video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_298
|
videos/HRA_part2/298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 enthusiastic engineer in a red shirt, beige vest, and khaki pants is seen in an amusement park, surrounded by roller coasters, with a Ferris wheel visible in the distance. He runs through the park with a map in hand, passing by various rides and attractions. The video captures him stopping briefly to study the map, before continuing his energetic jog through the lively environment, showcasing his passion for both engineering and the thrilling atmosphere of amusement parks.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2580
|
videos/HRA_part1/2580.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, captured in high definition, is seen grooming itself by wiping its face with a flipper. The otter, with its brown fur and small, round ears, sits upright on a rocky shore, the surface speckled with white stones. The background features a lush green forest, with tall trees standing majestically against a bright sky. The otter pauses, looking directly at the camera with curious eyes, before continuing its self-cleaning ritual, creating a captivating moment in nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1823
|
videos/HRA_part1/1823.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, athletic woman runs on a track under clear blue skies, her black hair tied back in a ponytail. She wears a yellow tank top, black running tights, and white running shoes, showcasing her strong physique. The camera captures her from various angles as she sprints, highlighting her focused determination. In one shot, she is seen from the side, her arms pumping with power. Another angle shows her from the front, her face set in intense concentration. The final shot is a close-up of her face, beads of sweat glistening on her forehead, embodying the spirit of perseverance and strength in motion.]"
},
{
"from": "gpt",
"value": "Bad. The woman's arm in the video is incomplete, and her facial features are blurry."
}
] |
seed46_1212
|
videos/HRA_part2/1212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wild salmon, exhibiting vibrant hues of silver, red, and green, swims gracefully in a crystal-clear river, its scales shimmering under the natural sunlight filtering through the water. The salmon's powerful body and forked tail are showcased as it propels itself upstream against the current, highlighting its determination and strength in nature's challenging environment.]"
},
{
"from": "gpt",
"value": "Normal. The salmon's mouth in the video is generated incorrectly."
}
] |
seed42_1630
|
videos/HRA_part0/1630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, passionate writer in a vibrant red dress is captured in a series of captivating moments, all set within the lush, golden ambiance of an orchard during autumn. She begins by standing pensively, holding a vintage typewriter, embodying creativity and inspiration. Next, she's shown mid-dance, arms elegantly extended, her movements expressive and free, the typewriter now resting on the ground, symbolizing her liberation from constraints. In another scene, she leans back, laughing joyously, her feet slightly off the ground, the typewriter still visible, highlighting her uninhibited spirit. Lastly, she strikes a confident pose, hands on hips, with a serene smile, the typewriter by her side, signifying her connection to both art and nature. Throughout, the orchard's warm colors and abundant fruit provide a rich, textured setting for her expressive journey.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video has missing limbs, facial and body deformities, and fingers are not generated."
}
] |
seed46_1686
|
videos/HRA_part2/1686.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 fluffy, baby panda with distinctive black and white fur crawls across a lush, green forest floor, surrounded by vibrant vegetation and bamboo shoots. It moves with a curious, almost playful demeanor, its tiny paws gripping the mossy ground. The scene is filled with natural light filtering through the dense canopy above, casting dappled shadows on the panda as it explores its environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2181
|
videos/HRA_part2/2181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Caspian tern soars gracefully through the air, its large size and robust build evident as it navigates the skies above a serene coastal landscape. With a striking orange-red bill that is thick and strong, this bird exemplifies power and agility. Its plumage is predominantly white, with a faint tinge of grey on the back, and its wings display black tips that contrast beautifully with the rest of its feathers. As it glides over the water, the tern's keen eyes search for prey, showcasing its hunting prowess against the backdrop of a calm sea and a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The gull's wings and tail in the video are missing."
}
] |
seed44_1877
|
videos/HRA_part1/1877.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 art gallery, illuminated by soft purple and blue lights, a woman with curly brown hair, styled in a bun, wears a silver sleeveless dress and silver earrings. She gently caresses a large, textured, abstract artwork, the colors of which resemble cosmic nebulas, while standing on a transparent floor that reveals city lights below. The walls are lined with similar cosmic-themed art pieces, creating an immersive environment. She leans toward the artwork, her expression showing deep appreciation, as she stands on the glowing, see-through floor, with the dazzling cityscape visible beneath her feet.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1674
|
videos/HRA_part0/1674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, typically found in woodland streams, curiously explores a sandy beach near a vibrant beach resort, walking along the shoreline with its distinctive flat tail and brown fur. It passes by colorful umbrellas and sun loungers, a unique sight among the usual beachgoers enjoying the sunny weather. The beaver's presence adds an element of surprise and charm to the bustling beach scene, as it navigates the sandy terrain with its natural grace and agility.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's movements in the video are not smooth."
}
] |
seed46_1086
|
videos/HRA_part2/1086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vivid close-up of an ibis's face, its piercing yellow eye set against a backdrop of dark feathers, commands attention. The bird's distinctive curved bill, a striking contrast to its plumage, adds character. Its textured feathers, a mix of brown and black, envelop the head, while the yellow iris and bill tip pop against the dark plumage. The ibis's head tilts slightly, revealing a patch of bare red skin, and its textured feathers frame the captivating facial features, capturing the essence of this unique bird species.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1705
|
videos/HRA_part1/1705.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casino, a distinguished chef, donning a traditional white chef's uniform with black stripes and a black necktie, walks with purpose. He carries a large, covered silver platter, its lid adorned with a golden handle. Behind him, a bustling kitchen reveals chefs in action, preparing exquisite dishes. The casino's opulent decor is visible through a glass partition, featuring patrons enjoying themselves at various gaming tables. The chef's confident stride and the casino's lively atmosphere create a captivating contrast between culinary expertise and the thrill of gambling in outer space.]"
},
{
"from": "gpt",
"value": "Normal. The black necktie does not appear in the video."
}
] |
seed46_2380
|
videos/HRA_part2/2380.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red beret and a white apron over her colorful outfit, stands in a vibrant laundry room filled with patterned tiles and graffiti art. She smiles as she sorts clothes into a vintage washing machine, her creative spirit evident in the artistic space around her. The room is illuminated by soft, yellow lights hanging from the ceiling, casting a warm glow over the artist's industrious yet joyful task. Surrounded by various paints and brushes on the walls, she pauses to admire a piece of abstract art hanging nearby, before returning to her domestic chore with a renewed sense of purpose.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are not smooth and are uncoordinated."
}
] |
seed46_3103
|
videos/HRA_part2/3103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chimpanzee dressed as a waiter in a red bow tie and apron over a white shirt and black pants, stands against a green screen backdrop. Initially, the chimp looks directly at the camera with its hands on its hips. Then, it begins to dance, swaying its body and moving its arms energetically to an unseen beat. The chimp's facial expressions range from serious to playful, adding to the surreal atmosphere of the scene. Throughout, the green screen remains unchanged, allowing the focus to remain on the dancing chimpanzee-waiter.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1288
|
videos/HRA_part0/1288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dingo, exhibiting a reddish-brown coat and alert demeanor, crawls near the base of a lush, cascading waterfall set within a dense, verdant forest. The waterfall, framed by towering trees and vibrant foliage, provides a dramatic backdrop as it plunges into a clear pool below, where the dingo stealthily approaches. The animal's cautious movement, combined with the serene yet powerful presence of the waterfall, creates a captivating scene of nature's raw beauty and untamed spirit.]"
},
{
"from": "gpt",
"value": "Bad. The dingo in the video walks very awkwardly, with uncoordinated movements."
}
] |
seed42_2499
|
videos/HRA_part0/2499.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, known for its brown fur and flat tail, swims underwater in a clear, glassy lake during the daytime. It surfaces, revealing its full body, including the distinctive markings on its face and body. The beaver then proceeds to swim along the bottom of the riverbed, showcasing its webbed hind feet propelling it forward. Throughout the video, the beaver remains submerged, occasionally coming up for air, with the tranquil water and lush green vegetation along the riverbank providing a serene backdrop for this aquatic mammal's natural behavior.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's limbs in the video have generation issues, and the eyes were not generated."
}
] |
seed46_2441
|
videos/HRA_part2/2441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 giant panda, identifiable by its distinctive black and white fur, engages in a leisurely stroll through a lush, green bamboo forest, its round body moving gracefully despite its bulk. It then proceeds to crawl, using its front paws to pull itself forward in a slow, deliberate motion, highlighting its unique method of navigating its environment. The panda's movements are unhurried and methodical, showcasing its relaxed demeanor as it explores its verdant surroundings. Throughout the scene, the panda remains the central focus, with the vibrant greenery of the bamboo forest providing a vivid contrast to its striking fur pattern.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1859
|
videos/HRA_part2/1859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer kneels on a grassy park area, attentively watching a squirrel. The squirrel, emboldened, leaps from the ground onto the officer's outstretched arm, seeking a nut held in the officer's other hand. The cop wears a standard police uniform, including a navy blue shirt, black tactical pants, and a badge, while the greenery and trees in the background set a peaceful outdoor scene. The squirrel's acrobatic leap and the officer's gentle interaction create a heartwarming moment in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel in the video has a twisted body, twisted paws, twisted face, and twisted legs."
}
] |
seed42_2558
|
videos/HRA_part0/2558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, wearing a green shirt and khaki shorts, walks through a savanna landscape, holding a book bag, with a hyena casually following at a distance. The student, in casual attire suitable for warm weather, continues walking along a dirt path, with the hyena maintaining a parallel path some distance away. As they move, the student occasionally glances back at the hyena, which returns the look, both seemingly unafraid and unperturbed by each other's presence, set against a backdrop of dry grasses and scattered trees typical of a savanna environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1954
|
videos/HRA_part1/1954.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a lifelike jaguar mascot, wearing a brown uniform and a name tag, leaps over a green cash register in slow motion, set against a vibrant yellow backdrop. The mascot, with its mouth playfully open, is captured mid-air, just above the register, which is adorned with colorful bills and coins. The cash register itself is old-fashioned, with a large price display and mechanical keys, adding a nostalgic touch to the dynamic scene.]"
},
{
"from": "gpt",
"value": "Bad. The head of the jaguar mascot in the video was generated abnormally."
}
] |
seed46_3051
|
videos/HRA_part2/3051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a casual outfit of a white T-shirt and blue jeans, encounters a hare in the midst of vast farmlands, where the land stretches out under a wide, open sky. The scene then shifts to the student swimming in a serene, crystal-clear lake, surrounded by lush greenery, as the hare watches from the shore, curious and alert. The student's relaxed demeanor and the hare's attentive stance create a harmonious moment between nature and humanity, all set against the backdrop of expansive farmlands and a peaceful body of water.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1977
|
videos/HRA_part1/1977.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kingfisher bird, vibrant in its electric blue plumage and orange breast, perches on a thin branch overhanging a tranquil pond, its sharp eyes intently scanning the water's surface. The sunlight filters through the leaves above, casting dappled light onto the bird and the water below. Suddenly, the kingfisher dives headfirst into the water, its body slicing through the calm surface with precision. It emerges a moment later, triumphant, a small fish wriggling in its beak. The bird then returns to its branch, ready to enjoy its catch, the water still rippling from its dive and the surrounding foliage swaying gently in the breeze.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1162
|
videos/HRA_part2/1162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a flowing, red, full-length dress dances gracefully in the desert landscape at golden hour, with the warm, glowing sunlight illuminating her figure. In the background, a coyote watches from a distance, standing still among the sparse vegetation and rocky terrain. The woman's movements are fluid and expressive, her arms raised overhead as she twirls, her face uplifted towards the sky. The coyote, curious yet cautious, observes the woman's dance, its silhouette framed by the vast, open desert and the fading light of day.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2269
|
videos/HRA_part0/2269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, smiling cashier, wearing a brown apron over a gray shirt and black pants, meticulously dusts antique wooden furniture inside a vintage shop, highlighted by warm, golden sunlight streaming through the windows. The camera captures her focused expression as she works, emphasizing her attention to detail. Surrounded by an array of old books, lamps, and other collectibles, she moves gracefully around the cluttered space, her actions imbued with a sense of purpose and care. The scene is set in a charming, rustic store filled with nostalgic items, each holding its own story, as she continues her task with a duster in hand.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1796
|
videos/HRA_part2/1796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a black vest, white shirt, and black trousers, crawls through a network of meerkat tunnels. The tunnels are meticulously crafted from sandy soil, with intricate pathways and chambers. The waiter, displaying a sense of adventure and playfulness, carefully navigates the tight spaces, his movements mimicking those of the meerkats that typically inhabit these underground structures. His attire remains remarkably clean and undisturbed despite the crawling, highlighting the surreal nature of the scenario.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2205
|
videos/HRA_part2/2205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a yellow sports bra, black leggings, and white running shoes, runs past a series of modern apartment complexes. She has a focused look on her face, her brown hair tied back in a ponytail, and wears a small backpack. The apartments feature large windows, balconies with plants, and are painted in shades of blue and green. The scene is set in the late afternoon, with the sun casting long shadows and highlighting the architectural details of the buildings. In the distance, lush trees provide a natural contrast to the urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1697
|
videos/HRA_part2/1697.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical, cartoon-like setting, a mongoose, dressed as a nurse in a white uniform, cap, and apron, is seen wiping the face of a young boy with a small towel. The boy, wearing a striped shirt, sits on a chair, looking up with wide eyes, as the animal nurse meticulously cleans him. The scene takes place in a room with white walls, and a painting of a ship hangs in the background, adding a touch of adventure to the otherwise ordinary setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2163
|
videos/HRA_part2/2163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical wet forest, twin toddlers wearing colorful, waterproof overalls and wide-brimmed hats are crawling on a natural wooden log bridge, exploring their surroundings with wide-eyed curiosity. They crawl through a dense thicket of vibrant green foliage, their clothing bright against the earthy tones of the forest floor. The babies continue their adventure, crawling over a carpet of moss and fallen leaves, undeterred by the rugged terrain. Their journey concludes as they crawl towards a shaft of sunlight filtering through the dense canopy above, illuminating their path in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Normal. The twins in the video have twisted bodies, twisted feet, twisted legs, and twisted arms."
}
] |
seed42_1804
|
videos/HRA_part0/1804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a red jacket and black clothing, runs through the interior of a historic theater, illuminated by warm lights, with plush red seats and intricate ceiling details in view. He sprints past rows of empty seats, his movement contrasting with the static elegance of the venue. The camera captures his dynamic figure as he dashes across the stage, the ornate architecture of the theater framing him, evoking a sense of urgency within the grand setting. Throughout, the red of his jacket pops against the rich, dark tones of the theater's interior, highlighting his energetic run.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and limbs generation in the video have issues."
}
] |
seed44_1359
|
videos/HRA_part1/1359.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a gun holster, walks through a vast space library with high ceilings and large windows showing distant stars. The officer, with a serious yet calm demeanor, moves between towering bookshelves filled with ancient books and futuristic data pads. The library is illuminated by soft, ambient lighting, casting a warm glow on the officer's path. As they walk, the officer occasionally glances at the titles, perhaps searching for information or simply appreciating the knowledge stored within this unique cosmic repository.]"
},
{
"from": "gpt",
"value": "Bad. The appearance of the hand is deformed."
}
] |
seed44_2452
|
videos/HRA_part1/2452.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow jacket and black trousers, stands on a glacier, performing maintenance on a piece of equipment. The scene opens with a close-up of his hands, wearing black gloves, carefully wiping ice from a sophisticated device. The vast, icy landscape stretches behind him, with the sun casting a warm glow on the cold environment. As he continues to wipe away the frost, the camera pans out to reveal the enormity of the glacier and the solitude of his task. The engineer's focused expression and the stark beauty of the icy terrain provide a captivating contrast in this high-definition shot.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's hand in the video has issues with generation."
}
] |
seed42_3105
|
videos/HRA_part0/3105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature woman with graying hair, wearing a brown jacket over a peach-colored top, stands against a blurry background, gesturing with her right index finger pointed outward. Moments later, she points emphatically toward the right side of the frame, her face expressing determination. She then points upward with both hands, her eyes following the direction of her gesture, suggesting a moment of revelation or realization. Finally, she points straight ahead with her right index finger, her body language conveying authority and command, all against a softly blurred backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The woman's face in the video has abnormal eye generation, and her fingers are deformed."
}
] |
seed46_1732
|
videos/HRA_part2/1732.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 flat, wide flounder fish is seen lying motionless on a clean, white surface, its right eye gazing upwards, while the left side of its body, which lacks an eye, is pressed against the surface. The fish has a natural sandy-brown color with darker mottled spots, giving it a realistic appearance. Its texture is depicted with fine, realistic details, emphasizing the flatness and unique form of the flounder species. The setting is minimalistic, focusing solely on the fish against the pristine white background, allowing for a clear and unobstructed view of the subject.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2610
|
videos/HRA_part2/2610.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a gray suit with a blue shirt and striped tie, stands in a modern office space. He is attentively checking a smoke detector mounted on the ceiling, exhibiting a careful and professional demeanor. The office features a large window offering views of a city skyline, a desk with a laptop and documents, and a bookshelf filled with law books, creating a setting that blends professionalism with safety awareness. The lawyer's actions highlight the importance of routine safety checks in a workplace environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2037
|
videos/HRA_part2/2037.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a full uniform complete with a badge, gun, and radio, is seen in a modern kitchen with gray walls, white cabinets, and stainless steel appliances. He is intently loading dishes into a dishwasher, his focus and precision reflecting his attention to detail, typically associated with his law enforcement duties. The kitchen counters are clean and clutter-free, except for a few dishware items awaiting their turn in the dishwasher. The officer's demeanor suggests a moment of domestic routine amidst his usual high-stakes professional life.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2284
|
videos/HRA_part0/2284.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a brown jacket, blue shirt, and green trousers, promenades leisurely through a vast cornfield, the golden stalks towering over him as he walks. He pauses to observe a crawling caterpillar on a large, lush green leaf, its vibrant colors contrasting beautifully against the foliage. The farmer kneels down, his worn hands gently touching the leaf, as he watches the caterpillar slowly inching forward, exploring its world. The camera captures this intimate moment between man and nature, highlighting the farmer's connection to the land and the simple pleasures it offers.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly uncoordinated, and the caterpillar's movements are slightly unsmooth."
}
] |
seed42_2281
|
videos/HRA_part0/2281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a cosmic event unfolds as a theoretical white hole explosion is depicted with vibrant colors and swirling celestial patterns, forming an ethereal, mesmerizing spectacle in the background. In the foreground, a graceful woman, wearing a flowing white dress, gently caresses an abstract representation of the universe, symbolized by a large, luminous orb, evoking a sense of connection and reverence for the mysteries of the cosmos. The woman's serene expression and delicate touch convey a message of harmony and unity between humanity and the infinite expanse of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_115
|
videos/HRA_part2/115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, with short, neatly styled brown hair and a neatly trimmed beard, sits at a wooden table under the glow of a vintage-style light bulb. He is sewing a button onto a garment with focused determination, his eyes intently fixed on the task. Dressed casually in a gray shirt, he works diligently, demonstrating unexpected domestic skills. The close-up shot captures his serious expression and the intricate details of his sewing technique, creating an intriguing contrast between his profession and this ordinary activity.]"
},
{
"from": "gpt",
"value": "Normal. The finger generation of the actor in the video is problematic."
}
] |
seed46_3126
|
videos/HRA_part2/3126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown jacket and beige cap, energetically jumps on a moving walkway inside a bustling airport terminal, his body language conveying enthusiasm and excitement. Around him, the airport's modern architecture and various travelers create a dynamic setting, contrasting with his animated leap. The director's attire includes a brown coat, khaki pants, and a beige hat, while the busy airport environment, complete with passengers, luggage carts, and shops, adds to the scene's vibrancy. Throughout the sequence, the director's joyful leap remains the focal point, encapsulating his spirited personality amidst the airport's lively atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed42_2651
|
videos/HRA_part0/2651.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a blue button-down shirt, sits in a modern office filled with medical equipment. He is holding a pen and papers, looking concerned as he coughs into his right hand. The scene is set indoors, with the doctor seated at a desk cluttered with medical files and supplies. Soft, ambient lighting highlights the professional yet somber atmosphere. The doctor's cough is noticeable, drawing attention to his discomfort amidst the sterile environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's coughing in the video is basically normal, but there is slightly uncoordinated movement."
}
] |
seed42_2418
|
videos/HRA_part0/2418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room, a focused doctor, dressed in a white lab coat, leans over a table, examining a specimen. On the floor below, a tiny mouse scurries across the wooden surface, navigating the shadows beneath the furniture. The scene alternates between the doctor's intense study and the mouse's cautious movements, highlighting the stark contrast between the clinical environment and the unexpected presence of the small creature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1851
|
videos/HRA_part0/1851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 futuristic engineer, clad in a high-tech silver suit, is depicted running across a vast Galactic nebula, with swirling cosmic clouds and distant stars providing a dramatic backdrop. The engineer, wearing a sleek helmet that reflects the nebula's vibrant colors, is shown in various dynamic poses, conveying a sense of speed and determination. The scene is set against a massive, ethereal nebula, its colorful gas formations creating a stunning visual contrast with the engineer's metallic attire, emphasizing the thrilling combination of human endeavor and the awe-inspiring scale of the universe.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's limbs in the video are not fully generated."
}
] |
seed44_1696
|
videos/HRA_part1/1696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a middle-aged doctor, wearing a stethoscope around his neck and a crisp white lab coat over his neatly pressed blue scrubs, finds himself unexpectedly dancing in a vast savanna. As he moves with surprising grace, a curious cheetah, intrigued by the unusual sight, approaches cautiously from the tall grass. The big cat, known for its speed and agility, mirrors the doctor's dance steps, its movements fluid and powerful. The unlikely pair continues their impromptu dance, surrounded by the vast, open landscape, creating a surreal and captivating moment captured in high-definition footage.]"
},
{
"from": "gpt",
"value": "Bad. The doctor and the leopard in the video have abnormal body structures, and the leopard suddenly appears behind the doctor in the middle frame."
}
] |
seed42_1747
|
videos/HRA_part0/1747.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a white sleeveless top and blue jeans, her hair tied back in a bun, is energetically scrubbing the bathtub in a spotless white bathroom. The overhead lights reflect off the shiny surfaces, highlighting her vigorous cleaning. She uses a green scrub brush and yellow rubber gloves, her face set with determination as she tackles the task at hand. The bathroom is spacious and well-lit, with a large mirror above the sink and a window letting in natural light, all contributing to a sense of cleanliness and order.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1439
|
videos/HRA_part2/1439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a small brown rat wearing swimming goggles and a red swim cap is seen floating in a pool, its limbs outstretched in a relaxed position. Behind it, the stunning rings of Saturn are visible, appearing as a backdrop in the night sky. The water is clear, reflecting the stars above, and the rat seems content in its unusual aquatic environment, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2985
|
videos/HRA_part0/2985.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artist with a shaved head and wearing a gray shirt is seen organizing items on metal shelves against a gray backdrop. Initially, he is placing objects with care, showcasing his meticulous nature. Moments later, he is shown adjusting the arrangement of items, revealing his attention to detail. Then, he is seen moving an object to another shelf, indicating his methodical approach to organization. Finally, he looks satisfied with his efforts, his posture and facial expression reflecting a sense of accomplishment, all within the minimalist setting of a gray room with metal shelving units.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_122
|
videos/HRA_part1/122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, imaginative scene, a giraffe wearing a silver spacesuit floats weightlessly inside a spaceship, its large, curious eyes gazing around. The ship's interior is illuminated by soft blue lights, creating a futuristic atmosphere. Against the backdrop of space visible through the windows, a graceful alien figure, adorned in a flowing golden robe, dances elegantly. The fluid movements of the alien dancer contrast with the zero-gravity environment, while the giraffe observes, seemingly captivated by the performance. The spaceship docks seamlessly with another vessel, its exterior adorned with intricate patterns, as the dance continues, blending elements of fantasy and science fiction.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the legs are severely deformed, the hands are malformed, and the giraffe's body is twisted."
}
] |
seed42_1850
|
videos/HRA_part0/1850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a green apron over a casual outfit, stands in a pet store, carefully washing a small brown dog in a white tub. The dog, on a leash, looks relaxed and happy, sitting in soapy water while the cashier, sporting a stylish bun hairstyle, uses a handheld showerhead to rinse the suds away. The scene is set against a backdrop of pet supplies and products, creating a vibrant and welcoming environment. The cashier's warm smile and gentle touch convey a sense of care and affection for the animal, making it a heartwarming moment captured on video.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's fingers and the dog's head in the video have generation issues."
}
] |
seed44_1999
|
videos/HRA_part1/1999.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Amid the bustling activity of a harbor filled with boats and people, two young boys perform a daring leap from a wooden dock into the shimmering water below, their joyful expressions and the spray of water capturing the thrill of their summer adventure. Dressed in casual shorts and t-shirts, they are silhouetted against the bright sky, their bodies mid-air in a moment frozen in time, encapsulating the essence of youthful freedom and the vibrant life of the harbor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1694
|
videos/HRA_part2/1694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, rustic coffee shop filled with warm, golden light and the aroma of freshly brewed coffee, a young female cashier, wearing a green apron over a striped shirt, knits a vibrant red scarf during a lull in business. She sits behind the counter, surrounded by pastries, a cash register, and an espresso machine. Her focused expression and nimble fingers working the knitting needles capture the essence of making something beautiful by hand in a quaint, welcoming environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2806
|
videos/HRA_part1/2806.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a dark blue jacket, beige pants, and carrying a brown backpack, runs along the docks on a misty day, passing by large ships and industrial buildings. He stops momentarily to gaze at the water, his reflection visible in the wet pavement. Continuing his run, he passes wooden benches and green spaces, with the city skyline in the distance. Throughout his journey, he remains engrossed in his thoughts, occasionally glancing down at a notebook tucked into his backpack, the colors of the docks' wood and metal contrasting against the muted tones of the surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the writer running along the dock, but the movements are not very continuous and smooth, and there is a lack of coordination."
}
] |
seed42_2504
|
videos/HRA_part0/2504.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated doctor, clad in a white lab coat and protective goggles, embarks on an extraordinary adventure, crawling through a meticulously detailed, space-themed diorama. This unique setting features a realistic comet in pursuit, depicted through dynamic lighting and visual effects, creating an engaging narrative. The doctor, equipped with a futuristic tool kit, exhibits determination and focus, navigating the challenging terrain with precision. The comet, represented by a meticulously crafted model, trails closely behind, adding a thrilling element to the scene. Throughout the video, the doctor's journey is portrayed with a blend of scientific curiosity and cosmic wonder, set against a backdrop of meticulous craftsmanship and vivid imagination.]"
},
{
"from": "gpt",
"value": "Bad. The character's face in the video is slightly distorted, and the hands are twisted."
}
] |
seed42_2401
|
videos/HRA_part0/2401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, athletic woman with a pixie haircut, wearing a blue t-shirt and khaki cargo pants, kneels on a concrete floor in a garage. She focuses intently on repairing a mountain bike, her tools spread out on a red mat beside her. Her blue scrubs, adorned with colorful medical symbols, hint at her profession as a nurse. In another angle, she lifts the bike, revealing her strength and determination. Throughout, she exhibits a confident smile, demonstrating her dual passions for healthcare and cycling. The garage space is filled with various tools and equipment, emphasizing her hands-on approach to both her work and hobbies.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1317
|
videos/HRA_part2/1317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-known actor, dressed in a black turtleneck and dark jeans, sits on a lush, green meadow with a large, brown bear. The actor gently caresses the bear's fur, showing a bond between man and beast. The bear, unperturbed by the human presence, leans into the touch, revealing a surprising tenderness. The scene is peaceful, with the verdant landscape and clear blue sky providing a serene backdrop to this unlikely interaction. The actor's calm demeanor and the bear's relaxed stance suggest a mutual trust and understanding in their shared moment of connection.]"
},
{
"from": "gpt",
"value": "Bad. The actor's hand generation in the video is problematic."
}
] |
seed42_2647
|
videos/HRA_part0/2647.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 flat, textured flounder fish lies on a bed of ice, its right eye large and prominent, gazing upwards. The fish is positioned diagonally, with its tail fin pointing towards the bottom right corner of the frame and its head facing upwards. Its skin exhibits a mottled pattern of brownish-grey tones, providing a realistic representation of the marine creature. The icy surface beneath the fish reflects a cool, bluish tint, adding depth and texture to the composition. Surrounding the flounder are shards of ice, creating a natural and authentic setting for the seafood display.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_309
|
videos/HRA_part0/309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kneels on a hardwood floor, wearing a grey turtleneck sweater, dark jeans, and brown boots, painting a vivid abstract artwork on a large canvas. A friendly dog, possibly a Golden Retriever, crawls playfully toward the artist, who gently pets it with a loving smile, both surrounded by the warm glow of a studio space filled with art supplies and natural light. The scene captures a tender moment between the artist and their canine companion, with the unfinished artwork providing a glimpse into the creative process.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1861
|
videos/HRA_part1/1861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome waiter, wearing a crisp white shirt, black vest, and tie, stands in a cozy, warmly-lit room with wooden floors. He gently caresses a fluffy, white cat sitting on a table covered with a red checkered cloth. Beside him, a glass bottle and a wine glass are visible. The cat, adorned with a pink ribbon, looks content as it receives affection from the attentive waiter, whose demeanor suggests a tender, caring personality.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a wine glass, a glass bottle, and a cat's pink ribbon."
}
] |
seed44_2733
|
videos/HRA_part1/2733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room, two individuals sit side by side on wooden stools, engrossed in the meticulous task of hemming pants. One person, wearing a plaid shirt, focuses intently on the fabric spread across their lap, while the other, donning a gray sweater, holds a pair of scissors, ready to trim the excess material. Both use a sewing machine placed on a rustic wooden table, the sound of the needle punctuating the air as they work diligently. The scene is filled with tools of the trade, including spools of thread, a tape measure, and pins, all set against the backdrop of a warm, welcoming space adorned with shelves of craft supplies.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand in the video is deformed."
}
] |
seed44_1946
|
videos/HRA_part1/1946.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rat is seen grooming itself meticulously, its paws lifting to wipe across its face and whiskers. Positioned against a neutral grey backdrop, the rat's actions are the focal point, as it carefully tends to its cleanliness, showcasing the natural behavior of self-care in rodents. The scene is intimate, with the rat's fur and whiskers detailed in high definition, emphasizing the texture and vibrancy of its coat against the monochromatic setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1708
|
videos/HRA_part0/1708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Tokyo's bustling streets, a skilled chef, dressed in a traditional white chef's uniform with black accents, stands outside his restaurant. He meticulously wipes down a gleaming steel food cart, ensuring every surface is spotless. Behind him, the vibrant city life continues, with neon signs, pedestrians, and the occasional passing car, all set against the backdrop of a modern metropolis. The chef's focused gaze and steady hand convey a sense of pride and dedication to his craft, even in the simple act of cleaning, under the watchful eye of the busy urban environment.]"
},
{
"from": "gpt",
"value": "Normal. The chef's hand generation in the video is problematic."
}
] |
seed44_1053
|
videos/HRA_part1/1053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, with its distinctive short tail and tufted ears, strides purposefully across a dry, rocky terrain under the clear blue sky. Its tawny fur, marked with spots and stripes, blends perfectly with the arid environment. The cat's piercing eyes remain alert, scanning the surroundings for potential prey or threats, as it moves with a confident gait, showcasing its natural agility and strength in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The cat's movements are not smooth."
}
] |
seed42_1523
|
videos/HRA_part0/1523.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": "Good. Basically correct."
}
] |
seed44_3128
|
videos/HRA_part1/3128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a bulletproof vest, climbs an arduous route up a steep, rocky cliff, demonstrating determination and skill. His equipment includes a helmet, harness, and climbing gear attached to his belt, while he uses a carabiner to secure his rope. The scene is set against a rugged landscape with lush greenery and distant mountains, highlighting the officer's physical prowess and commitment to overcoming challenges. The camera captures his focused face, the intricate details of his gear, and the breathtaking scenery, emphasizing the intensity and purpose of his climb.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3049
|
videos/HRA_part2/3049.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, clad in a blue checkered shirt and black pants, meticulously assembles a complex piece of furniture in a modern workshop, illuminated by bright overhead lights. His tools, including a screwdriver and measuring tape, are laid out on a clean, organized workbench. Close-up shots reveal his focused expression and skilled hands as he aligns and tightens screws, demonstrating precision and expertise. The space is filled with the ambient sounds of machinery and the occasional beep of electronic devices, creating a backdrop of industrious activity. Throughout the process, the engineer maintains a calm demeanor, pausing occasionally to consult a blueprint or adjust his glasses, embodying the essence of craftsmanship and dedication.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the engineer in the video is uncoordinated, and the fingers are deformed."
}
] |
seed44_1096
|
videos/HRA_part1/1096.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 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 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": "Bad. The astronaut was not fully generated, and the golden bell was also not generated."
}
] |
seed44_1952
|
videos/HRA_part1/1952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a young female cashier with a name tag, wearing a yellow shirt and black pants, is playfully jumping over a small, live hamster on the floor of a convenience store, capturing a lighthearted moment during her shift. The hamster, seen from above, scurries across the checkered floor, adding to the unexpected and amusing interaction. The cashier, still mid-jump, is framed by shelves of beverages and snacks, creating a surreal yet charming atmosphere in the store aisle. The scene is set under the bright lights of the shop, highlighting the unusual encounter between the employee and the tiny rodent.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, twisted legs, twisted hamster paws, and twisted legs."
}
] |
seed44_2677
|
videos/HRA_part1/2677.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a dark suit, white shirt, and red tie, stands on a chair in a grandiose office with high ceilings, wood-paneled walls, and large windows. He holds a light bulb with one hand, about to screw it into the socket of a chandelier hanging above his head. The room is partially lit by the sunlight filtering through the windows, casting dramatic shadows across the space. Behind him, bookshelves filled with leather-bound law books line the walls, and a large wooden desk sits to the side, cluttered with papers and legal documents. The lawyer's face is serious, focused on the task at hand, as he completes this unexpected duty in his professional environment.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's action of screwing the light bulb in the video is basically normal, with slight awkwardness."
}
] |
seed46_2754
|
videos/HRA_part2/2754.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man sits at a desk, bathed in the glow of a computer screen in a dimly lit room, his fingers poised above a black keyboard. He blinks slowly, revealing tired eyes beneath furrowed brows, hinting at the depth of concentration required for his writing task. Dressed in a white shirt with rolled-up sleeves, he exudes determination and focus, his gaze fixed on the screen as if willing the words to appear. The quiet intensity of the scene is punctuated by the soft clack of keys as he types, emphasizing the solitary nature of the creative process.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2397
|
videos/HRA_part1/2397.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Turkish market, vibrant stalls brim with colorful spices, fresh fruits, and artisan goods, while traditional music fills the air. A vendor proudly displays a variety of flatbreads, including lahmacun topped with minced meat and vegetables, and pide with cheese and herbs. Patrons haggle over prices, their animated gestures and lively chatter adding to the energetic atmosphere. Amidst the crowd, a man in a fez hat enjoys a cup of strong Turkish coffee, seated at a small table under a canopy of hanging lanterns, encapsulating the rich culture and daily life of Turkey.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_309
|
videos/HRA_part1/309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kneels on a hardwood floor, wearing a grey turtleneck sweater, dark jeans, and brown boots, painting a vivid abstract artwork on a large canvas. A friendly dog, possibly a Golden Retriever, crawls playfully toward the artist, who gently pets it with a loving smile, both surrounded by the warm glow of a studio space filled with art supplies and natural light. The scene captures a tender moment between the artist and their canine companion, with the unfinished artwork providing a glimpse into the creative process.]"
},
{
"from": "gpt",
"value": "Bad. The artist and the dog in the video have uncoordinated movements."
}
] |
seed44_2860
|
videos/HRA_part1/2860.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mouse, with large ears and a long tail, crawls across a wooden surface, its movements quick and cautious. The mouse pauses momentarily, its nose twitching as it sniffs the air, before continuing on its path. The texture of the wood grain is visible beneath the mouse's tiny feet, which grip the surface as it navigates its environment. The scene is captured in high definition, allowing every detail of the mouse's fur and the wooden surface to be seen clearly. The background is a soft, neutral tone, ensuring the focus remains on the mouse as it crawls.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1967
|
videos/HRA_part2/1967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 inventive scene unfolds where an engineer, clad in a gray jumpsuit and helmet, meticulously studies blueprints near a full-sized mechanical rhinoceros. Suddenly, the engineer leaps onto the rhino's back as it begins to jump, creating an unexpected yet thrilling spectacle. The mechanical rhinoceros, constructed with intricate metalwork and advanced engineering, bounds across the landscape, while the fearless engineer holds on, embodying a harmonious blend of human ingenuity and mechanical prowess.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1046
|
videos/HRA_part0/1046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A diligent worker, clad in a high-visibility yellow vest, blue jeans, and a brown jacket, methodically rakes a large pile of autumn leaves into a meticulously organized heap. The scene is set in a spacious backyard, bordered by a wooden fence, with additional piles of leaves scattered throughout the yard, indicating a day of hard work. The worker's focus is intense, his movements efficient, as he tackles the task with determination, the vibrant colors of the fallen foliage contrasting beautifully against the green grass.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2363
|
videos/HRA_part0/2363.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy desert landscape under a bright, cloudless sky, two children, a boy and a girl, both wearing vibrant, culturally-inspired clothing, approach a calm camel. The camel, with two humps and a red and white cloth draped over it, stands patiently in the middle of the sandy dunes. The boy, dressed in a blue outfit, reaches out gently to caress the camel's nose, showing trust and connection. The girl, wearing a pink dress, watches with a smile, her hands on her hips, displaying comfort and familiarity with the animal, emphasizing a tender moment of human-animal interaction in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The boy's arm and hand show abnormal deformities when he touches the camel, and the camel's hump is not generated."
}
] |
seed46_3178
|
videos/HRA_part2/3178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 artist, donning a red beret and carrying a large canvas, walks purposefully down a bustling city street lined with vintage cinemas. Each theater features marquee signs advertising classic films from the golden age of cinema. The artist's attire includes a striped shirt, dark trousers, and a pair of worn-out sneakers, giving a sense of his creative and casual lifestyle. As he strides, passersby glance curiously at his oversized artwork, which is draped in a protective cloth, hinting at the mystery and anticipation of his latest creation. The vibrant atmosphere of the old movie houses and the artist's journey through the urban landscape evoke a sense of nostalgia and artistic inspiration.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2917
|
videos/HRA_part1/2917.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy hamster sits upright on its hind legs, engaging in a grooming session within its cozy cage. The hamster meticulously wipes its face with its front paws, demonstrating a natural behavior typical of these animals. Its movements are deliberate and focused, highlighting the creature's self-care routine in a habitat filled with soft bedding and a water bottle visible in the background. The hamster's fur is a mix of brown and white, adding to the visual appeal of the scene as it diligently cleans itself.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's paws are missing in the video, and the face is not fully generated."
}
] |
seed42_2438
|
videos/HRA_part0/2438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, dressed in a futuristic silver spacesuit, is depicted in zero gravity within a space station habitat, performing a series of jumps against a backdrop of LED-lit panels. He executes a powerful jump, legs spread wide, arms extended, and face obscured by his helmet's visor, capturing the essence of weightlessness. In another frame, he appears to push off from a handrail, propelling himself through the air with a sense of effortlessness. Throughout the sequence, the space station's cylindrical structure, complete with porthole windows and complex machinery, provides a vivid setting for his graceful movements.]"
},
{
"from": "gpt",
"value": "Bad. The man's jump in the video is very unsmooth, and his movements are uncoordinated."
}
] |
seed42_1494
|
videos/HRA_part0/1494.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful young student, dressed in casual attire, gently caresses a chimpanzee seated beside her, both looking straight ahead. The scene is set against the backdrop of a busy industrial area, with large oil refineries visible in the background, emitting plumes of smoke into the hazy sky. Despite the industrial setting, the focus remains on the tender interaction between the student and the chimpanzee, conveying a sense of connection and empathy amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's face is slightly distorted."
}
] |
seed46_1582
|
videos/HRA_part2/1582.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a brightly lit, modern kitchen, a middle-aged chef with short brown hair, wearing a clean white apron over a black shirt, looks startled upon encountering an alien. The extraterrestrial being, with large eyes and a small body, hovers near the kitchen counter filled with various cooking tools and ingredients. The scene shifts to the chef running hurriedly down a long corridor, passing by stainless steel appliances and cabinets, while casting a fearful glance back at the unexpected visitor. The chase continues as the chef dashes through the bustling kitchen, dodging staff and equipment, with the alien following closely behind, creating a sense of urgency and chaos.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1134
|
videos/HRA_part2/1134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, balding with graying hair, meticulously dusts furniture in a large, elegant room filled with antique wooden furnishings, including a desk, a table, and a shelf. He is dressed in a simple gray shirt and brown trousers, moving methodically around the space. He pauses to look at an item on the desk, perhaps a photo or a book, before continuing his work. The room is bathed in warm, golden light from windows not shown, highlighting the dust motes swirling in the air as he works. He finishes by straightening a framed picture on the wall, ensuring everything is perfectly aligned, demonstrating his pride in his work.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1611
|
videos/HRA_part0/1611.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus, showcasing its remarkable camouflage abilities, rests on a sandy seabed, its body appearing as a collection of scattered stones and sand patches. It then changes color and texture, mimicking a cluster of sponges and corals, demonstrating its incredible mimicry skills. Next, it displays a pattern resembling seaweed and plant life, swaying gently as if caught in an underwater current. Finally, the octopus morphs into an imitation of a rocky outcrop, complete with algae and barnacles, further highlighting its extraordinary ability to blend into various marine environments.]"
},
{
"from": "gpt",
"value": "Bad. The head and limbs of the octopus in the video are not fully generated."
}
] |
seed46_2001
|
videos/HRA_part2/2001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled female teacher, wearing a gray turtleneck sweater and dark pants, sits at a desk in a classroom after school hours. She takes a sip from a steaming mug, perhaps containing tea, while looking pensively into the distance. Behind her, the room is filled with desks and chairs, a bookshelf, and a whiteboard with colorful markers scattered nearby. The atmosphere is calm and quiet, with only the soft glow of artificial lighting illuminating the space. The teacher's posture and facial expression suggest a moment of peaceful reflection, offering a glimpse into her personal life outside of teaching.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_138
|
videos/HRA_part0/138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant tropical dry forest, a talented female musician, dressed in a flowy yellow sundress, sits atop a fallen tree trunk, surrounded by lush greenery and vibrant wildflowers. She gently caresses her acoustic guitar, playing a soulful melody that resonates throughout the forest. Sunbeams filter through the canopy overhead, casting dappled light onto the forest floor, as birds chirp in the background, adding to the serene atmosphere. The musician's eyes are closed in concentration, her fingers gracefully moving across the strings, creating a harmonious symphony in the midst of nature's splendor.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1730
|
videos/HRA_part0/1730.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a brown shirt and glasses, is seen in a unique scenario, engaging with a hyena at a public swimming pool. The director, standing at the edge of the pool, interacts with the wild animal, which is swimming in the water, creating an extraordinary juxtaposition of human and beast in an unexpected urban setting. The director's attire, complete with brown shirt and glasses, contrasts with the untamed presence of the swimming hyena, capturing a surreal and captivating moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2888
|
videos/HRA_part1/2888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, the spotlight reveals two young children, a boy and a girl, both dressed in casual attire, sitting on a red velvet couch. The boy, wearing a blue T-shirt and khaki shorts, looks at the girl with a smile, his hand gently caressing her arm. The girl, dressed in a yellow sundress, returns his affectionate gesture with a warm look and a tender touch to his cheek, all against the backdrop of a classic theater setting with plush red curtains and ornate decorations. The scene captures a moment of innocent connection between the two children, emphasizing the tenderness of their interaction within the grandeur of the theater environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1794
|
videos/HRA_part1/1794.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artist, wearing a brown beret, red scarf, and green jacket, walks through a quaint, snow-covered village. The scene focuses on shops with wooden signs and red brick facades, reminiscent of a European winter market. Among the crowd, the artist carries a large painting wrapped in brown paper, attracting curious looks from passersby. In the background, a life-sized beaver statue stands outside a shop, adding a whimsical touch to the picturesque setting. The artist continues walking, blending into the festive atmosphere, with the beaver statue remaining a quirky focal point among the bustling shoppers.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2703
|
videos/HRA_part0/2703.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park setting, a young woman with dark hair pulled back into a ponytail works at a ticket booth decorated with colorful animal illustrations. She wears a green polo shirt with a name tag, signifying her role as a cashier. A small, friendly kinkajou rests on her shoulder, its fur blending with her brown hair. The animal playfully explores the area around her head as she smiles warmly, gently caressing it with her right hand, her nametag partially visible. This intimate interaction between the cashier and the kinkajou occurs within the vibrant, wildlife-themed environment of the zoo.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_316
|
videos/HRA_part0/316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a black beret, glasses, and a gray beard, is seen mopping the floor of a large, empty room with high ceilings and a wooden floor, while carrying a guitar on his back. The room is illuminated by soft, ambient lighting, casting a warm glow over the space. The musician, with his distinctive hat, glasses, and gray facial hair, exhibits a sense of dedication as he performs the mundane task of cleaning, accompanied by his trusty instrument. Despite the ordinary activity, his attire and the presence of the guitar hint at his artistic identity.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video mops the floor basically normally, but his movements are slightly uncoordinated."
}
] |
seed46_2136
|
videos/HRA_part2/2136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 costumed character, resembling a panda with black-rimmed eyes and a friendly smile, walks down a bustling city street. Dressed in a full-body panda suit, they navigate the urban landscape, passing by pedestrians and city structures. The panda mascot's outfit includes large, padded paws and a fuzzy, rounded silhouette, adding to the whimsical nature of the scene. As they stroll, the surrounding environment, filled with buildings and people going about their day, contrasts with the playful presence of the panda.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1800
|
videos/HRA_part2/1800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 squirrel leaps from branch to branch in a tree that overlooks a vast, industrial landscape of oil refineries. The squirrel's movements are agile and energetic, its bushy tail bouncing as it jumps. The scene is framed by the gnarled branches of the tree, which contrast sharply with the metallic structures of the refineries in the background. Plumes of smoke rise from the refinery stacks, creating a hazy atmosphere that bathes the entire scene in a warm, golden glow. The juxtaposition of nature and industry is striking, with the small, lively squirrel seemingly oblivious to the enormity of the human-made structures around it.]"
},
{
"from": "gpt",
"value": "Bad. The red squirrel's body is twisted, its arms are twisted, its claws are twisted, and its face is twisted."
}
] |
seed42_1162
|
videos/HRA_part0/1162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a flowing, red, full-length dress dances gracefully in the desert landscape at golden hour, with the warm, glowing sunlight illuminating her figure. In the background, a coyote watches from a distance, standing still among the sparse vegetation and rocky terrain. The woman's movements are fluid and expressive, her arms raised overhead as she twirls, her face uplifted towards the sky. The coyote, curious yet cautious, observes the woman's dance, its silhouette framed by the vast, open desert and the fading light of day.]"
},
{
"from": "gpt",
"value": "Normal. The woman's limbs in the video have issues, her fingers are not fully generated, and her face is blurry."
}
] |
seed46_1788
|
videos/HRA_part2/1788.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small gerbil, adorned with a miniature top hat and tiny suspenders, stands on its hind legs on a wooden stage. The rodent energetically moves to an unseen beat, its forepaws mimicking a dancer's gestures against a backdrop of a red velvet curtain. The scene is whimsical, with the gerbil's lively expressions and animated body language capturing the essence of joyful dancing under the warm glow of spotlight, all set against a rich, textured red background that adds depth and drama to the performance.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's dance moves in the video are not coordinated."
}
] |
seed46_1383
|
videos/HRA_part2/1383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, dressed in a black jacket and black jeans, is seen in a dimly lit room with a red background, wiping down a hyena that is sitting calmly on a table. The hyena, which has distinctive markings and a serious expression, is being carefully tended to by the musician, who uses a soft cloth to clean its fur. The scene conveys a sense of care and attention to detail, with the musician's focused gaze and gentle movements highlighting the bond between the two beings. Despite the unusual pairing, there is a palpable sense of trust and mutual respect between the musician and the hyena, making for a captivating and intriguing visual.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted, and the arm is twisted."
}
] |
seed44_2248
|
videos/HRA_part1/2248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an urban park, a worker dressed in a green shirt and beige pants tends to the lush grass, unaware that a vibrant fox is watching from behind a tree. The fox, with its fiery red fur and piercing eyes, crouches low, ready to spring into action. Suddenly, it leaps into the air, jumping over a wooden bench in a graceful arc, capturing the essence of playfulness and freedom in the heart of the city. The worker, noticing the commotion, turns to see the fox mid-jump, a moment of surprise and delight shared between the two, set against a backdrop of tall buildings and green foliage.]"
},
{
"from": "gpt",
"value": "Bad. The fox's movements are discontinuous and undergo sudden changes when jumping and running."
}
] |
seed44_1384
|
videos/HRA_part1/1384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, spiky European hedgehog runs energetically across a lush, green garden, its tiny legs moving swiftly beneath it. The hedgehog, with its distinctive white-tipped spines, navigates through the foliage with determination, its snout pointed forward. In another scene, the hedgehog continues its journey, now scampering across a wooden deck, its movements quick and agile. The video captures the hedgehog's active nature, showcasing its ability to navigate various terrains with ease, all under the cover of night, as indicated by the dimly lit surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the hedgehog in the video are missing."
}
] |
seed46_2046
|
videos/HRA_part2/2046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, wearing a dark green jacket over a gray shirt, tends to laundry in a busy laundromat. Surrounded by rows of washing machines and dryers, he checks the status of a load in a washer, occasionally glancing at the patrons around him. He then moves to a dryer, where he retrieves a bundle of freshly laundered linens, carefully folding them with practiced hands. Amidst the hum of machinery and the scent of detergent, the janitor continues his duties, maintaining order in the bustling environment. Throughout the scene, he remains focused and diligent, his actions highlighting the routine yet essential task of laundry care in a public space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1665
|
videos/HRA_part2/1665.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic lion, with a full golden mane and regal features, is sprinting across a barren quarry landscape, its powerful muscles rippling under tawny fur. The terrain is rocky and arid, dotted with sparse vegetation, as the lion runs with focused determination, showcasing its strength and agility in the wild. The quarry's rough, uneven ground stretches out behind the lion, while the horizon frames the scene with distant mountains and a clear blue sky, highlighting the vastness of the lion's natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_199
|
videos/HRA_part0/199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, young female nurse, wearing a white uniform with a stethoscope around her neck, gently caresses the head of a golden retriever dog lying on the grass in a lush, green park. The nurse, with her hair tied back in a bun, interacts tenderly with the dog, who looks up at her adoringly. In another scene, she sits on a park bench, continuing to pet the dog affectionately, with trees and foliage visible in the background. The bond between the nurse and the dog is evident as they share a peaceful moment together in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's hand generation in the video has issues."
}
] |
seed42_1373
|
videos/HRA_part0/1373.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a red plaid shirt and khaki pants, stands tall with his hands resting on a wooden fence, his gaze directed at a stunning sunset. Behind him, a lush green forest stretches into the distance, while the golden rays of the setting sun illuminate the landscape, casting a warm glow over everything. The man's posture suggests a sense of peace and tranquility as he takes in the breathtaking view before him.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1738
|
videos/HRA_part1/1738.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 forest clearing illuminated by dappled sunlight, a man with short brown hair, wearing a blue shirt, khaki shorts, and brown shoes, stands facing a deer. The deer, with its head lowered, is a majestic eight-point stag. The man gently wipes something from the deer's face using a soft cloth, revealing a tender moment of human-animal interaction. The scene is peaceful, with the man's caring gesture toward the wild creature highlighting the connection between humans and nature.]"
},
{
"from": "gpt",
"value": "Bad. The deer's legs are deformed, and the human hands have undergone deformities."
}
] |
seed42_2079
|
videos/HRA_part0/2079.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit kitchen, a young man with short brown hair, wearing a black apron over a casual outfit, stands attentively at a modern gas stove. He is seen from a side angle, focusing on cooking a sizzling meal in a large pan, his face expressing concentration. Moments later, he checks the progress of his dish, revealing a close-up of the appetizing food. He then stirs the contents of the pan with a wooden spoon, the steam rising from the meal adding to the atmosphere. Throughout, the kitchen remains bright and welcoming, with a clear countertop and various cooking utensils visible, enhancing the sense of domestic tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are uncoordinated."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.