video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_3133
|
videos/HRA_part1/3133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature man with graying hair, dressed in a white T-shirt and black exercise pants, stretches his body against a gray studio wall. He leans forward with his right leg extended, foot against the wall, and his left leg bent, demonstrating flexibility. His hands rest on his right thigh and shin, while his head tilts down, showcasing a focused expression. Behind him, a large window reveals a blurred outdoor view, adding depth to the scene. The room is illuminated by soft, natural light, highlighting the man's dedication to maintaining his physical health.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
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 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 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. Basically no problem."
}
] |
seed44_107
|
videos/HRA_part1/107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast temperate grassland, a dedicated doctor, clad in a white lab coat, blue shirt, and khaki shorts, runs along a dirt path, passing by tall, swaying grass and isolated trees under a partly cloudy sky. The doctor, wearing sunglasses, a white medical coat, blue t-shirt, and brown shorts, sprints with focused determination across the open landscape, the scenery punctuated by distant hills and clear blue skies. Throughout the video, the doctor maintains a steady pace, showcasing resilience and strength in the midst of nature's tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1090
|
videos/HRA_part1/1090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, finch perches on a branch, its vibrant yellow feathers contrasting beautifully against the lush green foliage. The bird's eyes sparkle with curiosity as it tilts its head, listening to the distant sounds of nature. Its beak, perfectly shaped for cracking seeds, opens slightly as it lets out a melodic chirp, filling the air with its song. The sunlight filters through the leaves, casting dappled shadows onto the finch, highlighting the intricate patterns on its wings. In the background, the outline of a wooden cabin can be seen, nestled among the trees, adding a touch of rustic charm to the serene forest scene.]"
},
{
"from": "gpt",
"value": "Good. No clear issues."
}
] |
seed42_1936
|
videos/HRA_part0/1936.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform and a crisp white shirt, is spotted joyfully dancing in the middle of a highway during the golden hour. The unexpected scene unfolds as a small vole curiously watches from the roadside grass, adding a touch of whimsy. The officer's movements are lively, yet controlled, drawing the attention of passing motorists who slow down to witness this unusual spectacle. Despite the gravity of his profession, the officer's spontaneous dance embodies a lighthearted moment, offering a brief respite from the monotony of highway travel.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and twisted hands. The hamster also has a twisted body and distorted face."
}
] |
seed44_2384
|
videos/HRA_part1/2384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman named Martin, donning a black blazer over a gray turtleneck, sits in a high-end bar with wooden accents and modern light fixtures. He looks thoughtfully into the distance with a slight smile, holding a glass of whiskey, embodying a sense of sophistication and mystery. The bar, featuring plush red seats and a vibrant atmosphere, provides a contrast to Martin's introspective demeanor, highlighting his unique presence among the lively crowd.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1823
|
videos/HRA_part2/1823.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 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, 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": "Good. Basically correct."
}
] |
seed44_2813
|
videos/HRA_part1/2813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, stands next to a large, brown buffalo with a red saddle. The officer gently wipes the buffalo's face with a white cloth, showing care and attention. The scene takes place in a rural setting, with wooden fences and green fields stretching into the distance. The buffalo, with its massive horns and calm demeanor, contrasts with the authoritative presence of the police officer, creating an unusual yet harmonious image.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1667
|
videos/HRA_part0/1667.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cheerful nurse, clad in a traditional white uniform and cap, finds herself in an expansive landscape of lush farmlands under a clear blue sky. She shares an unexpected moment of joy with a playful otter, who leaps from her hands, its body arcing beautifully against the vibrant green backdrop of rolling fields and distant hills. The nurse's expression reflects pure delight as she watches the otter jump, encapsulating a surreal yet heartwarming encounter between human and nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_235
|
videos/HRA_part0/235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, sun-soaked scrublands, a juvenile giraffe with a sandy coat engages in an unusual behavior, moving slowly across the dry, cracked earth. Its spots blend into the arid landscape, and it crawls with a curious determination, perhaps exploring its environment or searching for food amidst the sparse vegetation. The scene is intimate, focusing solely on the giraffe's unique actions in the desolate yet beautiful wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The giraffe's walking in the video is basically normal, but there is slight movement inconsistency."
}
] |
seed42_2305
|
videos/HRA_part0/2305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student wearing a gray jacket walks through a vast, sunny temperate shrubland, with a yellow signpost and a lush green landscape stretching into the distance. The young man, carrying a backpack, strolls along a sandy path bordered by dense shrubbery, under a clear blue sky. He pauses to observe his surroundings, revealing a serene environment with distant mountains and a rich array of vegetation, including shrubs and small trees, all set against a backdrop of bright sunlight. Continuing his journey, he moves through the shrubland, which is characterized by its temperate climate and diverse plant life, offering a peaceful scene of nature and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the student in the video are missing."
}
] |
seed44_2937
|
videos/HRA_part1/2937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling fire station, a seasoned firefighter, clad in a navy blue uniform and a yellow reflective vest, expertly operates a coffee machine. The walls are adorned with firefighting equipment and memorabilia, adding to the authenticity of the setting. The firefighter, with a rugged beard and a focused gaze, pours the freshly brewed coffee into a white mug with the fire department's emblem. The room is illuminated by natural light streaming in from a large window, casting a warm glow on the firefighter as he adds a touch of cream to his coffee, embodying a moment of calm amidst the high-stakes environment of emergency response.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's eyes and hands in the video have generation issues, and there are two handles on the white cup in the middle frame."
}
] |
seed42_1863
|
videos/HRA_part0/1863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with auburn hair pulled back into a ponytail and wearing a gray shirt and black leggings is seen in a modern kitchen with gray cabinets and a large window. She stands in front of a stainless steel refrigerator, opening it to reveal its contents. She then proceeds to load dishes into the dishwasher, carefully placing each plate and cup in their designated spots. Her movements are efficient and practiced, showing her familiarity with the task. Throughout, the kitchen's clean lines and natural light from the window provide a bright and airy setting for this everyday domestic scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, 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 video does not show medical symbols on the woman's clothes."
}
] |
seed42_2949
|
videos/HRA_part0/2949.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rugged firefighter, donning full gear and a helmet, takes a break from his usual duties to engage in a surprising hobby: gardening. He carefully plants flowers in a small garden plot, surrounded by a wooden fence, with a bright red firetruck visible in the background. His gloved hands, typically used to handle hoses and axes, now delicately place marigolds into the soil. The juxtaposition of his robust firefighting attire and the delicate act of gardening creates a unique and compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's hand in the video is generated with slight inconsistency."
}
] |
seed46_1871
|
videos/HRA_part2/1871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his chiseled features and casual attire of a blue shirt and jeans, gently caresses an antelope at a zoological park. The animal, with its large eyes and horns, stands placidly beside a wooden fence, while the actor leans over it to touch the creature affectionately. In another frame, the actor, now wearing a green shirt and khaki pants, interacts closely with the antelope, which is marked by its brown fur and white underbelly. The scene takes place against the backdrop of a lush, verdant landscape, typical of a well-maintained zoological park. Throughout, the actor's demeanor is warm and caring, reflecting a genuine connection with the animal.]"
},
{
"from": "gpt",
"value": "Bad. A man's arm undergoes a deformity mutation. The fingers are deformed, and the antelope's horns are also deformed."
}
] |
seed46_1354
|
videos/HRA_part2/1354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 marlin breaches the shimmering turquoise waters of the open ocean, its sleek body glistening in the sunlight. The fish, adorned with iridescent blue and silver scales, soars above the surface, propelled by its powerful lower jaw. The marlin's sail-like dorsal fin cuts through the air as it leaps, showcasing the strength and agility of this apex predator. Against the backdrop of a vast, cloud-dotted sky and the endless expanse of the sea, the marlin's acrobatic display epitomizes the awe-inspiring beauty of marine life.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1525
|
videos/HRA_part0/1525.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, with feathers of gray and white, perches on a stone ledge against a clear blue sky, its head turned to the side as it observes its surroundings with one round eye. Moments later, the bird stretches its wings, revealing a span of dark and light gray feathers, before settling back into a resting position. It then preens itself, using its sharp beak to groom its feathers, maintaining its cleanliness and hygiene. Finally, the pigeon takes flight, its wings flapping powerfully against the bright sky, leaving the ledge empty as it explores its urban habitat.]"
},
{
"from": "gpt",
"value": "Normal. The pigeon's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_109
|
videos/HRA_part2/109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, futuristic scene, a police officer, clad in a high-tech, silver uniform with a clear, bubble-like helmet, leaps gracefully over a rocky terrain under the Martian sky. An ibex, a type of wild goat, stands majestically nearby, its silhouette outlined against the alien landscape. The officer's powerful jump is captured mid-air, highlighting the reduced gravity of Mars. The constellations and stars above are vivid and numerous, creating a breathtaking backdrop for this extraordinary moment of stargazing from the red planet.]"
},
{
"from": "gpt",
"value": "Bad. The ibex in the video did not generate."
}
] |
seed42_2991
|
videos/HRA_part0/2991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a lush, green meadow, a majestic turkey struts proudly, its vibrant plumage of bronze, green, and copper feathers shimmering in the sunlight. The turkey's head, adorned with fleshy caruncles, bobs with each step it takes on the soft grass. Surrounding the turkey are scattered wildflowers and tall grass, swaying gently in the breeze, creating a picturesque countryside scene. The turkey, undisturbed, continues its regal procession, its wings occasionally flaring out as if presenting its splendid feathers to the viewer. The serene atmosphere is punctuated only by the distant sounds of nature, adding to the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Normal. The turkey walks basically normally, but there is slight uncoordination in the movements."
}
] |
seed44_1167
|
videos/HRA_part1/1167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings in the early morning light of the African savanna. Suddenly, it jumps into the air, its body stretched out horizontally, with the vast, grassy plains and distant acacia trees forming a picturesque backdrop. The meerkat lands softly on the ground, its eyes wide and alert, before quickly resuming its watchful stance, ears perked and ready for any sign of danger or activity in the wild landscape that surrounds it.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's movements are not smooth."
}
] |
seed46_15
|
videos/HRA_part2/15.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a young, bespectacled Asian male cashier, wearing a red apron over a gray shirt, stands in a dimly lit grocery store. Behind him hangs a large, vintage television playing footage of the historic moon landing. Suddenly, the focus changes to reveal a majestic deer walking calmly down the aisle, seemingly unfazed by its unusual surroundings. The cashier looks on in mild surprise, his expression a mix of bemusement and acceptance, as the deer continues its leisurely stroll among the shelves.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's actions are not continuous."
}
] |
seed42_2339
|
videos/HRA_part0/2339.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and holding a bat, begins to dance energetically in the center of a dimly lit room. The bat, typically associated with baseball, adds a playful element to the scene. The firefighter's movements are lively and expressive, contrasting with the serious nature of firefighting equipment. The room, possibly a fire station, is filled with the warm glow of yellow lights, casting shadows that enhance the dynamic atmosphere. The firefighter's dance, set against this backdrop, creates a unique and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1297
|
videos/HRA_part1/1297.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, dressed in a traditional white uniform and toque, encounters a curious brown bear on a winding forest path. The chef, holding a large basket of freshly picked mushrooms, stops in surprise, maintaining a cautious yet calm demeanor. The bear, intrigued by the chef's presence, stands on its hind legs, sniffing the air with interest. The scene is set in a lush, green forest, with sunlight filtering through the dense canopy, casting dappled shadows on the ground. The chef, with a look of determination, slowly backs away, keeping a steady eye on the bear, who watches intently, its ears perked up, before both continue on their respective paths, the chef returning to the kitchen and the bear disappearing back into the woods.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3141
|
videos/HRA_part0/3141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, donning a yellow vest and jeans, finds unexpected joy as he dances with a gentle horse in a grassy, fenced-in yard beside a country house. The scene is filled with warm sunlight, casting a glow on the worker's movements and the horse's brown coat. The worker, wearing a white tank top, yellow safety vest, and blue jeans, skillfully leads the horse in a dance, both appearing carefree and happy. Their joyful interaction is set against a backdrop of greenery and a wooden fence, creating a heartwarming contrast to the worker's usual environment.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the workers and the horse in the video are missing, the body generation is distorted, the horse's body is distorted, and there are problems with the head generation."
}
] |
seed46_3129
|
videos/HRA_part2/3129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned in a red apron with a white floral pattern, sits on a wooden chair in a sunlit room filled with art supplies. She gently caresses a chicken, which is perched on her lap, its head adorned with a vibrant red comb. The room is decorated with colorful paintings, a large easel, and a variety of art tools, creating a warm and creative atmosphere. The artist's face, framed by curly brown hair, expresses love and connection as she interacts with the bird, highlighting the unique bond between the two.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1428
|
videos/HRA_part1/1428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome male waiter, wearing a crisp white shirt, black vest, and necktie, serves a couple at an elegant indoor restaurant. Suddenly, he breaks into song, passionately singing an operatic aria while continuing to serve. The camera captures his animated face as he sings, highlighting his emotional performance. Throughout, the well-lit dining area with its ornate chandelier and patrons at other tables remains visible, creating a lively atmosphere. The waiter's confident singing and the restaurant's upscale ambiance provide a memorable contrast to his regular duties.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, and the hands are twisted."
}
] |
seed44_2930
|
videos/HRA_part1/2930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 gray T-shirt and black cargo pants, methodically mops the floor of a modern industrial space, surrounded by sleek machinery and equipment. His attire includes a name badge and a pair of safety glasses hanging around his neck, signifying his professional role. The scene is lit by bright overhead lights, casting shadows that emphasize the rhythmic motion of the mop. The engineer's focused gaze and steady hand convey a sense of duty and precision as he tackles the mundane task of cleaning, set against the backdrop of a high-tech environment.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand appears deformed, and the mop in his hand is also distorted."
}
] |
seed42_2804
|
videos/HRA_part0/2804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, donning a black tank top and dark jeans, mimics the agile movements of a mongoose, sprinting across a lush, verdant landscape. His intense gaze and athletic build convey strength and determination as he leaps over obstacles, embodying the spirit of the nimble creature. The scenery features vibrant greenery and a clear blue sky, providing a vivid contrast to his swift, mongoose-inspired running. Throughout the sequence, the actor maintains his focus and momentum, seamlessly integrating the mongoose's grace and speed into his performance.]"
},
{
"from": "gpt",
"value": "Bad. The man can be clearly seen running in the video, but his movements are not continuous and smooth, showing some coordination issues."
}
] |
seed44_2995
|
videos/HRA_part1/2995.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, with its bushy tail swaying, dances gracefully in a clearing surrounded by lush green foliage. Its movements are fluid and lively, as if performing a choreographed routine under the dappled sunlight filtering through the leaves. The fox leaps and twirls, its fur shimmering with golden highlights, embodying the spirit of the wild in a joyful, uninhibited dance. Against the backdrop of the vibrant forest, the fox's agile form and animated expressions convey a sense of freedom and playfulness in nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1790
|
videos/HRA_part1/1790.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a medium-large raptor with a brown back and contrasting white underparts, soars majestically over a vast body of water. Its piercing eyes scan the surface below for prey, its feathers ruffled by the wind. Suddenly, it dives headfirst into the water, emerging triumphantly with a wriggling fish clasped firmly in its talons. The osprey then flies off, heading towards its nest perched high in a tree, ready to feed its young. The scene is set against a backdrop of rolling hills and a clear blue sky, highlighting the bird's natural habitat and hunting prowess.]"
},
{
"from": "gpt",
"value": "Bad. The osprey's wings in the video have issues with generation, the face is generated blurry, and the claws are not generated at all."
}
] |
seed44_1243
|
videos/HRA_part1/1243.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman wearing a brown jacket and brown pants is crawling on a wooden floor inside a rustic cabin. She is moving towards a large, curious moose that has its head inside the cabin through an open window. The moose, with its distinctively large antlers, is also partially inside the cabin, seemingly intrigued by the woman's presence, creating an unusual and captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The moose moves headfirst through the window, which is unrealistic."
}
] |
seed44_2171
|
videos/HRA_part1/2171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit African savanna, a herd of majestic Cape buffaloes gathers near a watering hole. The scene opens with a panoramic view of the landscape, emphasizing the natural habitat. A buffalo, its body glistening with water droplets, emerges from the watering hole and begins to rub against a tree, its large horns and muscular frame highlighted. Another buffalo, also wet, vigorously shakes its head, spraying water around. The herd grazes peacefully nearby, showcasing their daily routine in the wild, with the watering hole as a central point, surrounded by tall grasses and scattered acacia trees.]"
},
{
"from": "gpt",
"value": "Normal. The head generation of the walking water buffalo in the video has issues, and there are three front legs appearing in the middle frames of the walking water buffalo."
}
] |
seed46_2806
|
videos/HRA_part2/2806.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 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 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": "Good. No obvious issues."
}
] |
seed44_2814
|
videos/HRA_part1/2814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a royal blue scrubs top and light blue pants, stands against a white wall with a large, welcoming smile. She waves energetically with her right hand, her dark brown hair styled in a bun. Behind her, a row of lockers can be seen, adding context to the hospital setting. Her left arm rests by her side, and she wears a silver watch on her wrist. The nurse's eyes are closed as she waves, conveying genuine warmth and friendliness to the viewer.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's eyes in the video have generation issues, and the fingers are deformed."
}
] |
seed46_2831
|
videos/HRA_part2/2831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a costumed musician, dressed in a vibrant green hippopotamus outfit, gracefully crawls across a dimly lit stage. The stage is adorned with a red velvet curtain, adding a touch of drama. The musician's movements are slow and deliberate, almost balletic, as they crawl with an air of performance art. The costume is complete with oversized hippo ears and a large, friendly smile, creating a surreal and captivating visual display.]"
},
{
"from": "gpt",
"value": "Bad. The musician's crawling motion in the video is not smooth."
}
] |
seed42_2108
|
videos/HRA_part0/2108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an imaginative scene, a waiter, dressed in a classic black suit and tie, carefully balances a tray of cocktails above his head as he swims underwater. Surrounding him are porcupines, wearing tiny swim caps and goggles, swimming alongside in a synchronized pattern, all submerged in a vast, clear pool under soft, ambient lighting. The waiter's face, visible beneath the water, shows a mix of concentration and amusement at the unusual company he keeps during his aquatic beverage service.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1025
|
videos/HRA_part0/1025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone seagull perches regally atop a wooden post on a deserted, windswept beach, its pristine white feathers ruffled by the salty breeze. The gull, with its sharp yellow beak and piercing eyes, surveys the vast expanse of sea and sky, seemingly contemplating the horizon. Suddenly, it spreads its wings, launching into flight, the camera capturing the intricate detail of its feathered anatomy as it glides effortlessly over the undulating waves. The seagull then returns to its perch, standing tall against the dramatic backdrop of an overcast sky, embodying the spirit of the coast.]"
},
{
"from": "gpt",
"value": "Normal. The wings flew away, and then suddenly reappeared."
}
] |
seed42_1932
|
videos/HRA_part0/1932.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 inventive engineer, wearing safety goggles and a lab coat, has designed a unique, waterproof hamster-sized diving suit. The hamster, now transformed into an aquatic explorer, swims energetically in a clear fish tank, bubbles rising around it. The tank is placed on a wooden table in a cluttered workshop filled with tools and gadgets. The engineer watches intently, clipboard in hand, documenting the hamster's swimming patterns as it propels itself through the water with its tiny limbs, creating a whimsical yet scientific scene.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's face and hands, as well as the hamster's paws, are generated incorrectly in the video."
}
] |
seed46_2514
|
videos/HRA_part2/2514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space habitat designed to mimic Earth's savanna, a majestic rhinoceros, fitted with a specialized spacesuit, calmly walks on artificial grass under a simulated sky. Tourists, dressed in sleek, white spacesuits, observe from a safe distance behind transparent barriers, their expressions a mix of awe and curiosity. The rhino moves gracefully, its every step monitored by advanced technology to ensure its well-being in the zero-gravity environment. This unique scene captures the harmony between wildlife conservation and the boundless possibilities of space exploration, offering viewers a glimpse into a world where nature and technology coexist in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The rhinoceros's face is distorted, the legs are twisted, and the human faces are distorted."
}
] |
seed42_2091
|
videos/HRA_part0/2091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student wearing a gray sweater and black jeans sits in a classroom, wiping the surface of a large, advanced telescope with a cloth, as if preparing it for use. The room is dimly lit, with a projector screen displaying images of deep space in the background. The student's focus is intense, their actions deliberate, as they handle the telescope with care, its size and complexity suggesting it is used for serious astronomical research or communication. The overall scene conveys a sense of dedication and curiosity about the mysteries of the universe.]"
},
{
"from": "gpt",
"value": "Good. Basically no 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 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 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": "Good. Basically correct."
}
] |
seed44_322
|
videos/HRA_part1/322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European brown hare is seen swimming across a serene, glassy lake, its ears perked up and alert. It moves gracefully through the water, showcasing its rarely-seen swimming ability. The hare's body, including its long legs and large hind feet, propels it forward as it navigates the calm lake surface. The scene is set against a lush green landscape, highlighting the unexpected yet captivating sight of a hare swimming.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2941
|
videos/HRA_part2/2941.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate woman in a khaki safari outfit gently caresses the muzzle of a rhinoceros, standing on wooden docks overlooking a tranquil lake. The woman, wearing a wide-brimmed hat and a satisfied smile, connects with the rhino, which has a textured hide and a horn. Both are framed by lush greenery and set against a backdrop of serene water, creating a harmonious scene of human-animal interaction. The woman's affectionate touch and the rhino's calm demeanor, along with the peaceful lake in the background, evoke a sense of mutual respect and tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2827
|
videos/HRA_part2/2827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a white hazmat suit with a respirator mask, meticulously paints the walls of a spacious, well-lit room with vibrant orange strokes, capturing the essence of transformation. His attire, complete with protective goggles and gloves, underscores the precision and safety measures involved in the task. The room, initially a blank canvas, gradually comes alive with color, highlighting the engineer's skill and attention to detail as he revitalizes the space.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's arm is missing in the video, the fingers are deformed, and the face is blurry."
}
] |
seed46_3173
|
videos/HRA_part2/3173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, with a coat of dark fur and a muscular build, sprints across a lush, green savanna landscape, kicking up small clouds of dust with each stride. The chimp's powerful limbs propel it forward with agile determination, showcasing its natural athleticism in a vivid display of movement. As it runs, its eyes are fixed ahead, ears pressed back, and mouth slightly open, revealing a tongue panting from exertion. The background features tall grass swaying in the breeze and scattered acacia trees under a vast, cloud-dappled sky.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the chimpanzee in the video have generation issues, and the facial generation is blurry."
}
] |
seed46_2906
|
videos/HRA_part2/2906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, middle-aged man wearing a white lab coat over a crisp blue shirt and khaki trousers walks his golden retriever on a leash in a lush, green park. The sun filters through the leaves, casting dappled light on the path. The doctor, with salt-and-pepper hair and glasses, smiles warmly as he interacts with his dog, which bounds joyfully ahead, exploring the surroundings. The two stroll past other park-goers, who exchange friendly nods, creating a scene of community and companionship in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's face is distorted, hands are distorted, the dog's head is distorted, legs are distorted, and the body is distorted."
}
] |
seed42_3178
|
videos/HRA_part0/3178.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. Basically correct."
}
] |
seed42_1005
|
videos/HRA_part0/1005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a crisp white uniform and a colorful stethoscope, finds herself at the edge of a vast, shimmering ocean, where the sand meets the water. In her arms, she holds a small, fluffy rabbit, its ears perked up in curiosity. Together, they watch as a group of rabbits, similarly white and fluffy, leap and jump playfully across the sandy shore, the waves gently lapping at the background, creating a serene and whimsical scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1966
|
videos/HRA_part0/1966.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brightly lit, futuristic classroom filled with advanced technology, two young children, a boy and a girl, both wearing school uniforms, gently caress a small, friendly robot astronaut. The robot, designed with smooth, rounded edges for safety, features a smiling face on its metallic body, which is painted in shades of silver and blue. The room is decorated with educational posters and interactive screens, creating an engaging learning environment. The children, showing curiosity and affection, interact with the robot, which responds with gentle movements and playful sounds, fostering a connection between humans and artificial intelligence in a nurturing setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1717
|
videos/HRA_part0/1717.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and utility belt, stands in a dimly lit alleyway, his face partially obscured by shadow. He takes a deep breath, his chest expanding beneath his bulletproof vest, as he prepares for action. The focus is on his breathing, a testament to his calm under pressure, with the urban environment providing a gritty backdrop. His hand rests on his holstered weapon, and his eyes scan the surroundings, alert and watchful, as he draws another measured breath.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1285
|
videos/HRA_part2/1285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, imaginative scene, a group of koalas dressed in miniature black suits and top hats gather under a starlit sky, paying respects at a unique space-themed funeral. One koala, standing out from the crowd, begins to dance sorrowfully yet gracefully, its movements illuminated by the glow of distant galaxies and shimmering stars. As it twirls, a cosmic dust trail follows its path, symbolizing the connection between life, death, and the vastness of the universe, creating a surreal and poignant moment in the vast expanse of space.]"
},
{
"from": "gpt",
"value": "Normal. The dancing koala's movements are not fluid, with abrupt changes."
}
] |
seed46_1310
|
videos/HRA_part2/1310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bobcat, distinguished by its brown fur, white underbelly, and tufted ears, stealthily crawls across a sandy surface in a suburban town, near wooden fences and lush greenery. It pauses to sniff the air, displaying its sharp teeth and alert demeanor. The feline then continues its crawl, passing by a stone wall and wooden planks, indicating the proximity to human habitation. Throughout the scene, the bobcat's cautious and curious nature is evident as it explores its surroundings in the town's outskirts.]"
},
{
"from": "gpt",
"value": "Normal. The cat's movements in the video are not smooth."
}
] |
seed44_1680
|
videos/HRA_part1/1680.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated, sword-like upper jaw, glides gracefully through the clear, turquoise waters of the open ocean. Its sleek, metallic blue body shimmers as it swims, propelled by a powerful tail fin. The fish is seen from various angles, showcasing its impressive size and streamlined shape designed for speed. At one point, it leaps out of the water, displaying its agility and strength, before plunging back into the depths, leaving a trail of shimmering ripples on the ocean surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_14
|
videos/HRA_part1/14.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male teacher, wearing a gray sweater over a button-down shirt, yawns dramatically in a classroom filled with desks, capturing a candid moment during a school day. His eyes are closed, his mouth is wide open, and his right hand is holding a red pen, while stacks of papers and books clutter the desk in front of him. The walls are adorned with educational posters, and sunlight streams in from a nearby window, illuminating the room. This intimate scene portrays the relatable, unguarded moment of a dedicated educator succumbing to a yawn amidst his daily responsibilities.]"
},
{
"from": "gpt",
"value": "Bad. There were issues with the generation of the face, hands, and red pen of the character in the video."
}
] |
seed46_1306
|
videos/HRA_part2/1306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up of a rotisserie chicken, golden brown and crispy-skinned, slowly turning on a spit under the glow of overhead lights. The chicken is surrounded by an array of fresh vegetables, including bell peppers, onions, and tomatoes, which are also roasting alongside it. The scene is set in a bustling open-air market, with the rotisserie stand positioned between colorful fabric canopies and bustling shoppers. The camera captures the succulent chicken from various angles, highlighting its mouthwatering texture and the aromatic steam rising from it, all against the vibrant backdrop of the market.]"
},
{
"from": "gpt",
"value": "Normal. The shape of the generated roasted chicken does not match the actual shape of a chicken."
}
] |
seed44_2736
|
videos/HRA_part1/2736.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cave, a small brown bat, with leathery wings folded against its body, walks along the rocky ground with deliberate steps. Its face, framed by long, curved ears, is keenly observant. The bat pauses momentarily, revealing its tiny feet and claws as it navigates the stone surface. The focus then shifts to the bat's head, highlighting its intricate facial features and alert eyes. Finally, the bat is seen walking away, its silhouette set against the textured cave wall, creating a captivating scene of a bat navigating its environment on foot.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1104
|
videos/HRA_part1/1104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast boreal forest, where the trees stand tall against the misty morning sky, a peculiar scene unfolds. A doctor, clad in a crisp white lab coat and wearing round spectacles, kneels beside a small, curious rat. The rodent, with its sleek brown fur and expressive beady eyes, sits upright, seemingly engaged in conversation. The doctor, with a gentle demeanor, wipes the rat's face with a soft cloth, removing unseen smudges. The interaction is tender, the forest providing a serene and natural backdrop to this unusual bond between human and animal.]"
},
{
"from": "gpt",
"value": "Normal. The paw generation of the mouse in the video is unreasonable."
}
] |
seed46_2440
|
videos/HRA_part2/2440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 domestic chicken, featuring brown and white feathers, is shown swimming in a small, clear body of water, surrounded by green grass and foliage. It paddles energetically with its feet, creating ripples on the water's surface, while its head remains dry above the waterline. The chicken's unique activity is captured in a series of shots that showcase its unexpected aquatic adventure in a natural, backyard setting.]"
},
{
"from": "gpt",
"value": "Bad. The chicken in the video has uncoordinated movements."
}
] |
seed46_1396
|
videos/HRA_part2/1396.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red tracksuit, emulates a monkey with playful antics, running energetically across a vibrant green field under a clear blue sky. The student's facial expression, complete with wide eyes and an open mouth, mirrors the monkey's characteristic features, enhancing the mimicry. Accompanied by a group of friends, who cheer and laugh in the background, the scene captures a moment of carefree fun and youthful exuberance. The student's attire, which includes a red jacket and matching pants, stands out against the lush greenery, while the clear blue sky provides a perfect backdrop for the lively scene.]"
},
{
"from": "gpt",
"value": "Normal. The video can more clearly show the students running, but the continuity is poor."
}
] |
seed42_2435
|
videos/HRA_part0/2435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic stork, distinguished by its gray feathers and black wingtips, is captured in a series of poses. Initially, it stands tall on a grassy bank, legs firmly planted, looking alert. Then, it spreads its wings wide, ready for flight, with a serene lake and lush greenery serving as a backdrop. Next, the bird is seen in mid-flight, gracefully soaring over the water's surface, with its wings fully extended and head held high. Finally, it lands elegantly, tucking its wings and extending its long legs, touching down on the grass near the water's edge, completing the sequence of its daily activities by the lakeside.]"
},
{
"from": "gpt",
"value": "Bad. The stork's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_1649
|
videos/HRA_part0/1649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bright, modern kitchen with white cabinets and countertops, two young children, a boy and a girl, both wearing red aprons over their clothes and chef hats, are attentively stirring ingredients in separate pans on a large, stainless steel gas stove. The boy, with short brown hair, focuses on his task with a serious expression, while the girl, with long blonde hair tied in pigtails, smiles as she stirs. The camera captures the sizzling sound of the food cooking, emphasizing the lively atmosphere. The room is filled with natural light from a window above the sink, illuminating the children as they cook, with a row of hanging pots and pans visible in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1861
|
videos/HRA_part2/1861.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": "Good. No obvious problems."
}
] |
seed42_1185
|
videos/HRA_part0/1185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 stunning kingfisher bird perches regally on a weathered branch that extends over a serene body of water, its vibrant blue and orange feathers glistening in the sunlight. The bird's piercing gaze is fixed on the water below, hinting at its hunting prowess. Suddenly, it takes flight, its wings a blur of color against the tranquil backdrop of the pond, surrounded by lush green foliage. As it hovers above the water, about to dive, the scene captures the kingfisher's agility and the beauty of nature in a single, captivating moment.]"
},
{
"from": "gpt",
"value": "Bad. The kingfisher's claws were not generated, and the wings were incompletely generated."
}
] |
seed46_2059
|
videos/HRA_part2/2059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor kneels in a lush green forest, attentively examining a small, injured deer lying on the mossy ground. The deer, with its distinctive brown coat and white underbelly, looks up at the doctor with trusting eyes. The scene is peaceful, with sunlight filtering through the trees, casting dappled shadows on the forest floor. The doctor, wearing a green field jacket and khaki pants, gently touches the deer's leg, showing care and concern. Nearby, other deer stand watch, their ears perked, observing the interaction from a safe distance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2943
|
videos/HRA_part1/2943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its dark brown coat and long, curved horns, is captured mid-stride as it sprints across a rocky terrain. The detailed shot focuses on the ibex's powerful legs and hooves, which grip the stone surface, propelling it forward with agility and strength. The ibex's body is outlined against a backdrop of rugged mountains and a clear blue sky, emphasizing its natural habitat. The video highlights the animal's endurance and speed as it navigates the challenging landscape with ease.]"
},
{
"from": "gpt",
"value": "Bad. The video shows abnormal generation of the argali's head, and the limbs of the argali in the middle frames are severely distorted."
}
] |
seed42_2182
|
videos/HRA_part0/2182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a classic white uniform and cap, is seen attentively checking a series of smoke detectors in a pristine hospital corridor. She methodically inspects each device, her actions conveying a sense of responsibility and care for patient safety. With a focused gaze and a tool in hand, she demonstrates her commitment to ensuring that the smoke alarms are functioning properly, maintaining a vigilant stance against potential hazards in the healthcare facility. Throughout the process, she moves from one detector to another, her white shoes echoing softly on the polished floor, reinforcing the importance of routine safety checks in a medical environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed42_2528
|
videos/HRA_part0/2528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful kangaroo, exhibiting strength and agility, sprints across a vast, arid landscape under a clear blue sky. Its muscular legs propel it forward in a series of bounding leaps, while its long, thick tail acts as a perfect counterbalance. The kangaroo's fur, a rich sandy brown, blends harmoniously with the earthy tones of the terrain, dotted with sparse vegetation. As it runs, its ears perk up, alert and attentive, showcasing the grace and endurance of this iconic marsupial in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. When running and jumping, the kangaroo's legs appear deformed."
}
] |
seed46_1123
|
videos/HRA_part2/1123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge, sits attentively on a stone bench in a small, enclosed garden. He rests his hands on his thighs, wearing black gloves, and looks directly at the camera with a serious expression. Behind him, lush greenery and blooming flowers frame the serene setting, offering a peaceful contrast to his authoritative presence. The officer's attire includes a navy cap, and he holds a black baton in his right hand, symbolizing his role in maintaining law and order. Despite the tranquility of the garden, his alert posture and watchful gaze convey readiness and vigilance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1761
|
videos/HRA_part1/1761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling train station filled with travelers, a diligent janitor wearing a yellow high-visibility vest is wiping down a large window, revealing the vibrant cityscape outside. The scene is set during the daytime, with bright sunlight illuminating the interior of the station. Among the crowd, a person dressed in a panda costume stands out, adding a whimsical touch to the busy environment. The janitor continues to clean the window, ensuring a clear view of the passing trains and the urban landscape beyond.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2311
|
videos/HRA_part2/2311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent leopard, with striking golden eyes and a distinctive pattern of rosettes on its tawny fur, is captured in high definition as it lies on a branch. It begins by looking straight ahead, showcasing its majestic presence. Then, it turns its head to the right, revealing its sharp features and powerful muscles rippling beneath its coat. Next, the leopard proceeds to clean itself, licking its paw and wiping it across its face, a display of natural behavior in its untamed habitat. Throughout the sequence, the leopard remains perched on the branch, its gaze occasionally flicking towards the viewer, offering a rare glimpse into its private grooming routine.]"
},
{
"from": "gpt",
"value": "Normal. The leopard in the video is basically normal, but there is slight uncoordination in its movements."
}
] |
seed42_2746
|
videos/HRA_part0/2746.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A group of four energetic children, two boys and two girls, wearing colorful clothing including red, blue, and green shirts, jump high into the air in unison, against a backdrop of a cloudy sky and lush green grass. Their faces are filled with joy and excitement as they perform their synchronized leap. One boy, in a striped shirt, and one girl, in a pink dress, stand out among them, capturing the essence of youthful exuberance and carefree play in a natural outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3156
|
videos/HRA_part2/3156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 suburban neighborhood, a majestic moose stands near a residential street, its large frame contrasting with the mundane setting. The creature is seen wiping its antlers on a tree branch, possibly marking its territory. The scene is set against a backdrop of houses and greenery, giving the impression of wildlife encroaching upon human living spaces. The moose, with its shaggy fur and imposing stature, interacts with its environment in a display of natural behavior, despite the suburban backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The moose's tail in the video is deformed, and there is an issue with the nose generation."
}
] |
seed42_1988
|
videos/HRA_part0/1988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprawling mall, a middle-aged janitor, clad in a yellow high-visibility vest and dark pants, runs with purpose through the corridors. The scene begins with him standing alert, mop in hand, amidst the vibrant retail environment. Then, he sprints past various storefronts, the motion blur from his movement emphasizing his haste. As he continues, he deftly maneuvers around a corner, demonstrating agility in his work boots. Lastly, he is shown running with determination across a checkered tile floor, the bustling mall life continuing around him, highlighting his role in maintaining the facility's cleanliness amidst the daily hustle and bustle.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs are missing in the video, and his face is generated blurry."
}
] |
seed42_2964
|
videos/HRA_part0/2964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cheerful female cashier, wearing a green apron over a gray sweater and black pants, stands on a ladder cleaning the gutters of a small, wooden house during autumn. She has pulled back her long, dark brown hair into a bun. The scene is set in a backyard with lush green grass, and there are trees with yellow leaves in the background. The house features a red front door, a green window frame, and a roof with brown shingles. The woman uses a gloved hand to scoop out debris from the gutters, showcasing her determination and hard work.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1032
|
videos/HRA_part0/1032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a navy uniform with a badge, cap, and sunglasses, stands at the edge of a zoo's flamingo enclosure, where vibrant pink birds congregate. The scene shifts slightly to reveal a clear blue pool within the zoological park, where the officer now interacts with the public, demonstrating water safety techniques. Nearby, children and families watch, some seated on benches under the shade of lush trees, while others lean on the railing, observing the swimming demonstration with interest. Throughout, the police officer remains engaged and attentive, fostering a sense of community and safety among the zoo visitors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1642
|
videos/HRA_part2/1642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in a brown jacket and beige pants is seen crawling on his hands and knees through a lush, green forest, with ferns and mossy rocks surrounding him. Moments later, a large moose with a majestic rack of antlers stands tall and vigilant nearby, observing the man's unusual behavior. The scene then focuses on the man's face, showing his determination and focus, while the moose continues to watch from a distance, its presence adding a sense of wildness and unpredictability to the forest setting. Finally, the man and the moose share a silent moment of connection, both existing in harmony within the natural world, the man still crawling and the moose standing tall, creating a unique and unexpected encounter in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2517
|
videos/HRA_part2/2517.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male worker, wearing a white shirt, beige pants, and a traditional headscarf, is seen wiping the face of a brown camel with a white cloth. The action takes place in a sandy environment, with other camels standing in the background, creating a scene that highlights the care and connection between the worker and the animal. The worker's focused expression and gentle touch convey a sense of respect and familiarity, while the setting sun casts a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_1067
|
videos/HRA_part0/1067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman, wearing a vibrant red dress and black high heels, gracefully dances in the center of a bustling restaurant. The place is filled with the warm glow of hanging lights and lively chatter from the patrons seated at their tables. She moves with confidence and joy, her dress swirling around her as she twirls to the rhythm of the live band playing in the corner. The camera captures her expressive face, full of happiness, and the admiring glances of those around her who pause to watch her performance.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves of the person in the video are not coordinated."
}
] |
seed46_2583
|
videos/HRA_part2/2583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a full uniform complete with a badge, gun, and hat, is tending to a lush garden in a public park. He begins by weeding around vibrant flowers, his actions gentle yet purposeful. Next, he waters the plants with a hose, the mist from the water creating a small rainbow in the sunlight. Then, he plants a new shrub, digging a hole with a small shovel and carefully placing the plant inside. Finally, he prunes a bush into shape, his movements precise as he shapes the greenery, all while maintaining his authoritative yet approachable demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the police officer in the video are missing, and the face is deformed."
}
] |
seed46_2646
|
videos/HRA_part2/2646.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a costumed character resembling a janitor, complete with a green jumpsuit, gray mustache, and brown hair, performs an energetic jump. This quirky figure, embodying both the roles of maintenance worker and woodland creature, is set against a neutral backdrop. The playful scene is enhanced by the addition of an animated beaver, which appears to mimic the janitor's jumping action, creating a comical and engaging visual narrative. Both characters are depicted in vibrant colors, with the beaver sporting realistic features and the janitor maintaining his distinct uniform and facial details.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3151
|
videos/HRA_part0/3151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a trimmed beard, wearing a red flannel shirt, blue jeans, and a brown hat, stands in a barn filled with hay bales. He sneezes loudly, holding a pitchfork, as dust particles and shafts of sunlight fill the air around him. The barn is rustic, with wooden beams and a dirt floor, and the farmer's sneeze echoes throughout the space. Afterward, he wipes his nose with a red handkerchief, the barn's interior still visible behind him, before continuing his work with the hay.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2930
|
videos/HRA_part1/2930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a gray T-shirt and black cargo pants, methodically mops the floor of a modern industrial space, surrounded by sleek machinery and equipment. His attire includes a name badge and a pair of safety glasses hanging around his neck, signifying his professional role. The scene is lit by bright overhead lights, casting shadows that emphasize the rhythmic motion of the mop. The engineer's focused gaze and steady hand convey a sense of duty and precision as he tackles the mundane task of cleaning, set against the backdrop of a high-tech environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are slightly discontinuous."
}
] |
seed42_3106
|
videos/HRA_part0/3106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded male musician, clad in a brown jacket, blue jeans, and a gray hat, walks through a dense forest filled with tall, lush green trees. He carries a guitar case over his shoulder, suggesting a journey to or from a performance. The woodland environment is rich with ferns and moss, creating a vibrant, natural setting. Sunlight filters through the canopy, casting dappled light on the forest floor as the musician strides purposefully along the path, his attire and equipment blending harmoniously with the woodlands.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_1711
|
videos/HRA_part1/1711.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of a Downy Woodpecker perched on a thin tree branch is captured in stunning detail. The bird, with its distinctive black and white plumage and a red patch on the back of its head, is shown from the side as it focuses intently on something in the distance. Its sharp, pointed beak is slightly open, ready to peck at a nearby tree trunk. The woodpecker's eyes are large and alert, set against the intricate patterns of its feathers. The background is a soft blur of green leaves and twigs, emphasizing the bird's striking features.]"
},
{
"from": "gpt",
"value": "Normal. The bird's beak in the video is generated too high, and the claws are not generated."
}
] |
seed42_2411
|
videos/HRA_part0/2411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, grassy plains under a wide, clear blue sky, two small children, a boy and a girl, both wearing vibrant yellow raincoats and red boots, walk alongside a majestic bison. The bison, with its shaggy brown fur and large, powerful body, moves gracefully across the landscape, leading the children on an adventurous journey. The siblings follow closely, their expressions a mix of awe and delight, as they explore the wilderness together with their unlikely companion. The scene is peaceful, with the gentle swaying of tall grass and the distant silhouette of mountains framing the horizon.]"
},
{
"from": "gpt",
"value": "Bad. The boy's walking action is uncoordinated."
}
] |
seed46_2920
|
videos/HRA_part2/2920.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, donning a crisp white shirt, black trousers, and a waistcoat, unexpectedly finds himself fixing a leaky faucet in a vintage-styled restroom. With a wrench in hand, he leans over the basin, his face concentrated as he works under the sink. The scene captures the unusual sight of the waiter, his attire contrasting with the task at hand, as he tightens the faucet, the water now streaming smoothly. The room is adorned with antique fixtures and a classic mirror above the basin, adding to the unique scenario of a waiter turned handyman.]"
},
{
"from": "gpt",
"value": "Good. The waiter's actions in the video are basically normal."
}
] |
seed42_2905
|
videos/HRA_part0/2905.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, recognizable by its black ears and eye patches, crawls on all fours across a lush, green forest floor, its fur a striking contrast against the vibrant vegetation. It moves slowly, carefully placing each paw, showcasing its strength and agility. The panda's attention is drawn to something in the distance, its ears perked, adding a layer of curiosity to its demeanor. Surrounded by bamboo plants, a staple in its diet, the panda continues its crawl, encapsulating the essence of its natural habitat in every deliberate motion.]"
},
{
"from": "gpt",
"value": "Normal. The panda's legs show deformities."
}
] |
seed44_2363
|
videos/HRA_part1/2363.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 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 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": "Good. No obvious problems."
}
] |
seed46_2243
|
videos/HRA_part2/2243.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic musician, clad in a vibrant yellow raincoat and matching hat, stands under a powerful waterfall in a lush, green forest, playing a harmonica with intense focus. The water cascades over mossy rocks, creating a natural stage for the performer. Suddenly, the musician leaps into the air, harmonica still in mouth, capturing a moment of pure joy and freedom amidst the thundering water and verdant surroundings. The scene is framed by towering trees and ferns, emphasizing the connection between music, nature, and human spirit.]"
},
{
"from": "gpt",
"value": "Bad. The musician's harmonica playing movements in the video are not very smooth and continuous, showing some disharmony; the musician's jumping action is also discontinuous, with noticeable abrupt changes."
}
] |
seed44_1288
|
videos/HRA_part1/1288.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 unsmoothly, with uncoordinated movements."
}
] |
seed42_1943
|
videos/HRA_part0/1943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, vibrant green lizard with intricate patterns adorns its skin, positioned on a dry, cracked earth surface under a bright, cloud-dappled sky. It appears to dance, flicking its tongue and swaying its body in a manner that suggests movement to an unseen beat. The lizard's movements are fluid and energetic, its tail swishing and its limbs moving gracefully as if it's performing a choreographed routine. Despite the arid environment, the lizard's dance brings a sense of lively energy to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The sky full of clouds mentioned in the caption does not appear in the video."
}
] |
seed46_2020
|
videos/HRA_part2/2020.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, clad in a black shirt, performs energetically on stage under red lights, passionately singing into a microphone. Simultaneously, he wipes sweat from his forehead with his right hand, revealing a wristwatch. Behind him, a drummer in a black sleeveless shirt plays enthusiastically, and a guitarist in a black shirt strums powerfully. The stage is adorned with jaguar patterns, adding a touch of wild flair to the performance.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed42_2229
|
videos/HRA_part0/2229.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a majestic brown horse gallops gracefully across the foreground, its muscular form silhouetted against a backdrop of sprawling factories with billowing smokestacks. Amidst this industrial landscape, a group of diverse individuals dressed in vibrant, eclectic clothing forms a stark contrast as they engage in expressive dance moves, their joyous expressions and dynamic movements standing out against the grey, mechanical setting. This unlikely fusion of nature, industry, and human spirit creates a compelling narrative of resilience and vitality.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are uncoordinated, and the horse's movements are not smooth."
}
] |
seed46_1063
|
videos/HRA_part2/1063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a bobcat, recognizable by its short tail and tufted ears, dashes across the frame, passing by an automated checkout machine in a minimally designed convenience store. The animal's panicked sprint is juxtaposed against the sterile environment of the store, where the self-checkout machine stands idle. The bobcat's unexpected intrusion adds an element of chaos to the otherwise mundane setting, creating a surreal moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Normal. Two tails appeared."
}
] |
seed44_2150
|
videos/HRA_part1/2150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large Grouper fish, known for its speckled brown and white skin, swims serenely in clear, blue-green waters, surrounded by vibrant coral reefs teeming with life. Its powerful body, complete with a wide mouth and large eyes, glides effortlessly through the underwater environment. The Grouper pauses, hovering near a cluster of colorful corals and exotic marine life, showcasing its size and strength against the intricate patterns of the reef. The scene captures the fish's natural habitat, highlighting the contrast between its imposing presence and the delicate beauty of the coral ecosystem.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2956
|
videos/HRA_part0/2956.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rugged farmer, clad in a white tank top, denim overalls, and brown work boots, stands in a modest kitchen with white cabinets and a checkered floor. He reaches into a modern, stainless steel dishwasher, his hands strong and calloused from farm labor. Carefully, he extracts a large, white plate, placing it onto a wooden drying rack set on the counter, where other plates and utensils already rest. The scene is intimate, highlighting the unexpected domestic task of unloading the dishwasher performed by this typically outdoorsy figure.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted, the arm is twisted, and the plate is warped."
}
] |
seed46_1187
|
videos/HRA_part2/1187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, clad in dark attire with a badge and hat, interacts with a large, gray elephant at a beachside location, both standing near the water's edge. The elephant, with its distinctive tusks and wrinkles, playfully splashes water with its trunk, while the officer watches with an amused smile. In another scene, the officer gently pats the elephant's head, which is dripping with water, suggesting they have been swimming together. Lastly, the duo is captured in a heartwarming moment, with the officer and the soaking-wet elephant sharing a tender interaction against the serene backdrop of a sandy shore and the vast ocean.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1039
|
videos/HRA_part0/1039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed weasel, donning a lab coat and stethoscope, stands at the edge of a swimming pool, located in the backyard of a charming suburban house. The weasel, playing the role of a doctor, attentively examines a patient, who is resting on a floating mattress in the pool, under the shade of an umbrella. Surrounding the pool are other houses, creating a neighborhood backdrop, while the weasel-doctor continues to provide care in this unconventional setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1115
|
videos/HRA_part0/1115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a fantastical scene, a man wearing a brown fur coat and matching furry boots is seen dancing joyfully next to a massive, ancient mammoth with long, curved tusks. The mammoth stands placidly, observing the man's lively movements. Behind them, a quaint village is visible, featuring a row of charming, colorful houses with thatched roofs. The houses are nestled among lush greenery, creating a picturesque and harmonious setting. The man's animated dancing contrasts with the mammoth's calm presence, while the village in the background adds a touch of warmth and community to the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.