video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2790
|
videos/HRA_part1/2790.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and a helmet, walks alongside a majestic jaguar in a surreal scene. Both stride purposefully on a dirt path, the wild cat's spots contrasting with the firefighter's bright orange suit. The setting sun casts a golden glow, highlighting the unusual pair as they move together, the jaguar's powerful form and the firefighter's protective stance forming an unforgettable image. The firefighter's heavy boots and the jaguar's confident gait are in sync, creating a unique bond between human and beast in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's head, hands, and feet, as well as the jaguar's head and claws, are malformed in the video."
}
] |
seed42_2453
|
videos/HRA_part0/2453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly sunlit subtropical dry forest, a small, brownish-grey vole emerges from beneath the leaf litter, its fur blending seamlessly with the earthy tones of its surroundings. It pauses, nose twitching, before taking cautious steps forward, navigating the intricate network of twigs and leaves that carpet the forest floor. The vole's round ears and curious eyes are sharply focused, scanning the environment for both threats and opportunities as it walks through this arid woodland habitat, the sunlight filtering through the sparse canopy above.]"
},
{
"from": "gpt",
"value": "Normal. The mouse's legs appear deformed."
}
] |
seed42_1898
|
videos/HRA_part0/1898.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a straw hat and blue overalls, is seen playfully splashing water at a curious jackal on the banks of a serene lake during golden hour. The farmer then dives into the water, swimming with ease, while the jackal cautiously wades in, its ears perked up and attentive. They engage in a lighthearted game, the farmer swimming and the jackal paddling near the shore, both enjoying the cool waters under the warm, golden glow of the setting sun.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1983
|
videos/HRA_part0/1983.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large brown 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 problems."
}
] |
seed44_1286
|
videos/HRA_part1/1286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artist in a gray jacket, black shirt, and brown pants stands before a large, unfinished painting of a space elevator, his right hand gently caressing the canvas as if feeling the texture of the depicted structure. His left hand rests on his hip, and he looks down at the artwork with a slight smile, conveying a sense of pride and connection to his creation. The studio is dimly lit, casting dramatic shadows across the room and highlighting the artist's interaction with the painting, which features the towering space elevator reaching towards the stars.]"
},
{
"from": "gpt",
"value": "Bad. The character's fingers are deformed, and the face is slightly distorted."
}
] |
seed46_1852
|
videos/HRA_part2/1852.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, with a casual hairstyle and wearing a dark green jacket over a gray t-shirt, leans against a white wall with a wooden panel. She holds a book titled \"The Great Gatsby\" by F. Scott Fitzgerald, reading it intently during a break. The scene is set in a grocery store aisle, with shelves stocked with products like canned goods and boxes of cereal visible in the background. The cashier's relaxed posture and focused gaze on the classic novel convey a sense of peace and personal time amidst her work environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2520
|
videos/HRA_part1/2520.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny vole, brown in color, scurries through a miniature world set against the backdrop of towering skyscrapers, their glass facades reflecting sunlight. The vole runs across a small wooden bridge, navigating its way through a lush green park nestled within the urban jungle. It then darts under a miniature Eiffel Tower, a playful nod to global landmarks, before disappearing into the safety of a hollow log, all while the cityscape looms large and impressive in the background.]"
},
{
"from": "gpt",
"value": "Bad. The juvenile field mouse in the video has a twisted body, head, feet, and legs."
}
] |
seed46_2822
|
videos/HRA_part2/2822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stands in a spacious, modern gymnasium, surrounded by basketball hoops. He wears a gray jacket with a yellow reflective strip and a name tag, paired with khaki pants and black shoes. Holding a large, professional camera, he focuses on capturing images of the facility. The scene is illuminated by bright overhead lights, highlighting the clean, well-maintained space. The janitor's posture and attire convey a sense of pride and responsibility in his role, as he ensures the gym remains in pristine condition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2720
|
videos/HRA_part2/2720.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male doctor, wearing a white lab coat over casual attire, skillfully prepares dinner in a modern kitchen with stainless steel appliances and granite countertops. He expertly chops vegetables on a wooden cutting board, using a sharp chef's knife, while a pot simmers on the stove, releasing aromatic steam. The kitchen is illuminated by soft overhead lights, casting a warm glow over the scene. Behind him, a large window displays an urban skyline at twilight, adding a touch of sophistication to the domestic setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1454
|
videos/HRA_part2/1454.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 khaki safari outfit, complete with a wide-brimmed hat, kneels in a lush, green environment, closely observing a large hippopotamus. The director's intense focus and proximity to the wild animal emphasize the unique and potentially dangerous nature of the scene. The hippopotamus, with its massive body and distinctive features, slowly crawls through the tall grass, creating a sense of movement and life in the otherwise still landscape. The director's presence adds a narrative element, suggesting a story unfolding between human curiosity and the untamed wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The hippo's movements in the video are not smooth and coordinated."
}
] |
seed44_2857
|
videos/HRA_part1/2857.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant flamingo stands tall and proud on a sandy shore, its pink feathers glowing under the golden rays of the setting sun. Its long, slender legs elegantly support its body as it gazes out over the calm waters, creating a serene and picturesque scene. The flamingo's curved neck gracefully bends, while its beak rests gently on its chest, exuding a sense of tranquility and contentment. Surrounding palm trees sway gently in the breeze, adding to the idyllic atmosphere of this stunning coastal landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1019
|
videos/HRA_part0/1019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly contrasting scene, a middle-aged, bespectacled teacher wearing a gray jacket, blue shirt, and khaki pants runs alongside a majestic, wild panther, both moving at full speed across a lush green field under a bright blue sky. The teacher, with short brown hair and a look of intense focus, matches strides with the powerful feline, its sleek black fur rippling in the wind as it sprints effortlessly beside him. The unlikely pair cuts through the vibrant grassland, the teacher's clothing billowing slightly from the momentum, creating an extraordinary and dynamic image of an educator and a panther in motion together.]"
},
{
"from": "gpt",
"value": "Bad. Both the character and the black panther appeared deformed, and the facial expressions were not generated."
}
] |
seed46_1188
|
videos/HRA_part2/1188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a standard uniform with a badge and a hat, sits in a well-lit room with white walls. He nods slowly and deliberately in response to something off-screen, his serious demeanor and attentive body language conveying a sense of authority and engagement. The clean, organized setting and the officer's focused gaze suggest a formal environment, possibly an office or an interrogation room, where he listens intently to another person, nodding to show understanding and agreement.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2727
|
videos/HRA_part1/2727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin leaps from the crystal-clear ocean waters, its streamlined body glistening in the sunlight. The vibrant blue and silver hues of its scales contrast beautifully against the turquoise backdrop. In another scene, the marlin swims gracefully beneath the surface, its elongated bill leading the way as it navigates the underwater world. Surrounded by schools of smaller fish and the lush marine environment, the marlin embodies the power and elegance of life beneath the waves.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate the long beak of the sailfish, and the sailfish overall does not match reality."
}
] |
seed44_1859
|
videos/HRA_part1/1859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer kneels on a grassy park area, attentively watching a squirrel. The squirrel, emboldened, leaps from the ground onto the officer's outstretched arm, seeking a nut held in the officer's other hand. The cop wears a standard police uniform, including a navy blue shirt, black tactical pants, and a badge, while the greenery and trees in the background set a peaceful outdoor scene. The squirrel's acrobatic leap and the officer's gentle interaction create a heartwarming moment in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's hands and legs, as well as the squirrel, are generated abnormally in the video; during the middle frame of the squirrel's jump, the squirrel suddenly has an extra tail."
}
] |
seed44_3149
|
videos/HRA_part1/3149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical animated scene, a small, adventurous mouse dons a director's cap and carries a clapperboard, energetically guiding the action within a vibrant space casino. The setting is filled with neon lights, futuristic slot machines, and alien creatures gambling. Our rodent director, wearing a tiny suit and tie, races through the bustling casino floor, dodging patrons and games of chance, all while maintaining control over the film production taking place in this extraordinary intergalactic entertainment hub.]"
},
{
"from": "gpt",
"value": "Bad. The running action of the little mouse is not smooth."
}
] |
seed42_2883
|
videos/HRA_part0/2883.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene unfolds as a talented musician, clad in a red fox-themed costume, plays a golden saxophone under the neon lights of a bustling city street. The fox's expressive face, complete with whiskers and gleaming eyes, comes alive as it dances energetically, captivating the crowd with its infectious rhythm. Surrounded by urban graffiti and the glow of city lights, the fox's movements are fluid and dynamic, its tail swaying in time with the music. The atmosphere is electric, with onlookers swaying to the beat, all drawn into the enchanting performance of this unique fox-musician.]"
},
{
"from": "gpt",
"value": "Bad. The musician wearing the fox costume has unsmooth movements in the video."
}
] |
seed46_284
|
videos/HRA_part2/284.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a lab coat over a collared shirt and khaki pants, gently caresses a hamster in a zero-gravity environment, suggesting space agriculture. The doctor, with neatly trimmed facial hair and spectacles, holds the hamster with care and attentiveness, floating effortlessly in a spaceship's cabin. The hamster, nestled in the palm of the doctor's hand, appears relaxed and comfortable, indicating a nurturing bond between the two. In the background, hydroponic plants grow in LED-lit chambers, emphasizing the agricultural aspect of the scene. The doctor's focus on the hamster, combined with the futuristic setting, conveys a sense of compassion and innovation in space farming.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the doctor wearing khaki pants."
}
] |
seed46_3100
|
videos/HRA_part2/3100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 high-tech laboratory setting, a professional lawyer, dressed in a sharp navy suit, consults with a dedicated nanobot repair crew. The crew, clad in matching silver jumpsuits, works diligently on a complex control panel. One crew member uses a microfiber cloth to carefully wipe down a row of advanced machinery, ensuring every surface is spotless. The lawyer observes closely, occasionally pointing to specific components and engaging in animated discussions with the crew about the intricacies of the nanobot technology. The scene is lit by the soft glow of the lab equipment, creating a futuristic and professional atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2154
|
videos/HRA_part0/2154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charming hedgehog, adorned with a miniature top hat and a tiny pair of spectacles, pirouettes gracefully on a wooden floor, surrounded by a medley of autumn leaves. The scene is imbued with a warm, golden light, casting gentle shadows that sway in harmony with the hedgehog's dance. As the music swells, the hedgehog leaps into a joyful jig, its quills bouncing playfully with each step. In the final moments, the hedgehog pauses, bowing elegantly to an invisible audience, the leaves rustling softly in applause, all set against the backdrop of a rustic barn door.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2826
|
videos/HRA_part0/2826.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a kangaroo, dressed in a chef's hat and apron, is shown playfully hopping around a vibrant, modern restaurant kitchen filled with gleaming stainless steel appliances and colorful, contemporary decor. The kangaroo then takes a break from its culinary duties to enjoy a refreshing swim in an outdoor pool, surrounded by lush greenery and bright, sunny skies, creating a surreal and delightful blend of dining and leisure. After its swim, the kangaroo returns to the restaurant, where it is greeted by patrons sitting at tables, enjoying their meals in the stylish dining area, complete with large windows offering views of the beautiful landscape outside. Finally, the kangaroo is seen back in the kitchen, preparing a dish with precision and care, as if it were a true master chef, all while maintaining its playful and endearing demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's face is distorted, its body is twisted, and its paws are contorted."
}
] |
seed46_2447
|
videos/HRA_part2/2447.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a gorilla wearing an astronaut suit stands before a massive spaceship, its textured surface reflecting the alien landscape. The gorilla looks up at the ship with curiosity and determination, ready to embark on a journey through interstellar space. Suddenly, the scene changes to show the gorilla swimming underwater, its powerful arms propelling it forward through crystal clear water, surrounded by colorful fish and vibrant coral reefs. The contrast between the futuristic space travel and the natural beauty of the underwater world highlights the versatility and adaptability of this extraordinary creature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2988
|
videos/HRA_part2/2988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a slender gazelle, elegantly attired in a black apron and cap, diligently wipes down a wooden countertop with a green cloth. The setting is a quaint, rustic grocery store, filled with shelves of produce and goods. The gazelle, with its distinctive horns and graceful demeanor, performs the task with meticulous care, embodying an unexpected yet captivating scenario behind the register.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's head and arms are twisted in the video."
}
] |
seed44_1484
|
videos/HRA_part1/1484.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious, softly lit room with a neutral color palette, two children, a boy and a girl, both wearing pajamas, are seen playing together. The boy, wearing blue pajamas, crawls across the floor, while the girl, dressed in pink pajamas, manipulates a gravity control device, causing everyday objects to float around them. The floating items include a teddy bear, a toy car, and a book, creating a whimsical atmosphere. The children laugh and play among the floating objects, the girl adjusting the gravity device to move the items closer or further away, all within the cozy, safe environment of their playroom.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2354
|
videos/HRA_part2/2354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic juxtaposition, a rugged firefighter, clad in full gear and holding a fire hose, stands tall against a backdrop of scientific equipment and dark matter research posters. The scene shifts to focus on the firefighter gently caressing the side of a large, complex machine, symbolizing a tender connection between humanity and the pursuit of knowledge. The firefighter's protective clothing contrasts with the sterile environment of the research facility, creating a compelling visual narrative. Behind him, screens display data related to dark matter studies, emphasizing the unusual fusion of two vastly different worlds.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's walking is basically normal, but there is slight uncoordination in the movements."
}
] |
seed42_3044
|
videos/HRA_part0/3044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, donning a clean white uniform and a traditional toque blanche hat, sits at a modern, sleek kitchen table. He is intently typing on a laptop, his fingers deftly moving across the keyboard, with the focus of someone accustomed to multitasking. The background is a bustling commercial kitchen, filled with stainless steel appliances and busy staff working in harmony. Despite the chaos around him, the chef remains composed and focused on his task, exemplifying the blend of professionalism and culinary expertise.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3090
|
videos/HRA_part0/3090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged-looking man in a gray shirt and blue jeans is crawling on his hands and knees under a wooden deck in a backyard, fixing something. Suddenly, a moose appears in the frame, standing majestically behind the deck, curious about the activity. The worker, unaware of the unexpected visitor, continues his task diligently, his back arched as he focuses on the repair work, while the large, wild animal watches him from a distance, creating an unusual juxtaposition of urban labor and wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1016
|
videos/HRA_part0/1016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, wearing a yellow life jacket and a helmet, is seen swimming alongside a moose in a large, clear lake. Both are in the middle of the water body, surrounded by vast expanses of water. The woman, with her dark brown hair visible, looks up at the moose, which is also swimming, its head held high above the water. The moose, with its distinctive antlers, swims parallel to her, both seemingly enjoying the cool waters. Behind them, a lush forest with tall green trees stretches to the horizon, providing a serene and picturesque backdrop to this unusual scene of a woman and a moose swimming together.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1967
|
videos/HRA_part1/1967.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 rhinoceros's legs show deformities and mutations, and the engineer's hands and arms also undergo deformities, with mutations appearing in the legs."
}
] |
seed42_205
|
videos/HRA_part0/205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A renowned actor, wearing a brown costume resembling a moose, dances gleefully in a large, empty studio with high ceilings and exposed pipes. The overhead lights cast a warm glow on the wooden floor, highlighting the actor's animated expressions and exaggerated movements. The studio walls are adorned with abstract paintings and vintage movie posters, adding a whimsical touch to the scene. As the actor continues to dance, their enthusiasm is contagious, bringing a sense of joy and playfulness to the space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1300
|
videos/HRA_part2/1300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and beige pants, paints a vivid mural featuring a gorilla on a brick wall, surrounded by lush greenery. The gorilla, depicted in motion, seems to be running across the artwork, blending seamlessly with the real-world setting. The artist's focused gaze and deft brushstrokes capture the essence of movement and life, merging the realms of art and nature in a captivating scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1557
|
videos/HRA_part1/1557.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow fire-resistant jacket, gently caresses a small meerkat standing on its hind legs. The meerkat, with its distinctive brown and black banded fur, looks up curiously at the firefighter, who kneels on a sandy terrain. Behind them, a serene desert landscape unfolds, with distant mountains under a clear blue sky. The firefighter's protective gear and the meerkat's natural habitat form an unlikely yet touching tableau of connection between a human and wildlife.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3162
|
videos/HRA_part0/3162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene unfolds where a musician, clad in a leopard-print jacket and dark sunglasses, passionately plays a saxophone under a spotlight. Nearby, a cheetah with a golden collar and bell, standing on its hind legs, dances gracefully to the music. The setting is a stage decorated with colorful neon lights, creating an electrifying atmosphere as the audience watches in awe. The musician's performance is captivating, and the cheetah's movements are fluid and expressive, both in perfect harmony with the upbeat jazz melody.]"
},
{
"from": "gpt",
"value": "Normal. The musician's saxophone playing actions are basically normal, with slight disharmony; the cheetah stands on its hind legs and dances elegantly to the music, but the movements are very discontinuous and there are abrupt changes."
}
] |
seed44_3060
|
videos/HRA_part1/3060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, wearing a white tank top, blue jeans, and black sneakers, meticulously cleans a car using a sponge and bucket filled with soapy water, under a clear blue sky. He begins by pouring water from a green hose nozzle onto the vehicle, the bubbles catching the sunlight. Next, he uses a sponge to scrub the car's hood, his focused gaze and dedicated posture conveying his commitment to the task. Then, he rinses the suds away with the hose, revealing the car's now gleaming surface. Lastly, he wipes down the clean car door with a cloth, the contrast between the dirty rag and the shiny paintwork highlighting the effectiveness of his efforts.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1693
|
videos/HRA_part1/1693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful red fox, standing on its hind legs in a grassy meadow under a twilight sky, wears a green bow tie and a brown top hat, adding a whimsical touch to the scene. It dances energetically, with the focus on its expressive face, showing pure joy and playfulness. The fox continues to dance, now surrounded by a group of admiring woodland creatures, including rabbits, squirrels, and birds, all watching in delight from the edge of a dense forest. The fox performs a final dance move, leaping into the air with its front paws raised, against the backdrop of the setting sun, casting a warm golden glow over the entire meadow.]"
},
{
"from": "gpt",
"value": "Bad. The red fox undergoes a mutation, resulting in physical deformities."
}
] |
seed46_2018
|
videos/HRA_part2/2018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a leopard print scarf, sits in a dimly lit room, engaged in caressing a small, furry creature. Behind her, a screen displays complex diagrams related to quantum entanglement experiments, adding a layer of intrigue. Her attire, which includes the eye-catching leopard print accessory, contrasts with the scientific theme of the scene. The focus is on her gentle interaction with the creature, while the backdrop hints at her intellectual pursuits, creating a compelling juxtaposition between the personal and professional aspects of her life.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, and there are sudden changes."
}
] |
seed44_1567
|
videos/HRA_part1/1567.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 garden filled with vibrant flowers and greenery, two young children, a boy and a girl, are happily engaged in gardening activities under a clear blue sky. The boy, wearing a red shirt and khaki shorts, attentively waters plants with a small watering can, while the girl, clad in a pink dress and white shoes, diligently digs soil using a tiny shovel. They both wear wide-brimmed hats to shield them from the sun. Nearby, a wooden bench sits beside a stone walkway, and a white picket fence surrounds the garden, completing the idyllic scene of youthful enthusiasm and nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1529
|
videos/HRA_part2/1529.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A costumed dancer, clad in a spacesuit with a weasel mascot head, performs an energetic dance routine on a stage designed to resemble the lunar surface, complete with craters and rocks. The backdrop displays a large, realistic moon, adding to the illusion. The performer's movements are lively and expressive, capturing the essence of joyful celebration against the stark, textured lunar landscape. The spacesuit features reflective patches that catch the stage lights, enhancing the visual spectacle, while the weasel mascot head adds a whimsical touch to the performance.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the face is distorted, and the legs are deformed."
}
] |
seed46_1485
|
videos/HRA_part2/1485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinguishable by his classic black vest and white button-down shirt, is shown shoveling snow with determination. His attire is uniquely juxtaposed with the wintry task at hand, as he clears a path in front of a charming, snow-covered cottage. Snowflakes gently fall from a cloudy sky, accumulating on the roof and surrounding trees, while the waiter, wearing black gloves and sensible shoes for traction, focuses on his unexpected duty. Despite the cold, he works diligently, the snow creating a picturesque setting that contrasts with his formal waiter's uniform.]"
},
{
"from": "gpt",
"value": "Bad. The server's movements in the video are not smooth and are uncoordinated."
}
] |
seed42_2948
|
videos/HRA_part0/2948.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray t-shirt and blue jeans is kneeling beside a large aquarium, meticulously cleaning the glass with a scrubbing tool, his focus unwavering. The room is softly lit, casting a warm glow over the scene. Behind him, a bookshelf filled with various items can be seen, adding a sense of home to the environment. As he works, his dedication is evident in the careful strokes of the brush against the glass, ensuring every inch of the tank is spotless for the aquatic life within.]"
},
{
"from": "gpt",
"value": "Normal. The man can be clearly seen using cleaning tools to wipe the glass in the video, his movements are basically normal but there is some lack of coordination."
}
] |
seed42_2200
|
videos/HRA_part0/2200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus with vibrant, mottled skin displays an array of colors, from rich reds to deep purples, against a dark, rocky reef background. It extends several of its long, muscular arms outward, revealing intricate patterns and textures as it interacts with its environment. One arm curls around a piece of coral, showcasing the creature's dexterity and strength. Another arm reaches towards the camera, almost as if to touch, providing a captivating close-up view of its suckers and the mesmerizing play of light on its skin. The octopus then retreats slightly, enveloping itself partially within a crevice, demonstrating its natural camouflage abilities in the underwater world.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the tentacles wrapping around the coral and extending outward are somewhat unsmooth and uncoordinated."
}
] |
seed42_3210
|
videos/HRA_part0/3210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space setting, a renowned actor portrays a courageous character who masterminds a daring bank robbery on a distant planet. Dressed in a high-tech suit, the actor stealthily maneuvers through the alien bank, filled with luminescent crystals and advanced security systems. In a surprising twist, the actor gently caresses a small, friendly porcupine-like creature, which assists in the heist by using its quills to disable the security mechanisms. The scene combines elements of action, suspense, and unexpected tenderness in the vastness of outer space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2025
|
videos/HRA_part1/2025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a green jacket, blue jeans, and a gray cap, stands on a ladder propped against the side of a barn, which features a vibrant red exterior and white trim. He is engaged in cleaning the gutters, using a gloved hand to remove debris. The scene is set against a backdrop of lush greenery and a clear blue sky. Moments later, he pauses to survey his work, a pitchfork leaning against the barn wall beside him. The farmer then continues his task diligently, his attire and the pastoral setting creating a vivid image of rural life.]"
},
{
"from": "gpt",
"value": "Bad. No pitchfork was generated."
}
] |
seed46_1755
|
videos/HRA_part2/1755.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow safety vest and a hard hat, finds himself in a whimsical scenario where he's crawling on his hands and knees through a narrow, dimly lit tunnel. The setting is enhanced by the presence of a stuffed weasel toy, which has somehow joined him on this unusual journey, adding a touch of humor and unexpectedness to the scene. The engineer's serious expression contrasts with the playful atmosphere created by the stuffed animal, making for a unique and memorable visual.]"
},
{
"from": "gpt",
"value": "Bad. The crawling motion is not smooth, and the limbs seem somewhat uncoordinated."
}
] |
seed44_1163
|
videos/HRA_part1/1163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a vibrant, freshly-caught salmon, its skin shimmering with hues of silver and pink, glistens under bright lights. The fish, set against a dark, textured background, boasts a rich gradient of colors from deep red to pale orange on its flesh, which is artfully presented with a diagonal cut to reveal its succulent texture. Delicate wisps of smoke rise from the salmon, indicating its recent preparation, while a chef's hand, adorned with a simple wedding band, holds a sharp filleting knife nearby, ready to prepare this exquisite piece of seafood.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1224
|
videos/HRA_part1/1224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue uniform and a stethoscope around her neck, is delightedly interacting with a small gerbil in a cozy living room. The gerbil, perched on a tiny platform, suddenly leaps into the air, its action frozen in mid-jump, capturing a moment of playful exuberance. The nurse, with a warm smile, watches the gerbil's antics, her caring demeanor evident in her facial expression and body language. The scene is set against a backdrop of a homely living space, with a couch, coffee table, and various household items visible in the background, creating a sense of domestic tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's palm is deformed, the face is distorted, the hamster's claws are deformed, the head is deformed, and the legs are twisted."
}
] |
seed42_217
|
videos/HRA_part0/217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, clad in a dark blue jacket, black tactical pants, and a peaked cap, leaps over a wooden barrier on a heath, demonstrating agility and readiness. The heath is characterized by lush greenery, tall grass, and scattered trees. The officer's action conveys a sense of urgency and physical prowess, with the natural landscape providing a dynamic setting for the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1261
|
videos/HRA_part1/1261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, brown capybara swims through a clear, tranquil body of water, its ears and nose poking above the surface. It propels itself forward with powerful kicks from its webbed hind feet, showcasing its natural swimming abilities. The scene is set against a lush, green forest backdrop, highlighting the capybara's natural habitat. As it continues to swim, droplets of water scatter around it, creating a peaceful and captivating underwater perspective.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's movements in the video are basically normal, with slight coordination issues."
}
] |
seed42_1859
|
videos/HRA_part0/1859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 uniformed police officer kneels on a grassy park area, attentively watching a squirrel. The squirrel, emboldened, leaps from the ground onto the officer's outstretched arm, seeking a nut held in the officer's other hand. The cop wears a standard police uniform, including a navy blue shirt, black tactical pants, and a badge, while the greenery and trees in the background set a peaceful outdoor scene. The squirrel's acrobatic leap and the officer's gentle interaction create a heartwarming moment in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's jumping motion in the video is not smooth and continuous, with sudden changes in limb positions between frames."
}
] |
seed42_25
|
videos/HRA_part0/25.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly capybara, adorned with a miniature nurse's hat and a stethoscope around its neck, crawls across a colorful, childlike set filled with oversized medical-themed toys. The capybara moves deliberately, as if performing a check-up on a giant teddy bear patient lying on a playful examination table, surrounded by an array of oversized bandages, cotton balls, and a smiling face thermometer, creating a heartwarming and imaginative playtime scenario.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's head and paws, as well as the teddy bear's face, have generation issues in the video."
}
] |
seed42_171
|
videos/HRA_part0/171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ferret, wearing a miniature red scarf around its neck, is seen playfully dancing on a wooden floor in a rustic cabin. The creature twirls and leaps energetically to an unseen melody, its movements capturing the pure joy of dance. The natural light from a nearby window illuminates the scene, casting warm shadows across the room, highlighting the ferret's agile form as it continues its impromptu performance.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2804
|
videos/HRA_part0/2804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 black tank top and dark jeans, mimics the agile movements of a mongoose, sprinting across a lush, verdant landscape. His intense gaze and athletic build convey strength and determination as he leaps over obstacles, embodying the spirit of the nimble creature. The scenery features vibrant greenery and a clear blue sky, providing a vivid contrast to his swift, mongoose-inspired running. Throughout the sequence, the actor maintains his focus and momentum, seamlessly integrating the mongoose's grace and speed into his performance.]"
},
{
"from": "gpt",
"value": "Normal. The man's facial features in the video are generated disproportionately, and his hands and feet are deformed."
}
] |
seed46_285
|
videos/HRA_part2/285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a gray long-sleeved shirt and khaki pants, is seen wiping down a hippopotamus with a large cloth. The scene takes place in a spacious, well-lit room with concrete walls and floor, resembling a zoo enclosure or animal care facility. The engineer, wearing safety glasses and a name badge, approaches the docile hippopotamus with a bucket of soapy water and a sponge, carefully cleaning its skin. The hippo, appearing calm and cooperative, stands in the middle of the room, surrounded by various tools and equipment typically found in an engineering workshop, creating an unusual yet intriguing juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2487
|
videos/HRA_part2/2487.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, intimate dining room, a sophisticated waiter, dressed in a crisp white shirt, black vest, and tie, tenderly caresses the smooth surface of a wine bottle, as if appreciating its craftsmanship. The scene is set with elegant table settings, fine china, and crystal glasses, creating an atmosphere of luxury. The waiter's hands, adorned with a simple silver ring, move gracefully over the bottle, highlighting his connection to the art of serving. Behind him, the glow of candlelight casts warm shadows on the walls, adding to the romantic ambiance of the restaurant.]"
},
{
"from": "gpt",
"value": "Bad. The server's hand is normally missing in the video, and the wine bottle is deformed."
}
] |
seed44_220
|
videos/HRA_part1/220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sun-drenched subtropical shrubland, a striking red fox gently caresses the foliage with its bushy tail as it moves gracefully through the sparse landscape. The fox, with its vibrant fur and alert demeanor, interacts tenderly with the arid environment, highlighting the delicate balance between predator and habitat. Against the backdrop of scrub vegetation and scattered trees, the fox's movements convey a sense of care and connection to the natural world.]"
},
{
"from": "gpt",
"value": "Normal. The limbs and face of the red fox in the video have generation issues."
}
] |
seed46_248
|
videos/HRA_part2/248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a majestic buffalo, with its shaggy brown fur and powerful stature, stands beneath the vibrant lights of an amusement park, visible through the trees. A carousel featuring colorful, whimsical animals spins in the background, adding to the surreal scene. Suddenly, the focus is on a young boy, perhaps five years old, wiping his hands on his jeans after enjoying a snack. Dressed in a red t-shirt and denim, he looks up with a smile, the Ferris wheel towering above him, encapsulating the essence of childhood joy and the unexpected combination of nature and entertainment.]"
},
{
"from": "gpt",
"value": "Normal. The boy's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1528
|
videos/HRA_part0/1528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hermit crab, adorned with a vibrant red and orange color palette, emerges from its seashell home on a sandy beach. The crab, showcasing its intricate, spiraled shell, scuttles across the sand, leaving a trail of tiny footprints. It pauses to explore its surroundings, its eyes on long stalks scanning the environment. Nearby, a group of similar hermit crabs gather, creating a social scene among the rocks and driftwood, all set against the backdrop of a serene, sunlit beach.]"
},
{
"from": "gpt",
"value": "Normal. The hermit crab in the video has too many legs, and the eyes are generated in the wrong position."
}
] |
seed42_2526
|
videos/HRA_part0/2526.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic giraffe, distinguished by its dark, jagged spots, gently caresses a smaller giraffe with its head, creating a tender moment in the midst of a lush, green savanna landscape. The taller giraffe, with a weathered face and long eyelashes, shows affection toward the younger one, which has lighter, less pronounced markings, standing against a backdrop of tall grasses and distant trees under a bright, sunny sky. This intimate scene captures the essence of giraffe behavior in their natural habitat, emphasizing the bond between two individuals against a vivid, verdant setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3207
|
videos/HRA_part1/3207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mongoose, recognized by its sandy brown fur, black-tipped tail, and alert demeanor, runs swiftly across a dry, grassy terrain under a clear blue sky. It bounds gracefully over small tufts of grass, its body elongating and contracting with each leap, showcasing its agility and speed. Its eyes are focused ahead, ears perked, and nose twitching, indicating high alertness as it navigates the open space. The mongoose's movement is fluid and purposeful, its feet barely touching the ground as it darts forward, leaving a slight cloud of dust in its wake.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2121
|
videos/HRA_part1/2121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, characterized by its golden-brown fur and tiny ears, energetically jumps across wooden dock planks by a serene lake, surrounded by lush greenery. The hamster's miniature size contrasts with the vast, natural setting, creating a whimsical scene. Its movements are agile and lively, as it leaps from one dock plank to another, showcasing its playful spirit against the backdrop of a peaceful lakeside environment.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's limbs are missing in the video, and there is an issue with the mouth generation."
}
] |
seed46_300
|
videos/HRA_part2/300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic brown horse gallops across a lush, green meadow under a clear blue sky, its muscular body rippling with each powerful stride. The horse's mane and tail flow dramatically in the wind, creating a sense of speed and freedom. A pair of vibrant yellow flowers appear briefly in the foreground, adding a pop of color to the scene. The horse continues its run, hooves kicking up small clumps of earth, highlighting its strength and grace as it moves through the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Normal. The horse's movements in the video are slightly unsmooth."
}
] |
seed46_1242
|
videos/HRA_part2/1242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a waiter wearing a green apron and carrying a tray with refreshments walks through a temperate rainforest. Surrounded by lush greenery, moss-covered trees, and ferns, he moves along a narrow path. The environment is enhanced by the presence of a large tree trunk, its roots exposed, and the sound of a nearby waterfall. Sunlight filters through the dense foliage, casting dappled light on the forest floor, creating a magical atmosphere as the waiter continues his journey.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not coordinated."
}
] |
seed44_1625
|
videos/HRA_part1/1625.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 focused maintenance worker, clad in a dark green jacket over a gray shirt, blue jeans, and brown work boots, kneels on the floor of a clean, organized industrial space. He is attentively replacing batteries in a complex piece of machinery, demonstrating his expertise and care. The scene is illuminated by bright overhead lights, highlighting his meticulous task. Behind him, shelves stocked with tools and equipment provide context for his work environment, emphasizing the importance of regular maintenance in a professional setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are not fully generated, facial features are missing, and the leg proportions are incorrect."
}
] |
seed44_3030
|
videos/HRA_part1/3030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a human-like jackal, dressed in a red apron and name tag, stands behind a checkout counter. The background features a vibrant, turquoise water surface, suggesting a swimming pool or body of water. The jackal, with its distinctive canine features and upright posture, interacts with customers, handling items scanned over a register. The setting is illuminated by bright, warm lighting, casting a glow on the turquoise water, which stretches out behind the cashier area, merging the indoor and outdoor environments in an unexpected juxtaposition.]"
},
{
"from": "gpt",
"value": "Bad. The product scanned on the cash register mentioned in the caption does not appear in the video."
}
] |
seed46_1340
|
videos/HRA_part2/1340.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, known for his captivating performances, sits in a dimly lit room with wooden floors and walls adorned with musical instruments. He is sewing a button onto his burgundy velvet jacket, his fingers adorned with silver rings. His rugged appearance is highlighted by his scruffy beard and long, wavy hair. Behind him, a large window reveals the silhouette of a tree against a gray sky, adding a touch of melancholy to the scene. Despite the somber atmosphere, his focused gaze and the presence of a vintage microphone stand nearby suggest a sense of determination and passion for his craft.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1862
|
videos/HRA_part2/1862.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European brown hare sits upright on a grassy meadow under an overcast sky, performing a grooming behavior. It wipes its face with a paw, showcasing the natural habit of self-cleaning. The hare, with its distinctive long ears and brown fur, is shown in a close-up shot, emphasizing the details of its facial features and the texture of its fur. The background is blurred, focusing attention solely on the hare's grooming actions in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1829
|
videos/HRA_part1/1829.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, captivating squid floats in the deep sea, its body a mesmerizing blend of purples and pinks, illuminated by bioluminescent lights. The creature's eyes are large and expressive, conveying intelligence and curiosity. Its tentacles, adorned with suckers, gracefully undulate in the water, while its two feeding tentacles extend forward, ready to capture prey. The intricate patterns on its skin shift and change, creating an otherworldly display as it moves through the dark, mysterious depths of the ocean.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1501
|
videos/HRA_part1/1501.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a tan belt holding a radio and handcuffs, diligently repairs a damaged wooden fence in a suburban neighborhood. The fence, marred by graffiti and broken planks, is set against a clear blue sky. The officer, wearing a hat and sunglasses, demonstrates community involvement by hammering a new plank into place, emphasizing public service beyond traditional law enforcement duties.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the face is distorted, and the hand is twisted."
}
] |
seed44_1100
|
videos/HRA_part1/1100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 parallel universe setting, a firefighter, identifiable by his black helmet with a shiny badge, black uniform, and red suspenders, crawls on all fours through a desolate urban landscape. The cityscape features a large, gray building with broken windows and a dark, cloudy sky. The firefighter's movements are slow and deliberate, as if navigating through a hazardous environment. His gear includes a heavy-duty jacket, sturdy gloves, and a breathing apparatus strapped to his back, alluding to the dangerous conditions he faces. Despite the bleak surroundings, the firefighter's determination is evident in his focused gaze and resolute posture.]"
},
{
"from": "gpt",
"value": "Bad. The crawling motion can be seen, but the limbs are not coordinated and the movements are not fluid."
}
] |
seed44_1791
|
videos/HRA_part1/1791.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a navy blue shirt and beige trousers, gently caresses a buffalo in a rural setting. The buffalo, with its shaggy brown fur and large horns, stands calmly under a clear blue sky, with lush green grass and distant trees providing a peaceful backdrop. The engineer, showing a tender side, connects with the animal, which is often a symbol of strength and resilience, in a moment of quiet intimacy amidst the natural landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_215
|
videos/HRA_part0/215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a helmet, gently caresses a tiny, spiky hedgehog with a gloved hand, their eyes tenderly locked in a heartwarming connection. The scene is set against a backdrop of a partially extinguished fire, with billowing smoke and the remnants of flames, highlighting the contrast between the rough exterior of the firefighter and the delicate nature of the animal. The hedgehog, seemingly unharmed, nestles into the palm of the firefighter's hand, creating a poignant moment of compassion amidst the chaos.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's head generation in the video is problematic."
}
] |
seed44_2042
|
videos/HRA_part1/2042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a green spacesuit with a clear helmet, stands on an alien planet with vibrant purple foliage and orange skies, holding a tablet displaying educational diagrams. Nearby, a body of water shimmers under the exotic sky, showing aquatic life adapted to this unique ecosystem, swimming gracefully beneath the surface. The teacher occasionally glances up from the tablet to observe the surrounding alien flora and fauna, integrating real-world examples into the lesson. Throughout the scene, the focus remains on the teacher's engagement with the alien environment, using it as a teaching tool, while the colorful, otherworldly landscape provides a captivating backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_263
|
videos/HRA_part0/263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic zebra, adorned with its distinctive black and white stripes, stands at the edge of a crystal-clear pool located in a vast, open mine. The zebra, with its striking pattern, contrasts beautifully against the barren landscape of the mine. Suddenly, it gracefully plunges into the water, swimming effortlessly as it explores the submerged depths of the mine, the sunlight filtering through the water's surface creating a mesmerizing play of light and shadow around the zebra. This unique scene unfolds in a large, abandoned mine, now filled with water, providing an unexpected aquatic habitat for wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The zebra's head and legs are distorted in the video."
}
] |
seed46_1046
|
videos/HRA_part2/1046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 diligent worker, clad in a high-visibility yellow vest, blue jeans, and a brown jacket, methodically rakes a large pile of autumn leaves into a meticulously organized heap. The scene is set in a spacious backyard, bordered by a wooden fence, with additional piles of leaves scattered throughout the yard, indicating a day of hard work. The worker's focus is intense, his movements efficient, as he tackles the task with determination, the vibrant colors of the fallen foliage contrasting beautifully against the green grass.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is deformed, and the rake is also deformed."
}
] |
seed44_1103
|
videos/HRA_part1/1103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space reality TV show set against a metallic spaceship interior, a muscular firefighter wearing a red swim cap, goggles, and a black swimsuit floats weightlessly in zero gravity. He performs swimming strokes in mid-air, surrounded by floating water droplets, while a diverse group of fellow firefighters observes from a viewing platform. The scene conveys a sense of camaraderie and adventure among the crew members, who are participating in a unique aquatic challenge aboard the spacecraft. The firefighter's robust physique and focused expression highlight his determination and skill, even in the unconventional setting of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1324
|
videos/HRA_part2/1324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man with glasses and a gray beanie, wearing a dark jacket, leans into the soil with a green-handled shovel, his wedding band glinting in the light. He pauses to wipe sweat from his brow, revealing a determined look. Moments later, he is joined by another man, both digging in unison, the second man dressed in a brown jacket, jeans, and a white t-shirt. The scene transitions to the first man, now shirtless and covered in dirt, continuing to dig with intense focus, highlighting the hard labor involved. Finally, the two men stand back, shovels resting on their shoulders, surveying their deep, freshly-dug hole, a sense of accomplishment evident in their satisfied expressions. Throughout the scene, the man with the beanie remains the central figure, his actions and expressions conveying the physical and emotional demands of the task.]"
},
{
"from": "gpt",
"value": "Bad. The hands and arms appear deformed and disfigured."
}
] |
seed42_2770
|
videos/HRA_part0/2770.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its curved horns and brown coat, walks steadily across a rocky terrain, with a clear blue sky and distant mountains providing a scenic backdrop. The ibex navigates the rugged landscape with ease, its hooves firmly gripping the stone surface. It pauses momentarily, its head held high, surveying its surroundings before continuing its journey, moving gracefully among the boulders and cliffs. Throughout the scene, the ibex remains the central focus, its presence commanding attention against the stark beauty of the alpine environment.]"
},
{
"from": "gpt",
"value": "Normal. The ibex's movements are not smooth."
}
] |
seed46_2696
|
videos/HRA_part2/2696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 North American beaver, known for its brown fur and flat, paddle-like tail, crawls along the muddy bank of a tranquil river. It pauses for a moment, gnawing on a piece of wood with its sharp incisors, before continuing its slow, deliberate crawl. Its small, rounded ears and half-closed eyes add to the relaxed atmosphere of the scene. The beaver's movement is unhurried, as it navigates the earthy terrain near the water's edge, occasionally pausing to survey its surroundings with a curious tilt of its head.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2888
|
videos/HRA_part1/2888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit theater, the spotlight reveals two young children, a boy and a girl, both dressed in casual attire, sitting on a red velvet couch. The boy, wearing a blue T-shirt and khaki shorts, looks at the girl with a smile, his hand gently caressing her arm. The girl, dressed in a yellow sundress, returns his affectionate gesture with a warm look and a tender touch to his cheek, all against the backdrop of a classic theater setting with plush red curtains and ornate decorations. The scene captures a moment of innocent connection between the two children, emphasizing the tenderness of their interaction within the grandeur of the theater environment.]"
},
{
"from": "gpt",
"value": "Bad. The children's faces in the video are slightly uncoordinated, and the children's hands are deformed."
}
] |
seed42_2760
|
videos/HRA_part0/2760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a neatly trimmed beard and a muscular build rearranges furniture in a modern living room. He lifts a heavy wooden coffee table with ease, his biceps flexing under a tight-fitting gray T-shirt. Wearing dark blue jeans and white sneakers, he positions the table in the center of the room, then pauses to consider the layout. Satisfied, he proceeds to adjust the placement of two large, plush armchairs, ensuring they are perfectly aligned with the table. The room features minimalist decor, with white walls, a large window letting in ample natural light, and a sleek flat-screen TV mounted above a low-profile entertainment unit. Throughout the scene, the man's confident demeanor and attention to detail are evident as he meticulously arranges the furniture to achieve a balanced and inviting space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1424
|
videos/HRA_part1/1424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a gray jacket and khaki pants, unloads a large, industrial dishwasher in a busy school cafeteria during lunchtime. He wears yellow rubber gloves and a face mask, and carries a mop and bucket, indicating his role in maintaining cleanliness. The scene captures him pausing for a moment, holding a clean tray, with students visible in the background, emphasizing the bustling environment. The janitor then continues his task, placing trays on a metal shelf, demonstrating his routine duty amidst the lively atmosphere of the cafeteria.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2466
|
videos/HRA_part0/2466.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with badges and a walkie-talkie attached to his belt, points assertively with his right hand while looking intently at something off-screen. He stands in a busy urban street scene, with pedestrians and vehicles in the background, conveying a sense of duty and command. His left hand rests on his hip, near his service weapon, and his authoritative stance is emphasized by the presence of a large, bustling city behind him, complete with tall buildings, traffic lights, and street signs.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_1066
|
videos/HRA_part0/1066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinctive black markings, is perched on a concrete ledge. It has a full, round body and is situated in an urban environment, as indicated by the presence of a streetlight and a partial view of a building's facade with windows. The bird faces right, its head turned slightly toward the viewer, revealing one bright, alert eye. Its beak is open, perhaps mid-call, and its feet grasp the edge of the ledge firmly. The scene is set against a backdrop of a clear, blue sky, offering a simple yet effective contrast to the textured details of the pigeon.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2708
|
videos/HRA_part2/2708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy hamster, primarily white with gray patches, leaps into the air from within a wire cage, its hind legs propelling it upwards with remarkable agility. The hamster's front paws extend forward as it jumps, highlighting its determination and playfulness. The scene is set against a backdrop of a green meadow, creating a whimsical contrast between the indoor cage and the outdoor setting. The hamster's joyful leap is captured in high detail, showcasing its adventurous spirit and the soft fur that covers its body.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's movements in the video are not smooth."
}
] |
seed44_2149
|
videos/HRA_part1/2149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant display under the aurora-lit sky, several figures clad in traditional fur coats and hats, reminiscent of indigenous Siberian attire, gather around a blazing bonfire set amidst the dense taiga forest. They begin to sway in unison, their movements a harmonious blend of ancient and modern dance styles. The firelight flickers across their faces, casting dramatic shadows as they leap and twirl, their feet barely touching the snow-covered ground. The camera captures the dancers from various angles, emphasizing the connection between their lively steps and the serene, starlit wilderness that surrounds them.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video has a twisted body, head, legs, and arms."
}
] |
seed42_310
|
videos/HRA_part0/310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a black jacket and khaki pants, confidently walks alongside a zebra in the middle of a desert landscape, both seemingly unfazed by the arid environment. The director holds a megaphone in one hand and a script in the other, while the zebra, a symbol of the untamed, ambles beside him, the two forming an unlikely duo in this surreal scene. The sun casts long shadows, highlighting the stark beauty of the desert, as the director and the zebra continue their journey together, a testament to the unexpected alliances that can occur in the pursuit of art.]"
},
{
"from": "gpt",
"value": "Bad. The director's face in the video is blurry, hands and feet are deformed, one of the zebra's hind legs is missing, the generation is uncoordinated, and a megaphone or script suddenly appears in the director's hand in the middle frame."
}
] |
seed44_3030
|
videos/HRA_part1/3030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a human-like jackal, dressed in a red apron and name tag, stands behind a checkout counter. The background features a vibrant, turquoise water surface, suggesting a swimming pool or body of water. The jackal, with its distinctive canine features and upright posture, interacts with customers, handling items scanned over a register. The setting is illuminated by bright, warm lighting, casting a glow on the turquoise water, which stretches out behind the cashier area, merging the indoor and outdoor environments in an unexpected juxtaposition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_279
|
videos/HRA_part1/279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 human teacher, wearing a casual blue shirt and jeans, is playfully dancing in a classroom filled with natural light, alongside a chimpanzee. The chimpanzee, dressed in a miniature version of the teacher's outfit, mirrors the teacher's dance moves with joyful expressions. Both the teacher and the chimpanzee engage in synchronized steps, creating a harmonious and whimsical scene, as they move across the room with the sun casting gentle shadows behind them. The teacher's face reflects amusement and connection, while the chimpanzee's animated body language conveys a sense of fun and companionship in their shared activity.]"
},
{
"from": "gpt",
"value": "Bad. The facial features of the human teacher in the video are distorted, the hands and feet are deformed, the head and limbs of the chimpanzee are deformed, and the hands of the human teacher and the chimpanzee in the middle frames are severely twisted and deformed."
}
] |
seed46_1824
|
videos/HRA_part2/1824.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 are distorted in the video."
}
] |
seed46_2081
|
videos/HRA_part2/2081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, equipped with sunglasses, a badge, and a radio, stands ready on a sandy beach, the ocean visible behind him. He then leaps into the air, his silhouette framed against the bright horizon, showcasing agility and dynamism. Next, he lands gracefully on the sand, his stance firm and authoritative. Finally, he is seen in mid-stride, walking purposefully along the shoreline, the vast ocean and clear blue sky completing the scene, embodying strength and determination in an idyllic coastal setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3110
|
videos/HRA_part0/3110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy white rabbit sits upright on a clean, wooden surface, using its paw to wipe its face meticulously, akin to a cat grooming itself. The action is repeated several times, showcasing the rabbit's cleanliness and the texture of its fur against the smooth wood. The rabbit then pauses, sitting still with its paws down and ears perked up, before resuming the wiping motion, its pink nose twitching occasionally. Throughout the sequence, the rabbit's focus remains on its grooming, offering a charming display of its self-care routine.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit in the video has uncoordinated movements."
}
] |
seed44_1477
|
videos/HRA_part1/1477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene, a distinguished film director, clad in a black jacket, blue jeans, and brown boots, stands on a rocky outcropping, passionately directing the action. Nearby, an agile ibex leaps over a boulder with remarkable grace, its brown fur and curved horns vivid against the craggy landscape. The camera focuses on the ibex mid-jump, capturing the animal's strength and agility, while the director observes intently, his silhouette framed against the dramatic mountain scenery.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_1100
|
videos/HRA_part0/1100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 parallel universe setting, a firefighter, identifiable by his black helmet with a shiny badge, black uniform, and red suspenders, crawls on all fours through a desolate urban landscape. The cityscape features a large, gray building with broken windows and a dark, cloudy sky. The firefighter's movements are slow and deliberate, as if navigating through a hazardous environment. His gear includes a heavy-duty jacket, sturdy gloves, and a breathing apparatus strapped to his back, alluding to the dangerous conditions he faces. Despite the bleak surroundings, the firefighter's determination is evident in his focused gaze and resolute posture.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2270
|
videos/HRA_part0/2270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 named Jay, distinguished by his short brown hair and beard, stands against a backdrop of tall pine trees. Dressed in a gray sweater, black shirt, and brown pants, he looks intently at the camera. His gaze shifts upwards, revealing a curious expression. Then, he smiles warmly, his eyes crinkling at the corners, exuding friendliness. Lastly, he closes his eyes in delight, basking in the beauty of nature surrounding him, the sunlight filtering through the dense forest creating a serene atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The man's eyes in the video have generation issues, and his facial features are slightly blurry."
}
] |
seed42_1656
|
videos/HRA_part0/1656.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cosmic-themed diner, a cheerful cashier, donning a red polka-dot apron over a black and white striped shirt, energetically dances behind the counter. The backdrop features a vast, detailed image of Jupiter, prominently displaying its iconic Great Red Spot. The cashier's playful movements contrast with the majestic, distant planet, creating a whimsical yet awe-inspiring scene. Patrons enjoy their meals, seemingly unfazed by the extraordinary setting, as the cashier continues to dance, infusing the space with a vibrant, lively atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The body movements of the person in the video are not coordinated."
}
] |
seed46_1268
|
videos/HRA_part2/1268.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 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 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's head is distorted, the arms are twisted, and the legs are deformed."
}
] |
seed46_2038
|
videos/HRA_part2/2038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars gracefully over a vast, shimmering ocean, its expansive wingspan casting a shadow on the water below. The bird's plumage, a stunning blend of white and dark feathers, contrasts beautifully against the blue sky. As it glides through the air, its sharp eyes scan the sea for signs of prey. In the background, the silhouette of an island can be seen, adding depth and scale to the scene. The albatross, a symbol of freedom and endurance, continues its flight, the wind gently ruffling its feathers, embodying the spirit of the open sea.]"
},
{
"from": "gpt",
"value": "Bad. The albatross's wings in the video have generation issues, the claws and head were not generated, and the body was generated in a distorted manner."
}
] |
seed44_1479
|
videos/HRA_part1/1479.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, covered in shaggy, dark brown fur, stands against a pale, sandy background. It uses its trunk to wipe mud from its body, creating a cloud of dust that catches the sunlight. The creature's large, curved tusks and drooping ears are prominent as it continues to clean itself, highlighting its ancient majesty in a moment captured with high-definition clarity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2299
|
videos/HRA_part0/2299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A great egret, standing tall with folded wings, perches gracefully on one leg atop a weathered wooden post in the midst of a serene marsh landscape, surrounded by lush green vegetation and calm waters. Its pristine white feathers contrast beautifully against the natural backdrop, while its sharp yellow eyes scan the environment keenly. The scene is set during the golden hour, with the warm sunlight casting a soft glow over the bird and its habitat, highlighting the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2452
|
videos/HRA_part2/2452.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 jacket and black trousers, stands on a glacier, performing maintenance on a piece of equipment. The scene opens with a close-up of his hands, wearing black gloves, carefully wiping ice from a sophisticated device. The vast, icy landscape stretches behind him, with the sun casting a warm glow on the cold environment. As he continues to wipe away the frost, the camera pans out to reveal the enormity of the glacier and the solitude of his task. The engineer's focused expression and the stark beauty of the icy terrain provide a captivating contrast in this high-definition shot.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.