classroom decorated with colorful posters and student artwork, a passionate teacher, wearing a dark green shirt and khaki pants, is seen in the act of catching a ball, demonstrating a physics lesson on motion and gravity. The students, seated at their desks, watch intently as the teacher, with a lively expression, skillfully catches the ball mid-air, illustrating the principles of force and motion in an engaging and interactive manner.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's movements in the video are not smooth and lack coordination."
}
] |
seed44_2737
|
videos/HRA_part1/2737.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil, shallow pond surrounded by lush vegetation, a large moose with a wide, flat antler rack stands with its head submerged underwater. As it lifts its head, water droplets cascade down its face. The animal then proceeds to shake its head vigorously from side to side, flinging water off its fur and antlers. Its ears flap dynamically during the shaking motion, and its tongue can be seen hanging out playfully. Throughout the scene, the moose's eyes remain closed, indicating its enjoyment of the refreshing activity.]"
},
{
"from": "gpt",
"value": "Normal. The moose in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed42_2117
|
videos/HRA_part0/2117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a well-dressed lawyer, complete with a suit, tie, and glasses, sits calmly on a wooden bench outdoors. Against a backdrop of lush greenery, the lawyer gently caresses a porcupine, which remains relaxed and quill-free. The lawyer's demeanor suggests a deep connection with nature, particularly with the docile porcupine, which is depicted without its typical defensive quills, highlighting a unique bond between human and animal in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed44_1729
|
videos/HRA_part1/1729.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 adorable otter, with a round face and curious eyes, walks on its hind legs across a wooden boardwalk, holding a small fish in its front paws. It wears a tiny red scarf around its neck, adding a touch of whimsy to the scene. The otter's brown fur contrasts against the light wooden planks, while the lush greenery and calm water of a pond can be seen in the background, creating a serene and picturesque environment. The otter's confident stride and the fish it carries suggest it has just enjoyed a meal, making the scene both charming and heartwarming.]"
},
{
"from": "gpt",
"value": "Normal. The otter's hind legs walk basically normally, with slightly uncoordinated movements."
}
] |
seed44_2861
|
videos/HRA_part1/2861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-looking male chef, donning a white chef's jacket and black pants, stands in a bustling kitchen environment, pulling a large, fully loaded dish from a high-end, commercial-grade oven. The oven is integrated into a sleek, stainless steel kitchen setup. The chef exhibits a focused expression, displaying his expertise and confidence. The dish, brimming with an exquisite culinary creation, is positioned at the center of the frame, highlighting its appeal against the busy kitchen backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1666
|
videos/HRA_part2/1666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning round glasses and a yellow sweater, sits at a wooden table cluttered with writing tools and a laptop, knitting a vibrant red scarf with large needles. The scene is set in a cozy room with a rustic wooden floor and a large window, through which daylight softly illuminates the space. On the wall hangs a large, colorful painting, adding a touch of artistic flair. The writer's hands, adorned with rings and bracelets, skillfully manipulate the knitting needles as they work on the scarf, all while surrounded by the warm, inviting atmosphere of the room.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are not smooth and lack coordination."
}
] |
seed46_2302
|
videos/HRA_part2/2302.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, clad in a brown leather jacket and blue jeans, traverses a desolate, rocky terrain reminiscent of Mars, accompanied by a robotic jackal. The landscape is barren and reddish, with distant mountains and a dim, orange-tinged sky. The writer, equipped with a backpack and walking stick, navigates the rough path, while the robotic companion, featuring sleek silver plating and glowing blue eyes, follows closely. The pair embarks on an adventure, exploring the rugged environment, with the writer occasionally stopping to jot down notes and the robot scanning the surroundings with its advanced sensors.]"
},
{
"from": "gpt",
"value": "Bad. The writer and the mechanical wolf walk very unsmoothly, with uncoordinated movements."
}
] |
seed42_1096
|
videos/HRA_part0/1096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 reality TV set, an antelope, wearing a small golden bell around its neck, stands calmly against a backdrop of stars and galaxies. The animal is gently caressed by a human figure dressed in a spacesuit, conveying a sense of comfort and companionship in the vastness of space. The astronaut's gloved hand softly touches the antelope's face, while the creature looks on serenely, the golden bell shining under the starlight, creating a surreal and touching moment in an extraterrestrial environment.]"
},
{
"from": "gpt",
"value": "Normal. The antelope has a golden bell on its mouth, which is unrealistic, and the astronaut's fingers appear deformed."
}
] |
seed44_1590
|
videos/HRA_part1/1590.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, dressed in a red shirt, black vest, and dark pants, stands on a dimly lit stage, pointing with his right hand. He wears a black beret and glasses, adding to his artistic flair. Behind him, a vibrant purple curtain complements the stage lights, which cast a warm glow on his face. His left hand rests on his hip, and he points emphatically with his right, engaging the audience in a dynamic performance. The background is blurred, emphasizing the musician's commanding presence as he points with passion and intensity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1486
|
videos/HRA_part2/1486.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, lush green forest setting, two young boys, one wearing a red t-shirt and shorts, and the other in a blue shirt and shorts, are seen interacting with a pair of deer. One boy gently wipes mud off a deer's leg using a cloth, showing care and concern, while the other observes intently. The deer stand calmly, trusting the boys' presence. The scene captures a tender moment of compassion and connection between children and nature. The forest backdrop, with its tall trees and dappled sunlight, adds to the peaceful atmosphere, highlighting the innocence and beauty of the interaction.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2126
|
videos/HRA_part0/2126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, costumed in a shimmering silver outfit reminiscent of celestial bodies, performs an interpretive dance against a backdrop of the Uranus aurora. The aurora, with its vivid green and purple hues, illuminates the scene with an ethereal glow. The actor's movements are fluid and expressive, capturing the essence of cosmic energy and the mystical atmosphere of the distant planet. As the dance progresses, the auroral lights pulsate and swirl, creating a mesmerizing visual harmony between the performance and the celestial phenomenon. Throughout the video, the focus remains on the captivating dance, with the Uranus aurora serving as a breathtaking and dynamic canvas for the actor's artistry.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, hand is twisted, face is distorted, and body is twisted."
}
] |
seed46_1136
|
videos/HRA_part2/1136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male musician, donning a red cap, stylish sunglasses, and a gray shirt, stands against a blurred background, engagingly waving at the audience with his right hand. Moments later, he passionately plays his guitar, exuding energy and confidence. He then smiles broadly, his eyes closed, clearly enjoying the music and the connection with his fans. Finally, he returns to waving, his joyful demeanor and dynamic presence captivating the crowd, all set against a backdrop of a lively concert atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_2942
|
videos/HRA_part1/2942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 strong, focused woman wearing a red helmet and climbing gear scales a towering rock face, the texture of the stone rough under her hands and feet. The camera captures her intense concentration, the strain in her muscles, and the determination in her eyes. Sunlight filters through wispy clouds, casting dramatic shadows on the cliffside as she ascends higher, leaving the green valley far below. The scene is framed by rugged terrain, emphasizing her solitary endeavor against the vast, natural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the female rock climber's climbing movements, which are not continuous and very uncoordinated."
}
] |
seed42_2687
|
videos/HRA_part0/2687.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling metropolis, an innovative female engineer wearing safety glasses and a reflective vest runs through a construction site filled with cranes and skyscrapers under construction. Her stride is confident, highlighting her determination. She navigates around concrete pillars and rebar, demonstrating agility amidst the urban landscape. The cityscape, featuring tall buildings and bridges, serves as a backdrop, emphasizing the scale of her environment. Throughout the scene, she maintains her composure, showcasing her expertise and passion for engineering in an active urban setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_318
|
videos/HRA_part1/318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged female teacher waves energetically with both hands, standing against a classroom backdrop filled with educational posters and a whiteboard. Dressed in a vibrant red blouse and dark pants, she wears a welcoming smile, her wavy brown hair framing her face. Her enthusiastic gesture conveys warmth and inclusivity, inviting students into the learning environment. The classroom setting includes rows of desks, a bookshelf, and a large window allowing ample natural light, enhancing the sense of openness and engagement.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's fingers are deformed in the video, and there is an issue with the arm generation."
}
] |
seed42_2466
|
videos/HRA_part0/2466.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badges and a walkie-talkie attached to his belt, points assertively with his right hand while looking intently at something off-screen. He stands in a busy urban street scene, with pedestrians and vehicles in the background, conveying a sense of duty and command. His left hand rests on his hip, near his service weapon, and his authoritative stance is emphasized by the presence of a large, bustling city behind him, complete with tall buildings, traffic lights, and street signs.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.