video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2179
|
videos/HRA_part1/2179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a dark green winter jacket, gray gloves, and a matching hat, diligently shovels snow from a pathway in front of a red-brick building with a yellow door. Snowflakes continue to fall gently, accumulating on the ground and surrounding trees. The man, with a serious yet focused expression, works methodically, clearing the path section by section. His breath visible in the cold air, he pauses momentarily, looking up at the sky as if assessing the weather conditions, before resuming his task with renewed determination.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers and eyes in the video have generation issues, and the tool in his hand is partially missing."
}
] |
seed42_1608
|
videos/HRA_part0/1608.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature, bespectacled teacher, wearing a gray blazer over a button-down shirt, walks down a dimly lit, empty hallway with lockers on either side. Suddenly, a small brown rat scurries across the floor in front of him, causing the teacher to pause and look down with a mix of surprise and curiosity. The rodent continues its journey undeterred, disappearing around a corner as the teacher resumes his walk, now with a slight smile and a shake of his head, as if amused by the unexpected encounter.]"
},
{
"from": "gpt",
"value": "Normal. The face and hands of the character in the video, as well as the mouse, were generated abnormally."
}
] |
seed46_2156
|
videos/HRA_part2/2156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-lit, modern clothing store, a friendly, young female cashier with brown hair tied in a bun assists a male customer. She is shown measuring the hem of a pair of beige slacks, using a measuring tape, while the man stands patiently. The pants are held up by the customer, who wears a casual outfit consisting of a blue shirt and dark pants. The cashier, dressed in a black apron over a white blouse, carefully marks the fabric with a tailor's chalk, indicating where the alteration should be made. The scene is set against the backdrop of the store, with various racks of clothes visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hands appear deformed, and the ruler in her hand is also distorted."
}
] |
seed44_2664
|
videos/HRA_part1/2664.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 doctor, wearing a brown jacket over a white shirt and khaki pants, walks through a temperate deciduous forest during autumn. The trees are predominantly bare, with scattered leaves covering the ground. The forest floor is carpeted with a thick layer of dry, brown leaves, creating a crunching sound underfoot. The doctor occasionally stops to observe his surroundings, showcasing his appreciation for nature. Throughout the scene, the forest remains dense and the trees tall, with occasional glimpses of sunlight filtering through the canopy, highlighting the serenity of the environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's fingers are incompletely generated, and there are issues with the feet generation."
}
] |
seed44_2083
|
videos/HRA_part1/2083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 waiter with neatly combed brown hair and a black uniform serves a couple seated at a beachside table, the ocean's horizon providing a romantic backdrop. He carefully places two plates of food on the table, his hands displaying a gentle, caressing motion, as if cherishing the art of serving. The couple looks on appreciatively, the man wearing a gray T-shirt and glasses, the woman adorned in a black dress with a plunging neckline. The scene is set during the golden hour, with the sun's rays casting a warm glow over the ocean and the couple, encapsulating a moment of intimate dining by the sea.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1102
|
videos/HRA_part2/1102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a black jacket over a gray shirt and dark pants, is engaged in an intense scene where he skillfully catches a falling glass bottle with his right hand, displaying remarkable agility and precision. His focused gaze and the dynamic motion of the catch are highlighted against a dimly lit, gritty urban setting, adding to the dramatic effect of the moment. The scene is shot in high definition, capturing every detail of the actor's expression and the fluidity of his movements as he successfully intercepts the bottle mid-air.]"
},
{
"from": "gpt",
"value": "Bad. The character's motion of grabbing the bottle in the video is seriously unsmooth and uncoordinated."
}
] |
seed46_1913
|
videos/HRA_part2/1913.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary writer sits at a contemporary desk, crafting stories about space exploration, surrounded by swimming gear and a large aquarium filled with exotic fish. The room is illuminated by a floor lamp with a large shade, casting a warm glow on the writer's face. They wear a black shirt and a necklace, their focus intense as they type on a laptop. Behind them, a window reveals a starry night sky, evoking a sense of wonder and adventure into the cosmos. Beside the desk, a modern painting in shades of blue and green adds a splash of color, reminiscent of water, perhaps reflecting the writer's love for swimming. The aquarium, visible in the background, features colorful fish swimming among plants and rocks, adding a dynamic element to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2076
|
videos/HRA_part2/2076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a white uniform and a badge, is seen running through a lush, green landscape dotted with tall trees and vibrant vegetation. In the distance, a serene hot springs oasis comes into view, its steam gently rising against the backdrop of a clear blue sky. The nurse, with a backpack and running shoes, continues her jog towards this peaceful destination, her movements fluid and energetic. Upon arrival, she pauses to enjoy the tranquil atmosphere, the steam from the hot springs swirling around her, before continuing her run along the scenic path that meanders through the verdant scenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2929
|
videos/HRA_part0/2929.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a brown jacket over a striped shirt and khaki pants, performs a surprising leap over a row of yellow school lockers, demonstrating unexpected athleticism. In the next scene, he jumps again, this time over a green garbage can, showcasing his lively spirit. Then, he leaps over a red fire extinguisher mounted on a wall, his movements fluid and agile. Finally, the janitor, still clad in his brown jacket and khakis, clears a hurdle formed by a mop and bucket, his face expressing pure delight in these spontaneous acts of physicality, all within the confines of a school corridor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3039
|
videos/HRA_part2/3039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a casual outfit, is seen vacuuming a spotless living room with a modern upright vacuum cleaner, showcasing an unusual sight of a retail employee handling household chores. The room is impeccably clean, with hardwood floors and minimal furniture, highlighting the thorough cleaning process. The cashier, with her nametag visible, exhibits a sense of pride in her task, as if applying the same diligence to vacuuming as she would to serving customers. The contrast between her job as a cashier and the domestic activity adds a layer of humor and unexpectedness to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2903
|
videos/HRA_part2/2903.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 female cashier, wearing a red apron over a white collared shirt, black pants, and brown shoes, pulls a heavy, overflowing shopping cart across a busy supermarket floor. She moves with determination, navigating the aisles filled with various products and customers. The cart, brimming with goods, contrasts with her clean and tidy appearance, highlighting the physical demands of her job. Behind her, the supermarket's brightly lit shelves and bustling atmosphere provide a dynamic backdrop to her task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2784
|
videos/HRA_part0/2784.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, donning a traditional white uniform with a tall hat, finds himself in an extraordinary situation, crawling on his hands and knees across a lush, green field. Beside him, a friendly hippopotamus ambles along, mirroring the chef's movements in a comical display of camaraderie. The chef's attire, complete with a pristine white apron and polished shoes, contrasts humorously with the unconventional crawling action, while the hippopotamus, with its massive frame and gentle demeanor, adds a surreal element to the scene. Both crawl under a low-hanging branch of a tree, adding a touch of whimsy to the unexpected pairing.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth, and the hippo's movements are slightly not smooth."
}
] |
seed44_1449
|
videos/HRA_part1/1449.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary crab, displaying a vibrant red and orange carapace, scuttles across a shallow, sunlit tide pool, surrounded by lush green seaweed and other marine life. The crab's claws, one significantly larger than the other, are prominently displayed as it navigates its environment, with the smaller claw delicately handling food. Its intricate shell pattern and the dynamic underwater setting provide a visually engaging scene, all captured in stunning detail against a backdrop of clear, blue water and a sandy ocean floor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1658
|
videos/HRA_part0/1658.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, clad in a leopard-print outfit, leaps gracefully over a series of low, wooden hurdles set against a green, grassy field, reminiscent of an athletic training montage. Her hair is tied back in a bun, and she wears minimal jewelry, allowing her fluid movements to take center stage. As she jumps, her body is captured mid-air, highlighting her strength and agility. The sunlight filters through the trees, casting dappled shadows on the ground, adding a dramatic effect to the scene. Behind her, a lush forest provides a natural backdrop, further emphasizing the wild and free spirit embodied by the leaping woman.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video is distorted, with a twisted face, twisted arms, twisted legs, and twisted hands."
}
] |
seed42_2607
|
videos/HRA_part0/2607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting, a cheerful female cashier, wearing a yellow apron over a casual outfit, dances joyfully behind the counter of a rustic wooden market stall. The stall is adorned with colorful decorations and surrounded by vibrant greenery, enhancing the festive atmosphere. She moves energetically to an unseen beat, her smile contagious, as she momentarily pauses her duties to revel in the music. The village backdrop includes traditional architecture, bustling locals, and a lively community gathering, all contributing to the sense of celebration and unity.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's dance moves in the video are not continuous, there are sudden changes, and the cashier's arm suddenly disappears or appears in the middle frames."
}
] |
seed42_2902
|
videos/HRA_part0/2902.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinct black markings, is perched on a concrete ledge. It has a full, rounded body and is situated in an urban environment, as indicated by the presence of a streetlight nearby. The bird's head is turned to the side, revealing its detailed eye and beak. Its wings are folded neatly against its body, and its legs, with their characteristic pinkish hue, grip the ledge firmly. The setting is an everyday city scene, with the pigeon appearing comfortable and unperturbed in its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the pigeon's claws in the video has issues."
}
] |
seed46_1333
|
videos/HRA_part2/1333.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lively brown and white dog bounds through the shallow waters of a serene lake at sunset, its fur glistening with droplets. It shakes vigorously, sending water flying in a sparkling mist, while standing on the sandy shore. Against the backdrop of a tranquil lake and a stunning sunset, the energetic canine leaps into the air, capturing the essence of joy and freedom. As it lands, it shakes again, creating a captivating spray against the golden hour light, highlighting every droplet in the air. Throughout, the dog wears a red collar, adding a pop of color against the natural hues of the landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_303
|
videos/HRA_part2/303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, open ocean scene where sunlight filters through the water's surface, illuminating a majestic manta ray as it glides effortlessly through the clear blue depths. The manta ray, with its impressive wingspan, showcases its graceful movements, framed against the vibrant coral reef below. Its dark dorsal side contrasts sharply with the lighter underbelly, creating a stunning visual as it maneuvers with fluidity. Nearby, smaller fish swim alongside the manta ray, highlighting the peaceful coexistence in the underwater ecosystem. The scene is serene and captivating, offering a rare glimpse into the beauty of marine life.]"
},
{
"from": "gpt",
"value": "Normal. The small fish mentioned in the caption did not appear in the video."
}
] |
seed46_2088
|
videos/HRA_part2/2088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, snow-covered landscape, a group of people in winter gear are seen interacting with a herd of majestic bison. The individuals are wiping snow off the bison's fur, showing care and connection with the animals. Their faces, wrapped warmly in scarves and hats, express determination and compassion. The bison, with their powerful statures and shaggy coats, stand calmly, accepting the attention. The scene is framed by the serene beauty of nature, with snowflakes gently falling and the distant silhouette of trees providing a peaceful backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2656
|
videos/HRA_part1/2656.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green shirt and beige cargo pants, stands on set with a megaphone in hand, coordinating the action. Nearby, a majestic tiger leaps gracefully over a log, its muscles rippling and eyes intense, demonstrating the power and agility of the big cat. The scene is set in a lush, verdant forest, with sunlight filtering through the leaves, creating a dramatic interplay of light and shadow. The director's focused gaze and the tiger's dynamic leap are captured in high definition, highlighting the intensity and precision required for filming such a scene.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the tiger jumping over a fallen log, but the movement is not very continuous and smooth, showing some lack of coordination."
}
] |
seed44_2759
|
videos/HRA_part1/2759.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, a mustache, and glasses sits against a white wall, intently sewing a button onto a piece of fabric with a red thread. He wears a gray shirt, and the focus is on his hands, which hold the needle and thread with precision. His facial expression is concentrated, and he occasionally looks up, offering a slight smile. Throughout, he continues his task diligently, the red thread weaving in and out of the button holes, securing it firmly to the fabric. The simplicity of the setting allows the viewer to fully appreciate the man's skill and attention to detail in this everyday task.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and the needle and thread in his hand are generated incorrectly."
}
] |
seed46_2764
|
videos/HRA_part2/2764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lone penguin stands majestically on a frosty, ice-covered shore, its sleek black and white feathers glistening under the soft, diffused light of an overcast sky. The penguin, with its round body, small flippers, and distinctive tuxedo-like appearance, looks out to the vast, icy sea, creating a sense of solitude and resilience in the harsh Antarctic environment. The scene is framed by rugged, snow-capped mountains in the distance, emphasizing the penguin's natural habitat and the stark beauty of its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1553
|
videos/HRA_part2/1553.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male bassist passionately plays a sleek, black upright bass, his eyes closed in concentration, against a dark stage background. He wears a black turtleneck sweater and jeans, exuding confidence and skill. His right hand expertly plucks the strings while his left hand positions the notes on the fingerboard. The bass, adorned with white fret markers, resonates with each stroke, creating deep, rich tones. The musician's dedication and the instrument's elegance are highlighted under the dim stage lights, captivating the audience with the bass's powerful sound.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1854
|
videos/HRA_part1/1854.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a brown leather jacket and jeans, walks alongside a cheetah in a natural savanna setting, both figures dwarfed by the vast, open landscape. The writer, wearing a beige hat, sunglasses, and holding a pen and notebook, looks thoughtful as they stroll together. The cheetah, sporting a tracking collar, walks parallel to the writer, its gaze forward, reflecting a sense of purpose and freedom. Together, they traverse the grassy terrain, the writer occasionally jotting down notes, while the cheetah remains vigilant, embodying the spirit of the wild.]"
},
{
"from": "gpt",
"value": "Bad. The person's legs are slightly deformed, and the hand holding the pen is detached from the body."
}
] |
seed46_2144
|
videos/HRA_part2/2144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a helmet, stands in an open field, engaging in a whimsical dance with a kangaroo. Both figures are silhouetted against a vibrant orange sunset, suggesting a surreal and unexpected partnership. The firefighter's movements are energetic and joyful, while the kangaroo, standing on its hind legs, appears to mimic the dance steps, adding a touch of humor and surprise to the scene. Throughout the dance, the firefighter's gear and the kangaroo's natural stance create a dynamic interplay of form and motion, set against the dramatic backdrop of the fading light.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_202
|
videos/HRA_part0/202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room with a soft, ambient glow, two young children, a girl and a boy, sit cross-legged on a patterned rug, their eyes wide with wonder and attention. The girl, wearing a yellow dress, leans forward slightly, her hands resting on her thighs, while the boy, dressed in a blue t-shirt and shorts, holds a toy car in one hand, both engrossed in listening to a story being told by an unseen narrator. The camera captures the children from a low angle, highlighting their expressions of rapt attention and the slight tilt of their heads, indicating their deep engagement with the tale unfolding before them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2754
|
videos/HRA_part1/2754.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man sits at a desk, bathed in the glow of a computer screen in a dimly lit room, his fingers poised above a black keyboard. He blinks slowly, revealing tired eyes beneath furrowed brows, hinting at the depth of concentration required for his writing task. Dressed in a white shirt with rolled-up sleeves, he exudes determination and focus, his gaze fixed on the screen as if willing the words to appear. The quiet intensity of the scene is punctuated by the soft clack of keys as he types, emphasizing the solitary nature of the creative process.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video types basically normally, but there is slight uncoordination in his movements."
}
] |
seed44_1447
|
videos/HRA_part1/1447.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ghost shrimp, nearly transparent with a slight gray tint, clings to the side of an aquarium, showcasing its delicate, see-through body and intricate internal structures. It hovers near a piece of driftwood, its multi-segmented legs and antennae visible as it interacts with its environment. The shrimp's eyes, dark and prominent against its translucent body, stand out as it explores its surroundings, highlighting its unique adaptation to freshwater habitats. Against the green backdrop of aquatic plants, the ghost shrimp's ethereal presence is captivating, offering a close-up view of its otherworldly form.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2006
|
videos/HRA_part0/2006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, reminiscent of Chris Evans, is seen in a minimalist living room with white walls and wooden floors, assembling a piece of furniture. He wears a fitted gray T-shirt, dark jeans, and a watch, his short hair perfectly styled. The room is sparsely decorated, featuring a potted plant and a small painting on the wall. The furniture he's building is a sleek, modern design, and he uses a variety of tools, including a screwdriver and an Allen wrench, demonstrating his handyman skills with ease and confidence.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the male actor using tools to repair and assemble furniture, but the movements are not continuous and smooth, and there is a lack of coordination."
}
] |
seed46_1753
|
videos/HRA_part2/1753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attorney, wearing a dark suit and carrying a briefcase, walks through a desolate industrial park at dusk, under the glow of orange streetlights. He pauses to gently touch the rough surface of a concrete wall, his expression thoughtful. The scene shifts to show him seated on a bench, still in the industrial setting, now bathed in the blue hour light, as he caresses the worn wooden slats, deep in thought. Throughout, the juxtaposition of the lawyer's polished appearance against the gritty industrial backdrop highlights the unusual intimacy of his actions.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2060
|
videos/HRA_part2/2060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a stunning array of coral formations takes center stage. Hard corals in various shades of brown and orange create a textured landscape, while neon green and blue soft corals sway gently in the current. Brightly colored fish, such as yellow tangs and red snappers, dart in and out of the coral structures. The water above is crystal clear, allowing sunlight to filter down and illuminate the rich colors of the coral reef. In the distance, the silhouette of a large sea turtle can be seen gliding through the water, adding to the serene atmosphere of this underwater paradise.]"
},
{
"from": "gpt",
"value": "Normal. The red snapper is not generated in the video."
}
] |
seed44_1272
|
videos/HRA_part1/1272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lush subtropical wet forest, a striking red fox curiously approaches a musician seated on a moss-covered log. The artist, dressed in a green shirt and brown vest, gently wipes away sweat from their brow, momentarily pausing their harmonious tune played on a wooden flute. Sunbeams filter through the dense foliage overhead, casting a warm glow on the scene, as ferns and tall trees surround them, creating a serene and enchanting atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2241
|
videos/HRA_part0/2241.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a brown shirt and blue overalls, stands in a lush green field under a clear blue sky, smiling as he observes a rabbit. The rabbit, located near the center of the frame, leaps into the air with excitement, its hind legs propelling it forward in a graceful arc. The farmer's joyful expression and the rabbit's energetic jump create a heartwarming scene, capturing the simple pleasures of rural life. The setting is enhanced by the vibrant green grass and the warm sunlight, which bathes the scene in a golden glow.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's legs appear deformed and mutated when jumping, and its body also becomes distorted."
}
] |
seed42_1824
|
videos/HRA_part0/1824.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, adventurous ferret, wearing a red life jacket, gleefully swims in a clear blue pool, its paws energetically paddling as it looks around with curious eyes. The pool is surrounded by a lush garden filled with vibrant greenery and colorful flowers, creating a serene and idyllic setting. Sunlight filters through the leaves above, casting dappled shadows on the water's surface, highlighting the ferret's playful movements as it enjoys its aquatic adventure.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's face and paws in the video have generation issues."
}
] |
seed44_2261
|
videos/HRA_part1/2261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an array of colorful fish. The grouper, with its distinctive spotted pattern and wide, flat head, explores its surroundings with a slow, methodical motion. Its eyes, fixed on the camera, seem to convey intelligence and awareness. The water is crystal clear, allowing every detail of the grouper's body and the intricate ecosystem it inhabits to be visible. The scene is illuminated by natural sunlight filtering through the surface, casting dappled light on the sandy seabed and the marine life above.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2009
|
videos/HRA_part2/2009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an astrophysics laboratory filled with high-tech equipment and screens displaying cosmic data, a worker, wearing a white lab coat over a gray shirt and dark pants, dances energetically. Accompanying him is a live rabbit, hopping playfully nearby, seemingly unfazed by the unusual environment. The scientist's joyful movements contrast with the serious scientific surroundings, creating a whimsical and unexpected scene. Throughout, the lab remains brightly lit and organized, with the scientist and the rabbit sharing a moment of lightheartedness amidst the serious pursuit of knowledge.]"
},
{
"from": "gpt",
"value": "Bad. The man and the rabbit dancing in the video is very unsmooth, with uncoordinated movements."
}
] |
seed46_199
|
videos/HRA_part2/199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, young female nurse, wearing a white uniform with a stethoscope around her neck, gently caresses the head of a golden retriever dog lying on the grass in a lush, green park. The nurse, with her hair tied back in a bun, interacts tenderly with the dog, who looks up at her adoringly. In another scene, she sits on a park bench, continuing to pet the dog affectionately, with trees and foliage visible in the background. The bond between the nurse and the dog is evident as they share a peaceful moment together in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's actions of petting the dog in the video are basically normal, with slight awkwardness."
}
] |
seed46_2290
|
videos/HRA_part2/2290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a maroon hoodie and gray sweatpants, diligently wipes down a large, brown bison statue with a white cloth, showing care and attention to detail. The scene takes place on a grassy campus, with trees in the background, highlighting the unique connection between the student and the symbolic animal figure. The student's focused expression and the careful motion of wiping the bison's surface convey a sense of respect and tradition associated with university life.]"
},
{
"from": "gpt",
"value": "Bad. The student's hand and the statue's head in the video have generation issues."
}
] |
seed44_2469
|
videos/HRA_part1/2469.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, agile squirrel leaps from a branch of a tall tree, its bushy tail and tufted ears clearly visible as it propels itself through the air. The creature, with its reddish-brown fur and white underbelly, is captured mid-jump, displaying its natural agility against a backdrop of lush green foliage. Its limbs are spread wide, showcasing its muscular strength and grace as it navigates the forest canopy. The squirrel's sharp claws are extended, ready to grip onto its next perch, highlighting its readiness and adaptability in its woodland habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2343
|
videos/HRA_part2/2343.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit prairie dotted with green shrubs and patches of tall grass, a large bison is rolling on its back in the dirt, surrounded by a cloud of dust. The bison, with its shaggy, brown fur and majestic horns, is enjoying a dust bath, rubbing vigorously against the ground. The camera captures the bison's content face as it lies on its side, legs kicking playfully in the air, creating a plume of dust that envelops its body. This behavior, known as 'dusting,' helps the bison remove parasites and excess oil from its coat, showcasing the creature's natural habits in a captivating scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_306
|
videos/HRA_part0/306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, donning a white tank top, beige shorts, and brown leather sandals, assembles a wooden table in a bright room with large windows and a view of greenery outside. He starts by carefully examining the instructions, his brows furrowed in concentration. Next, he skillfully uses a screwdriver to attach the legs to the tabletop, showcasing his handyman abilities. Then, he wipes his forehead with the back of his hand, a small smile on his lips, indicating satisfaction in his progress. Finally, he stands back to admire the finished product, hands on hips, revealing the completed table in the well-lit space, surrounded by lush vegetation visible through the window.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_2666
|
videos/HRA_part1/2666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant forest setting, a mother beaver gently caresses her kits with her large, flat tail, while they sit cozily together on the riverbank. The kits, with their soft, brown fur, look up at her with adoration, as the mother's nurturing touch conveys love and protection. Surrounded by the vibrant greenery and tranquility of nature, this heartwarming scene captures the tender bond between a beaver mother and her offspring.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's large, flat tail is not shown in the video."
}
] |
seed46_1550
|
videos/HRA_part2/1550.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a gray crew neck shirt, khaki pants, and black shoes, is seen from above, loading a stainless steel dishwasher in a well-lit kitchen. The kitchen features white cabinets, a white refrigerator, and a gray countertop. The teacher, with short brown hair and glasses, carefully places dishes into the lower rack of the dishwasher. In another angle, the teacher, now wearing a gray shirt and dark pants, continues loading the dishwasher, placing a cup in the upper rack. The room is brightly lit, with white walls and ceiling, and the teacher's focused expression conveys a sense of routine and responsibility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1562
|
videos/HRA_part0/1562.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, clad in a spacesuit and helmet, walks through a futuristic space station, where advanced agricultural technology is used to cultivate crops in zero gravity. Accompanied by a friendly fox, who curiously observes the floating plants and high-tech equipment, the engineer tends to the verdant greenery, demonstrating the feasibility of farming in outer space. The pair moves through the well-lit, sterile environment, highlighting the potential for sustainable food production beyond Earth's atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2642
|
videos/HRA_part2/2642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small hamster, with its distinctively furry cheeks and nose, energetically runs inside a clear plastic exercise ball. It scampers across a room filled with everyday objects like furniture and potted plants, providing a unique perspective on a typical living space. The hamster's movement is fluid and rapid, highlighting its determination and playful nature as it explores its surroundings within the safety of the transparent sphere.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's paws are missing in the video, and the face and body generation is blurry."
}
] |
seed44_2691
|
videos/HRA_part1/2691.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow jumpsuit with a tool belt, crawls through the dimly lit, narrow maintenance corridor of a spaceship, preparing for a hyperspace jump. The ship's interior is filled with pipes and wires, and the engineer's headlamp illuminates the complex machinery around him. He checks various components, ensuring everything is secure before the critical maneuver, his face a mask of concentration under the harsh, industrial lighting of the engineering section.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1967
|
videos/HRA_part0/1967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 scene unfolds where an engineer, clad in a gray jumpsuit and helmet, meticulously studies blueprints near a full-sized mechanical rhinoceros. Suddenly, the engineer leaps onto the rhino's back as it begins to jump, creating an unexpected yet thrilling spectacle. The mechanical rhinoceros, constructed with intricate metalwork and advanced engineering, bounds across the landscape, while the fearless engineer holds on, embodying a harmonious blend of human ingenuity and mechanical prowess.]"
},
{
"from": "gpt",
"value": "Normal. The rhino's legs show deformities and mutations, and the engineer's hand also becomes deformed."
}
] |
seed44_1396
|
videos/HRA_part1/1396.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a red 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": "Bad. The character's body is distorted, the face is twisted, the arms are deformed, and the legs are contorted."
}
] |
seed44_1597
|
videos/HRA_part1/1597.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a yellow vest and gloves, stands at the edge of a vast landfill, the sprawling site of discarded waste stretching into the horizon under an overcast sky. The artist begins wiping the surface of a found object, revealing layers of rust and texture beneath the dirt, as trash and debris are scattered across the landfill in the background. Moments later, the artist continues wiping the object, now partially cleaned, revealing its industrial form against the bleak landscape of waste. Finally, the artist holds the fully wiped object, a reclaimed piece of art, against the stark backdrop of the landfill, the clouds hinting at a dramatic sky overhead.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1945
|
videos/HRA_part0/1945.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a brown tweed jacket, sits at a wooden desk adorned with books and a typewriter, gently caressing a small, docile cheetah resting its head on the desk. The writer, with a neatly trimmed beard, looks intently at the camera, while the cheetah, with a collar and a bell, remains calm and attentive. The scene captures the unlikely companionship between the intellectual and the wild animal, set against a backdrop of a study filled with bookshelves and framed pictures.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's body and limbs in the video are generated abnormally."
}
] |
seed44_1910
|
videos/HRA_part1/1910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, donning a yellow safety vest, orange hard hat, and blue jeans, sits on a wooden beam, holding a hammer in his right hand and resting his left elbow on his knee, against a backdrop of a partially built structure with blue skies visible through the gaps. Moments later, he takes a break, sitting on the same beam with his legs crossed, now holding a water bottle and looking directly at the camera. Then, he is shown sitting with his legs dangling, his right arm resting on a higher beam, and his left hand holding the hammer, with the half-constructed building and clear blue sky in the background. Lastly, he sits with his back straight, both hands on his knees, and a focused expression, still clad in his yellow vest, orange helmet, and denim pants, the unfinished building and open sky framing him.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1473
|
videos/HRA_part2/1473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches on a branch, its vibrant green feathers contrasting against a clear blue sky, before taking flight against a backdrop of lush greenery and distant mountains. It swoops down gracefully, its long, slender beak aimed at capturing prey. The bird then returns to the branch, where it proudly displays its catch, a honeybee, before consuming it. Throughout the scene, the bee-eater's striking plumage, featuring shades of green, blue, and brown, catches the eye against the serene landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1422
|
videos/HRA_part2/1422.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clean-shaven male chef with short brown hair waves energetically with his right hand, standing in front of a vibrant green wall adorned with a pattern of white dots. He wears a traditional white chef's uniform with a black necktie, and his left hand rests comfortably in his pocket. The chef's warm smile and engaging demeanor convey a sense of welcome and enthusiasm, perfect for a cooking show introduction or a restaurant greeting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2073
|
videos/HRA_part1/2073.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, a slender gazelle, marked by its distinctive tan coat and white underbelly, is shown crawling on the ground, its posture conveying a sense of caution or rest. The scene is framed by lush green grass and distant acacia trees, creating a tranquil yet alert atmosphere. The gazelle's delicate features and attentive ears are highlighted, capturing the essence of its cautious behavior in the wild. Against this serene backdrop, the animal's careful movements are emphasized, offering a unique perspective on the gazelle's survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth, and there are sudden changes in the limbs."
}
] |
seed44_2815
|
videos/HRA_part1/2815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier with short brown hair and glasses, wearing a gray T-shirt and black pants, is seen lifting a large box of soda cans with both hands from a shopping cart onto a checkout counter. The store is busy with customers and products, adding to the bustling atmosphere. Moments later, he lifts another box of similar size with ease, demonstrating his strength and efficiency. The action takes place under bright fluorescent lights, highlighting the cashier's focused expression and determination as he manages the physical demands of his job.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the male cashier lifting a large box of soda cans from the shopping cart, with actions that are not continuous and smooth, and there are abrupt changes."
}
] |
seed42_2990
|
videos/HRA_part0/2990.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red jacket and brown trousers, runs along the edge of a harbor, the water glistening under the bright sun. Accompanied by a large, energetic dog with a tan coat, they traverse the harbor perimeter, surrounded by lush greenery. The farmer, showing a sense of urgency, sprints with focused determination, while the dog bounds alongside, mirroring his pace. Together, they navigate the harbor's edge, the water's surface reflecting sunlight in sparkling patterns, creating a dynamic scene of movement and companionship.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's head generation is problematic, the hands and feet are generated blurry, and the dog's head generation is also problematic."
}
] |
seed46_1389
|
videos/HRA_part2/1389.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 compassionate nurse, clad in a blue uniform and wearing a stethoscope around her neck, leaps with exhilaration against a cosmic backdrop featuring an artist's impression of a recently discovered exoplanet. Simultaneously, a cobra, coiled and ready to strike, mimics the action of jumping, adding an unexpected element to the scene. Both figures, the nurse and the cobra, are captured mid-leap, their silhouettes outlined against the star-studded universe, creating a vivid contrast between human emotion and the raw power of nature, all set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_178
|
videos/HRA_part2/178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a dark suit, finds himself unexpectedly dancing with a chimpanzee in a whimsical scene. Both appear joyful and engaged, with the lawyer maintaining eye contact, smiling, and gesturing with his hands as if leading the dance. The chimpanzee, equally enthusiastic, mirrors the lawyer's movements, wearing a small hat tilted playfully to one side. They dance against a backdrop of a bustling city street, with pedestrians passing by in the background, adding a surreal touch to the urban setting. The lawyer's polished shoes and the chimpanzee's hat become focal points as they whirl around, creating a delightful contrast between professionalism and playfulness.]"
},
{
"from": "gpt",
"value": "Bad. The characters in the video have twisted bodies, faces, arms, legs, and hands; the chimpanzee also has a twisted body, face, arms, legs, and hands."
}
] |
seed42_1590
|
videos/HRA_part0/1590.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in a red shirt, black vest, and dark pants, stands on a dimly lit stage, pointing with his right hand. He wears a black beret and glasses, adding to his artistic flair. Behind him, a vibrant purple curtain complements the stage lights, which cast a warm glow on his face. His left hand rests on his hip, and he points emphatically with his right, engaging the audience in a dynamic performance. The background is blurred, emphasizing the musician's commanding presence as he points with passion and intensity.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, and the hands are twisted."
}
] |
seed42_1223
|
videos/HRA_part0/1223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet, sunlit forest, a young woman who resembles a cashier from a local store embarks on a hike, dressed in hiking gear that includes a green jacket, khaki pants, and brown boots. She pauses to look at something intriguing in the distance, her hiking backpack visible. Moments later, she is seen walking confidently along the trail, her attire and equipment suggesting a preparedness for the outdoors. Then, she stops to rest, leaning against a tree trunk, her hiking poles propped up beside her, conveying a sense of peaceful contemplation. Finally, she continues her journey, walking away from the camera, her figure framed by the lush greenery and dappled sunlight, embodying the spirit of adventure and nature.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks smoothly, but the movements are uncoordinated."
}
] |
seed44_1953
|
videos/HRA_part1/1953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, characterized by its small size and adorable appearance, ambles through a lush, green forest with geysers erupting majestically in the distance, creating a misty, dreamlike atmosphere. The koala, wearing a tiny backpack, explores its surroundings with curiosity, passing by ferns and moss-covered rocks. It occasionally pauses to look at the camera, as if sharing its adventure. The geysers, shooting water high into the air against a backdrop of rolling hills, add a dramatic element to the serene forest setting, all captured in stunning detail.]"
},
{
"from": "gpt",
"value": "Bad. The koala in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed44_2917
|
videos/HRA_part1/2917.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, fluffy hamster sits upright on its hind legs, engaging in a grooming session within its cozy cage. The hamster meticulously wipes its face with its front paws, demonstrating a natural behavior typical of these animals. Its movements are deliberate and focused, highlighting the creature's self-care routine in a habitat filled with soft bedding and a water bottle visible in the background. The hamster's fur is a mix of brown and white, adding to the visual appeal of the scene as it diligently cleans itself.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1634
|
videos/HRA_part2/1634.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny, curious brown mouse crawls across the center of a large, gleaming solar sail, set against the vast, dark expanse of space. The sail, illuminated by distant stars and a faint blue planet on the horizon, captures the sunlight, creating a play of light and shadow as the mouse explores its surface. The contrast between the small creature and the grandeur of the solar sail highlights the scale and wonder of space exploration.]"
},
{
"from": "gpt",
"value": "Bad. The mouse's movements are uncoordinated."
}
] |
seed46_1229
|
videos/HRA_part2/1229.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter wearing a classic black suit and white shirt is seen playfully leaping over a miniature, cartoonish giraffe mascot positioned in the middle of a vibrant, bustling restaurant. The mascot, with its signature long neck and polka-dotted pattern, stands out against the lively backdrop of tables, chairs, and happy diners. The waiter's leap is captured mid-air, adding a touch of surreal humor to the composition. Behind him, the restaurant's interior is filled with patrons enjoying their meals, unaware of the unusual event unfolding before them.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1594
|
videos/HRA_part1/1594.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green zoological park, a dedicated zookeeper clad in khaki shorts, a gray T-shirt, and a cap runs along a path lined with palm trees, demonstrating his commitment to fitness within the serene surroundings. The camera captures him passing by enclosures housing various animals, highlighting the unique setting of his workout. As he jogs, the peaceful atmosphere of the park is evident, with glimpses of giraffes, elephants, and monkeys in the background, creating a vivid contrast between human activity and the natural world.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the character running, and the character's movements are basically normal, with slight coordination issues in the limbs."
}
] |
seed46_1545
|
videos/HRA_part2/1545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray shirt and khaki pants is seen in a whimsical scene, holding a small mouse on a wheel that matches the color of his shirt. The wheel rotates rapidly as the man watches, his gaze fixed on the active rodent. The scene is set against a plain, white backdrop, with the man's casual attire and focused expression contrasting with the unusual sight of the mouse energetically running on the miniature wheel.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers were not generated in the video, and the mouse was generated blurry."
}
] |
seed46_1068
|
videos/HRA_part2/1068.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut engineer, clad in a white spacesuit with a NASA logo, embarks on a critical space rescue mission, crawling through narrow, illuminated corridors inside a damaged spacecraft. The engineer's gloved hands and boots equipped with magnetic soles are prominent as they navigate the confined space. The scene is set against the backdrop of the Earth and stars, visible through a small porthole, emphasizing the perilous nature of the mission. Throughout, the engineer's determination and focus are evident as they work diligently to repair the vital systems of the stranded spaceship.]"
},
{
"from": "gpt",
"value": "Normal. The character's legs and arms are distorted in the video."
}
] |
seed44_2291
|
videos/HRA_part1/2291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman, clad in an elaborate, flowing red dress, dances passionately under the moonlight in a desert landscape, with ancient ruins visible in the distance. A jackal, observing her from a safe distance, is intrigued by the captivating scene. The woman's movements are fluid and expressive, her dress swirling around her as she loses herself in the music that only she can hear. The jackal, sitting calmly, watches with fascination, its silhouette framed by the glow of the full moon, creating a mystical atmosphere in the vast, starlit desert.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1243
|
videos/HRA_part0/1243.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 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 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": "Good. No obvious problems."
}
] |
seed42_2706
|
videos/HRA_part0/2706.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male chef, donning a gray t-shirt beneath a clean white apron, expertly wields a large spoon and spatula as he stirs a sizzling pan on a commercial stove in a bustling kitchen. Amidst the steamy atmosphere, his focused eyes and neatly trimmed facial hair convey his dedication to culinary artistry. With a vibrant red bandana tied around his neck, he exhibits a unique flair while preparing a gourmet dish. The scene captures the essence of hard work and passion in the culinary world, as the chef's movements are fluid and purposeful, encapsulating the heart of the kitchen environment.]"
},
{
"from": "gpt",
"value": "Normal. The male chef's hand and the ladle in his hand are generated incorrectly in the video."
}
] |
seed44_1412
|
videos/HRA_part1/1412.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, male gorilla with a silverback lumbers through the dense undergrowth of a temperate deciduous forest, illuminated by dappled sunlight filtering through the leafy canopy above. The gorilla, clad in his natural silver fur, moves with purpose, navigating the rich ecosystem of tall oaks and maples. His powerful form is juxtaposed against the lush greenery, creating a captivating scene as he walks among the towering trees, showcasing the raw beauty of nature in these vibrant woodlands.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's movements in the video are not smooth and coordinated."
}
] |
seed42_1308
|
videos/HRA_part0/1308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patient teacher, wearing a brown jacket and khaki pants, stands in a rural classroom with wooden desks and a world map on the wall. She gently caresses a small deer that has wandered inside, creating a tender moment. The deer, with its large eyes and curious demeanor, stands calmly beside the teacher, who offers a comforting presence. Both the teacher and the deer are bathed in the warm, golden light filtering through the windows, adding to the serene atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands are distorted, the face is distorted, and the deer's face is distorted."
}
] |
seed46_1510
|
videos/HRA_part2/1510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, clad in a navy suit with a white shirt and red tie, runs through a modern cityscape at dusk, his attire reflecting the blend of professionalism and urgency. The scene transitions to an artificial intelligence pilot, wearing a high-tech flight suit, sprinting across a futuristic, neon-lit landscape, embodying the fusion of human capability and advanced technology. Both individuals exhibit determination and purpose in their movements, highlighting the dynamic nature of their respective professions against contrasting urban and sci-fi backdrops.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1577
|
videos/HRA_part2/1577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant classroom decorated with colorful posters and student artwork, a passionate teacher, wearing a dark green shirt and khaki pants, is seen in the act of catching a ball, demonstrating a physics lesson on motion and gravity. The students, seated at their desks, watch intently as the teacher, with a lively expression, skillfully catches the ball mid-air, illustrating the principles of force and motion in an engaging and interactive manner.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's movements in the video are not smooth and continuous."
}
] |
seed44_253
|
videos/HRA_part1/253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent peacock, resplendent in its vivid blue and green plumage, struts regally across a lush, verdant garden, the sunlight dappling its feathers in a mesmerizing play of light and shadow. Its proud head, adorned with a striking crest, swivels gracefully as it surveys its domain. Suddenly, the peacock spreads its spectacular tail, revealing an eye-popping display of iridescent ocelli that seem to shimmer with an otherworldly glow. The air is filled with the rich, earthy scents of the foliage surrounding the bird, adding depth to this enchanting scene.]"
},
{
"from": "gpt",
"value": "Normal. The peacock's face in the video is deformed."
}
] |
seed44_3142
|
videos/HRA_part1/3142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 otherworldly ecosystem on an alien planet, a unique creature resembling Earth's beaver crawls through a dense, bioluminescent forest. Its brown fur stands out against the vibrant, glowing flora. The beaver-like being navigates the intricate terrain, its flat tail dragging slightly, as it explores the mysterious landscape filled with towering, luminescent trees and strange, colorful plant life. This extraterrestrial environment, illuminated by an eerie yet beautiful light, provides a surreal setting for the beaver's curious journey.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1553
|
videos/HRA_part0/1553.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male bassist passionately plays a sleek, black upright bass, his eyes closed in concentration, against a dark stage background. He wears a black turtleneck sweater and jeans, exuding confidence and skill. His right hand expertly plucks the strings while his left hand positions the notes on the fingerboard. The bass, adorned with white fret markers, resonates with each stroke, creating deep, rich tones. The musician's dedication and the instrument's elegance are highlighted under the dim stage lights, captivating the audience with the bass's powerful sound.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate jeans."
}
] |
seed42_2983
|
videos/HRA_part0/2983.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hyena leaps gracefully over pipes and machinery in an industrial oil refinery, backlit by the golden glow of sunset. The animal, wild and untamed, seems momentarily suspended in mid-air above the cold, metallic structures. Its spotted coat contrasts starkly with the urban landscape, highlighting the unusual and unexpected nature of this scene. Despite the hard edges of the refinery, there's a sense of fluid motion as the hyena propels itself forward, embodying a blend of natural agility and industrial might.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_2035
|
videos/HRA_part0/2035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape, a large, hairy mammoth tenderly caresses a smaller mammoth with its trunk, creating a touching scene of familial affection. The larger mammoth, covered in thick, shaggy fur, gently touches the younger one, who stands beside it, also covered in a coat of dark, coarse hair. Both creatures possess impressive tusks, with the adult displaying a more formidable set. They are surrounded by green vegetation and tall trees, with a waterfall visible in the distance, contributing to the serene atmosphere of this ancient bonding moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2087
|
videos/HRA_part0/2087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prison, dimly lit by neon blue lights, two figures, a male and female inmate, plot their daring escape. They wear matching orange jumpsuits with black stripes, symbolizing their confined status. Suddenly, they engage in a synchronized dance, using their movement as a clever ruse to distract guards. Their dance, a blend of hip-hop and contemporary styles, captivates the robotic guards, allowing the inmates to stealthily make their way towards freedom. The prison's cold, metallic interior contrasts sharply with the dynamic energy of their dance, highlighting the tension between confinement and liberation. Throughout, the focus remains on the two dancers, their precise movements and the prison's stark, oppressive environment.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and twisted hands."
}
] |
seed42_2062
|
videos/HRA_part0/2062.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sparrowhawk soars majestically across a clear blue sky, its sharp eyes scanning the terrain below for any signs of movement. Its streamlined body, covered in a mottled brown and gray plumage, cuts through the air with effortless grace. The bird's hooked beak and powerful talons are on full display as it dives suddenly, plummeting towards the earth in pursuit of prey. In a burst of speed, it snatches a small rodent from the tall grass, its sharp claws closing around the struggling creature. The sparrowhawk then rises again into the heavens, carrying its prize back to its nest, a picture of strength and agility against the vastness of the sky.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3009
|
videos/HRA_part2/3009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a police officer, clad in a high-tech suit with neon accents, runs across a rugged asteroid surface illuminated by the distant stars. The officer, equipped with a helmet and breathing apparatus, sprints past mining equipment and industrial structures, indicating an asteroid mining operation. With each stride, the officer's suit glows under the harsh lighting of the asteroid's environment, highlighting the action and determination in this dynamic scene set against the backdrop of space exploration and law enforcement.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the police officer in the video are deformed, and the head is generated unreasonably."
}
] |
seed44_2880
|
videos/HRA_part1/2880.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a flowing white dress, interacts with a majestic lion in a surreal setting, emphasizing their connection. She crawls on a surface covered with lush green grass, facing the lion with a relaxed demeanor. The lion, also crawling, responds to her with curiosity, its golden eyes locked onto hers. Both the woman and the lion are framed by the vibrant greenery of their surroundings, highlighting the unusual yet peaceful encounter between human and beast.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are not smooth."
}
] |
seed46_2665
|
videos/HRA_part2/2665.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a futuristic spacesuit, gently caresses a small, feathered chicken on a Mars base camp, surrounded by high-tech equipment and monitors displaying scientific data. The young woman, with her hair tied back in a bun, looks down at the bird with a warm smile, providing a moment of tenderness in the stark, utilitarian environment. The base camp is illuminated by artificial lights, casting a soft glow on the scene, with the red Martian landscape visible through the transparent dome. The student's affectionate gesture towards the chicken offers a sense of comfort and connection in the otherwise alien setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_117
|
videos/HRA_part0/117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lark soars gracefully across a vast, cloud-dappled sky, its brown, speckled wings outstretched against a backdrop of vibrant blue. It dives down toward a sunlit, rolling meadow filled with lush grasses and wildflowers, then ascends again, singing its melodious song. Perched atop a swaying stalk of golden wheat, the bird's chestnut head tilts curiously, its bright eyes alert and alive with the spirit of dawn. Against the horizon, the silhouette of distant hills cradles the scene, completing the picturesque vision of nature's tranquility.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1738
|
videos/HRA_part1/1738.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest clearing illuminated by dappled sunlight, a man with short brown hair, wearing a blue shirt, khaki shorts, and brown shoes, stands facing a deer. The deer, with its head lowered, is a majestic eight-point stag. The man gently wipes something from the deer's face using a soft cloth, revealing a tender moment of human-animal interaction. The scene is peaceful, with the man's caring gesture toward the wild creature highlighting the connection between humans and nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_208
|
videos/HRA_part1/208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A beautifully detailed brown trout swims gracefully in a clear, bubbling stream, its speckled skin shimmering beneath the water's surface. The trout's intricate pattern of spots and slashes is vivid against the backdrop of smooth river stones and aquatic plants. Sunlight filters through the water, highlighting the fish's movements as it navigates the current with effortless ease, a true testament to its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2722
|
videos/HRA_part1/2722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green park under the bright summer sun, two happy children, a boy and a girl, are energetically chasing each other on the grass. The boy, wearing a red t-shirt and blue shorts, stretches out his hands, playfully trying to catch the girl. She, donned in a yellow dress and sandals, giggles as she skillfully dodges him, both enjoying the thrill of the chase. They run amidst a scattering of colorful wildflowers, their laughter echoing through the serene environment, encapsulating the joy and innocence of childhood.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2157
|
videos/HRA_part1/2157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vole, brown with white underparts, scurries along a paved path between two large apartment complexes, their exteriors a mix of brick and siding, under a partly cloudy sky. The rodent navigates the concrete walkway, dotted with cracks and weeds, passing by the base of the buildings where potted plants and bicycles are stored. It continues its journey undisturbed, weaving between the structures that tower above it, set against the backdrop of a suburban neighborhood with cars parked along the street and other apartment buildings visible in the distance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1429
|
videos/HRA_part1/1429.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white button-down shirt, black pants, and a black apron, walks down a busy city street. He gently caresses the side of a food truck, which is brightly lit and surrounded by eager customers. The scene is set during the golden hour, with the warm sunlight casting a glow on the bustling urban environment. The waiter's tender touch on the food truck contrasts with the lively atmosphere of the city, creating a unique and captivating moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1997
|
videos/HRA_part1/1997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged worker, clad in a tan vest, dark pants, and brown gloves, interacts with a realistic monkey puppet, crawling on all fours across a lush green landscape. The detailed puppet, featuring lifelike fur and expressive eyes, follows the worker's movements closely. The worker, with a serious yet focused demeanor, guides the monkey puppet through various natural terrains, including dense foliage and rocky terrain, highlighting the puppet's agility and realism. Throughout the scene, the worker's connection with the monkey puppet conveys a sense of companionship and shared purpose in their outdoor adventure.]"
},
{
"from": "gpt",
"value": "Normal. The monkey's movements in the video are not smooth."
}
] |
seed44_3067
|
videos/HRA_part1/3067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white rabbit with black markings sits upright on a checkered cloth, using its right paw to wipe its face, as if cleaning or grooming itself, against a simple gray backdrop. The bunny pauses mid-wipe, its paw still touching its face, offering a candid glimpse of its self-care routine. This intimate moment is captured in high detail, highlighting the rabbit's endearing behavior and the textural contrast between its fur and the patterned fabric beneath it.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit in the video is missing one ear, and the front limbs are generated with distortion."
}
] |
seed44_1931
|
videos/HRA_part1/1931.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [On a sandy beach under clear blue skies, three young children, two boys and a girl, wearing colorful swimsuits and sunglasses, jump gleefully into the air in slow motion. Their silhouettes are highlighted by the sun, casting playful shadows on the sand. They leap again, this time with the vast ocean as their backdrop, their laughter echoing in the warm coastal breeze. Their final jump is captured mid-air, faces full of joy and wonder, the sea gently lapping at the shore behind them, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Bad. The children's faces and limbs in the video are generated abnormally, with one child suddenly disappearing in the middle frame, and other children's faces and limbs showing varying degrees of distortion."
}
] |
seed44_261
|
videos/HRA_part1/261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, wearing a gray t-shirt and jeans, attentively waters lush green plants arranged in a neat row against a plain studio wall. He begins by pouring water from a green watering can onto the first plant, a potted ficus. Next, he moves to the second plant, a healthy monstera, continuing his task with care. Then, he focuses on the third plant, a vibrant snake plant, ensuring each receives adequate hydration. Lastly, he tends to the fourth plant, a thriving peace lily, completing the sequence with dedication, all within the simple yet functional confines of the studio space.]"
},
{
"from": "gpt",
"value": "Normal. The director's watering action can be clearly seen in the video; the action is basically normal but lacks coordination."
}
] |
seed44_2510
|
videos/HRA_part1/2510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with gray hair and glasses sits in a cozy room filled with bookshelves, natural light, and warm tones. He wears a blue shirt and a brown cardigan, appearing thoughtful and engrossed in a thick hardcover book. Moments later, he looks up from reading, revealing a pensive expression. He then turns the page, his eyes scanning the text intently, before pausing again to reflect on what he has read. Throughout the scene, he remains seated in the same position, his attire and surroundings unchanged, creating a calm and intellectual atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2012
|
videos/HRA_part1/2012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, presumably a writer, sits at a grand dining table, meticulously polishing silverware with a white cloth. He wears a dark blue blazer, a button-down shirt, and glasses, presenting a scholarly appearance. The room is dimly lit, with the only bright spot being the gleam from the silver as he works. The setting suggests a large, elegant dining hall, possibly in an old mansion, where the writer has taken on the unexpected task of preparing the cutlery. His focus and precision convey a sense of dedication to the task, contrasting with his intellectual pursuits.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1162
|
videos/HRA_part2/1162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dressed in a flowing, red, full-length dress dances gracefully in the desert landscape at golden hour, with the warm, glowing sunlight illuminating her figure. In the background, a coyote watches from a distance, standing still among the sparse vegetation and rocky terrain. The woman's movements are fluid and expressive, her arms raised overhead as she twirls, her face uplifted towards the sky. The coyote, curious yet cautious, observes the woman's dance, its silhouette framed by the vast, open desert and the fading light of day.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video dances very unsmoothly, with uncoordinated movements."
}
] |
seed44_1268
|
videos/HRA_part1/1268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a brown jacket, beige pants, and carrying a sketchbook, walks through a surreal landscape inspired by a galactic nebula. The sky is a vivid swirl of cosmic colors - deep purples, electric blues, and fiery oranges, evoking the ethereal beauty of distant galaxies. Giant, floating rock formations, tinged with the same nebulous hues, tower above, while the ground beneath his feet is a shimmering, star-lit plane that reflects the celestial spectacle overhead. Despite the otherworldly setting, the artist strides purposefully, his form and clothing sharply detailed against the dreamlike backdrop, as if he's on a mission to capture the universe's wonders on paper.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2130
|
videos/HRA_part2/2130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit office cluttered with books and papers, a distinguished lawyer, wearing a gray suit, sits pensively at his desk, his glasses perched on the tip of his nose as he scrutinizes documents. Unbeknownst to him, a tiny brown mouse crawls across the worn wooden surface of the desk, pausing to nibble on a crumb near a row of neatly arranged ink bottles. The lawyer's focus remains on his work, unaware of the small creature sharing his workspace, as the mouse continues its journey across the desk.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's action of checking the documents in the video is basically normal, but there is slight disharmony; the brown rat's movements of crawling and eating breadcrumbs are not continuous, with abrupt changes."
}
] |
seed46_1983
|
videos/HRA_part2/1983.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large brown bear, with its shaggy fur glistening in the sunlight, is seen swimming gracefully in a serene lake, surrounded by lush greenery and tall trees. Its powerful forearms propel it through the crystal-clear water, creating ripples that expand outward. The bear's alert eyes and nostrils are just above the waterline, showcasing its keen senses as it navigates the aquatic environment with ease. The peaceful setting, with the occasional splash and the gentle lapping of water against the shore, highlights the bear's natural ability to swim in its tranquil habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.