video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1641
|
videos/HRA_part0/1641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a gray shirt, khaki cargo pants, and a brown belt pauses on a rocky trail, surrounded by lush greenery and towering trees. He leans on a wooden hiking stick, looking intently at the dense forest before him. Moments later, he hikes uphill, carrying a backpack and water bottle, with the sunlight filtering through the leaves overhead. Then, he stops to observe his surroundings, his weathered hands gripping the hiking stick, and the rich green foliage providing a stunning backdrop. Finally, he hikes through the dense wilderness, his attire and equipment suggesting a seasoned outdoorsman, and the vibrant greenery of the forest enveloping him in its beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand in the video has issues."
}
] |
seed44_2079
|
videos/HRA_part1/2079.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit kitchen, a young man with short brown hair, wearing a black apron over a casual outfit, stands attentively at a modern gas stove. He is seen from a side angle, focusing on cooking a sizzling meal in a large pan, his face expressing concentration. Moments later, he checks the progress of his dish, revealing a close-up of the appetizing food. He then stirs the contents of the pan with a wooden spoon, the steam rising from the meal adding to the atmosphere. Throughout, the kitchen remains bright and welcoming, with a clear countertop and various cooking utensils visible, enhancing the sense of domestic tranquility.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the check for dish progress and the close-up of the delicious food mentioned in the caption."
}
] |
seed44_2140
|
videos/HRA_part1/2140.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a beige cap and black jacket, sits on a chair next to a swimming pool at a luxurious hotel, surrounded by lush greenery and palm trees. The director holds a megaphone in one hand and a script in the other, meticulously planning the next shot. Nearby, a cobra slithers across the sun-drenched tiles, its scales shimmering under the bright sunlight, adding an unexpected element of danger to the idyllic scene. The hotel's grand architecture looms in the background, its white walls contrasting against the deep blue of the pool and the vibrant green foliage, creating a visually stunning setting.]"
},
{
"from": "gpt",
"value": "Bad. The number of snakes in the video is incorrect."
}
] |
seed46_2931
|
videos/HRA_part2/2931.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction site bustling with activity, filled with hard hats and heavy machinery, serves as the backdrop for a massive crane towering overhead. The crane, painted in bold yellow and black stripes, extends its long arm skyward, with a hook dangling below. Sunlight glints off the metal, highlighting the intricate framework and gears that enable the crane's powerful movements. At the top, a small cabin shelters the operator, who skillfully maneuvers the crane to lift and place heavy steel beams, essential for building the city's skyline. Dust and debris swirl around the base, where workers guide the crane's actions with precise hand signals, contributing to the urban landscape's ongoing transformation.]"
},
{
"from": "gpt",
"value": "Good. The hook of the crane can be clearly seen moving in the video, and the action is basically normal."
}
] |
seed42_179
|
videos/HRA_part0/179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two children, a boy and a girl, both wearing space suits with helmets under their arms, walk purposefully down a metallic corridor illuminated by blue light. The boy, with short brown hair and a red stripe across his helmet, carries a backpack, while the girl, with long blonde hair tied in a ponytail and a yellow stripe on her helmet, holds a small, mysterious box. They navigate through a door marked with alien symbols, indicating their arrival at a space diplomatic mission. Inside, they meet a diverse group of extraterrestrial beings, all gathered around a large holographic map, creating an atmosphere of intergalactic diplomacy. The children, standing tall among these alien delegates, represent humanity on this important interstellar journey.]"
},
{
"from": "gpt",
"value": "Normal. No helmets were generated under the arms of the two children."
}
] |
seed42_1280
|
videos/HRA_part0/1280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and a walkie-talkie on his belt, walks through a museum filled with historical artifacts. The museum exhibits a variety of items, including ancient statues, paintings, and glass cases displaying precious jewels. The officer's path takes him past a large statue, a painting of a woman, and a glass case containing a crown, as he ensures the safety and security of the museum's valuable collections. The museum's interior is grand, featuring high ceilings, marble floors, and ornate decorations, providing a fitting backdrop for the treasures it houses.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2749
|
videos/HRA_part0/2749.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown pelican with a large, distinctive orange pouch flies low over the surface of a calm bay, its wings spread wide against the vivid blue sky. It gracefully swoops down, diving into the water to catch fish, its body momentarily submerged before it resurfaces, triumphant. The pelican then floats on the water, preening its feathers with a meticulous beak, showcasing its survival skills in the serene coastal environment. Against the backdrop of a clear sky and calm waters, the pelican's flight and feeding habits are highlighted, emphasizing its unique features and behaviors in the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1614
|
videos/HRA_part2/1614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 opera performance, a farmer wearing a traditional straw hat and a patched apron over a checkered shirt runs across the stage under a backdrop of stars and planets. Simultaneously, a life-sized robotic tiger, designed with intricate circuitry patterns, races alongside him, both moving with a sense of urgency. The farmer's face is set in determination, and the tiger's robotic eyes glow with programmed intensity, highlighting the dramatic chase sequence unfolding against the cosmic setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2388
|
videos/HRA_part0/2388.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded chef, donning a red baseball cap, a gray t-shirt, and green apron over his attire, is seen energetically cleaning a car in a vibrant, sunny setting. He begins by rinsing the vehicle with a hose, water spraying from the nozzle. Then, he proceeds to wash the car using a large sponge, applying soapy suds to its surface. Next, he uses a squeegee to remove excess water, ensuring a streak-free finish. Lastly, he dries the car with microfiber towels, his movements demonstrating thoroughness and care, all while maintaining his lively demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The chef's facial expressions, arms, and hands are generated abnormally in the video, with the chef's hands and arms suddenly disappearing or appearing in the middle frames."
}
] |
seed42_2279
|
videos/HRA_part0/2279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a brown jacket, beige trousers, and a wide-brimmed hat, dances jovially in a mountainous landscape, the distant peaks shrouded in mist. A deer, with a full rack of antlers and a curious gaze, watches him from the edge of a lush forest. The farmer's movements are lively and carefree, his arms raised in the air, as if celebrating the beauty of nature that surrounds him. The deer, sensing no threat, cautiously approaches, its ears perked, adding a touch of whimsy to the scene. The mountains loom majestically in the background, their slopes dotted with trees and patches of greenery, providing a stunning natural backdrop to this unexpected dance.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's dance moves are not fluid, and there are sudden changes in the limbs."
}
] |
seed42_1782
|
videos/HRA_part0/1782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray, majestic and graceful, glides through crystal-clear waters, its body a stunning contrast of black and white. It somersaults effortlessly, performing acrobatic feats just beneath the ocean's surface, with sunlight filtering through and illuminating the scene. Schools of small fish scatter as the ray passes, highlighting the vastness of its wingspan. The ray then swims upward towards the sunlit water, creating mesmerizing patterns with its movements, before disappearing into the depths, leaving a trail of bubbles in its wake.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2169
|
videos/HRA_part2/2169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy gray mouse walks along the edge of a weathered wooden table, its tiny feet making delicate movements against the grainy surface. The mouse pauses momentarily, its whiskers twitching as it senses the environment, before continuing its journey. Its round ears and curious demeanor are highlighted as it explores the tabletop landscape, framed by a blurred background that suggests a rustic interior setting. Throughout the scene, the mouse's agile movements and cautious behavior are captured in detail, providing a close-up view of its natural actions.]"
},
{
"from": "gpt",
"value": "Normal. The rat's paws and hind body in the video were generated abnormally, with the hind body suddenly twisting in the middle frames."
}
] |
seed46_1644
|
videos/HRA_part2/1644.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-lit, organized retail store, two diligent employees wearing red aprons and name tags restock the shelves with groceries. One employee, a man with short brown hair, focuses on neatly arranging cereal boxes, ensuring they face forward. Meanwhile, his female coworker, wearing glasses and with her hair tied back, meticulously stacks cans of soup, aligning them perfectly. The shelves are filled with various food items, including crackers, canned goods, and pasta, all neatly organized and easily accessible to customers. The store is clean and inviting, with a fresh produce section visible in the background, showcasing an array of colorful fruits and vegetables.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1944
|
videos/HRA_part1/1944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 silverback gorilla is depicted in a dense, lush forest, illuminated by patches of sunlight filtering through the canopy. Initially, it stands powerfully on all fours, its muscles rippling under its dark fur. It then charges forward, running with a burst of energy, showcasing its strength and agility. The gorilla's movement is captured in a series of dynamic poses, highlighting its powerful build and the determination in its eyes, set against the vibrant greenery of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The running movements of the silverback gorilla in the video are very unsmooth and uncoordinated, with abrupt changes."
}
] |
seed42_2278
|
videos/HRA_part0/2278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a yellow shirt, catches a flying drumstick during an energetic performance under the spotlight. The scene transitions to show the artist passionately singing into the microphone, the crowd's glow sticks illuminating the dark venue. Next, the musician is seen catching a guitar pick from another band member, their connection highlighted by the stage lights. Finally, the artist reaches out to catch a flower thrown from the audience, a gesture symbolizing the bond between performer and fans, all set against a backdrop of colorful stage lighting.]"
},
{
"from": "gpt",
"value": "Bad. The musician's singing in the video is accompanied by uncoordinated movements."
}
] |
seed42_1886
|
videos/HRA_part0/1886.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, clad in rich brown fur, dashes across a lush, verdant forest floor, its bushy tail swaying energetically. The scene is captured in vibrant detail, with the beaver's small ears and alert eyes clearly visible as it navigates the underbrush. Its front paws, equipped with dexterous digits, grip the mossy ground, propelling it forward with a sense of urgency. The background features a dense thicket of trees and foliage, providing a natural habitat for the beaver's lively sprint.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2132
|
videos/HRA_part2/2132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, with iridescent green feathers and a forked tail, hovers near a red feeder, its wings a blur of motion against a clear blue sky. The bird's tiny feet dangle beneath it as it feeds, and its long, thin beak dips into the feeder's port. Suddenly, it takes flight, its wings creating an audible hum, and lands on a branch, where it preens its feathers with its curved bill. Throughout, the hummingbird's rapid wing movements and vibrant plumage are showcased against the serene backdrop of nature.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed44_158
|
videos/HRA_part1/158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room, two young children sit attentively at a wooden table, each engaged in the meticulous task of hemming pants. One child, a boy with short brown hair wearing a blue t-shirt and jeans, carefully measures the fabric with a silver ruler, ensuring precise folds. Beside him, a girl with long pigtails, dressed in a yellow dress, threads a needle with focused determination, her tongue slightly poking out in concentration. Both use matching white sewing machines placed on either side of the table, their small feet reaching down to operate the pedals. The atmosphere is one of diligent learning, with the children's expressions showing a mix of seriousness and occasional smiles, highlighting their engagement in this practical skill.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed44_171
|
videos/HRA_part1/171.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."
}
] |
seed46_2705
|
videos/HRA_part2/2705.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant male musician, clad in a black leather jacket, blue jeans, and black boots, passionately plays a red electric guitar on a dimly lit stage. He kicks his right leg high into the air, his black hair slightly disheveled, and his face expressing intense concentration. The scene is set against a backdrop of colorful stage lights and a blurred audience, capturing the raw energy and emotion of his performance.]"
},
{
"from": "gpt",
"value": "Bad. The musician's facial features and fingers are deformed in the video, the legs are incomplete, and the guitar is blurry."
}
] |
seed44_2560
|
videos/HRA_part1/2560.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor wearing a yellow high-visibility vest, khaki cargo shorts, and a green t-shirt is crawling on a sandy beach, possibly searching for lost items or performing an unusual cleaning task. The beach is wide and sandy, with shallow water and a calm sea stretching into the distance. Palm trees dot the landscape, and the beach is relatively empty except for a few people walking in the background. The janitor's actions are focused and deliberate, contrasting with the serene coastal scenery.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, arms, and legs are distorted in the video."
}
] |
seed44_1857
|
videos/HRA_part1/1857.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, named Bingo, energetically jumps onto a wooden platform in a spacious outdoor enclosure, surrounded by lush greenery and trees. Dressed in a tiny red jacket, Bingo displays his strength and agility, with the sunlight filtering through the leaves highlighting his movement. He then leaps from the platform onto a thick branch, showcasing his natural climbing skills. Next, he swings from a hanging tire, his joyful expressions and animated body language capturing the essence of playfulness. Finally, he bounds across the enclosure, his powerful legs propelling him forward, as he explores his environment with boundless energy and curiosity.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee undergoes a mutation and deformity when jumping, with its limbs becoming deformed and elongated."
}
] |
seed44_3014
|
videos/HRA_part1/3014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant parrotfish, distinguished by its bright green body with yellow fins and a striking pink head, swims gracefully in clear blue waters. Its unique appearance is highlighted as it explores a coral reef ecosystem, surrounded by various marine life. The fish's body, featuring bold colors and patterns, contrasts beautifully with the sandy seabed and lush underwater vegetation. As it moves, the parrotfish reveals its distinctive form and coloration, making it a captivating subject in the rich tapestry of oceanic biodiversity.]"
},
{
"from": "gpt",
"value": "Normal. The fin generation in the video has issues."
}
] |
seed44_1165
|
videos/HRA_part1/1165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green jungle environment, two young boys, one wearing a yellow t-shirt and the other in a blue shirt, are seen interacting with a small monkey. The monkey, sitting on a branch at eye level with the children, reaches out to touch the hand of the boy in the yellow shirt, who gently caresses its head in return. The second child looks on with a smile, his hands resting on the branch, as they both share a tender moment with the curious primate, surrounded by the vibrant foliage of their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The boy's hand appears deformed, and the monkey also appears deformed."
}
] |
seed42_1337
|
videos/HRA_part0/1337.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, donning a navy blue polo shirt, beige shorts, and brown shoes, is organizing a cluttered garage filled with various items. Initially, he stands thoughtfully amidst the chaos, surrounded by a bike, a toolbox, and gardening equipment. He then proceeds to sort through a pile of objects, showcasing his methodical approach. Next, he is depicted lifting a heavy object, demonstrating his physical strength. Finally, he is shown proudly admiring his neatly organized garage, with shelves neatly arranged and tools hanging orderly on the walls, a testament to his hard work and attention to detail.]"
},
{
"from": "gpt",
"value": "Bad. The hands and feet appear deformed, the object in hand distorts, and finally disappears; the hands and feet appear deformed."
}
] |
seed46_1238
|
videos/HRA_part2/1238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European starling perched on a branch, its vibrant plumage shimmering with hues of green and purple under the sunlight. The bird's beady eye is fixed ahead, and its feathers appear ruffled, as if enjoying a gentle breeze. The starling's curved bill and round body are distinct against the blurred green foliage in the background, creating a contrast that highlights the bird's intricate details. The scene is set in a serene forest environment, where the starling seems unperturbed by the camera, offering a rare glimpse into its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2530
|
videos/HRA_part1/2530.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A solitary black rhinoceros, distinguished by its squared-off lips and grayish-brown skin, wipes itself vigorously against a tree trunk in the midst of dense savanna vegetation. The action is captured in high definition, showcasing the rhino's determination and the textural contrast between its rough hide and the tree bark. The scene unfolds against a backdrop of lush greenery, highlighting the animal's natural habitat. Moments later, the rhino continues rubbing against the tree, emphasizing its commitment to the self-cleaning ritual, with the verdant foliage and distant trees framing the action in a captivating wildlife moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_149
|
videos/HRA_part0/149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, clad in a tailored gray suit, white shirt, and striped tie, rearranges furniture in a sophisticated office space. Initially, he thoughtfully observes the room, considering the layout. Then, he pushes a modern desk aside, revealing a keen eye for design. Next, he skillfully pulls a sleek office chair into place, demonstrating attention to detail. Finally, he stands back, hands on hips, surveying his newly organized workspace with satisfaction, the room's minimalist decor and natural light enhancing the professional atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2893
|
videos/HRA_part1/2893.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a white chef's uniform and black apron, kneels beside a granite countertop in a modern kitchen. He focuses intently on fixing a leaky faucet, his hands working diligently with a wrench and screwdriver. The kitchen features high-end stainless steel appliances, a double sink, and sleek cabinetry. Light spills in from a nearby window, illuminating the space as the chef, adorned with a white hat and displaying a serious expression, demonstrates his skills beyond the culinary arts.]"
},
{
"from": "gpt",
"value": "Bad. The chef's movements in the video are not smooth."
}
] |
seed44_1892
|
videos/HRA_part1/1892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier, donning a red apron with a name tag, works diligently behind a cluttered grocery store checkout counter. She is in the process of changing the batteries in a barcode scanner, handling the device with care and precision. The scene is set in a bustling supermarket, with customers waiting patiently in line, and the cashier's actions are framed by shelves stocked with various products. As she replaces the batteries, her focused expression conveys her commitment to ensuring the scanner functions smoothly, maintaining the efficiency of the checkout process.]"
},
{
"from": "gpt",
"value": "Normal. The female cashier's actions in changing the barcode scanner battery in the video are not smooth and coordinated, with her hand suddenly changing in the middle frame."
}
] |
seed42_1541
|
videos/HRA_part0/1541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising juxtaposition, a waiter in full uniform, complete with a white shirt, black vest, and tie, is shown running along the edge of a busy highway. The highway is filled with cars and trucks, creating a bustling urban atmosphere. The waiter's face conveys determination as he sprints, his black trousers and polished shoes moving swiftly against the gritty pavement. The scenery includes billboards and distant city buildings, providing a backdrop of urban life. Despite the unusual setting, the waiter remains focused, his gaze fixed ahead as he continues his unexpected journey along the highway.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2631
|
videos/HRA_part2/2631.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, evident from his refined facial features and confident posture, rakes leaves in an autumn backyard. He wears a brown jacket over a crisp white shirt, paired with khaki trousers, and brown shoes, presenting a polished appearance. The lush green grass, vibrant red leaves scattered about, and a large tree with a tire swing in the background create a warm, inviting atmosphere. The lawyer, possibly taking a break from his legal work, enjoys the simple pleasure of outdoor chores, his face expressing satisfaction and tranquility amidst the rich colors of fall.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1595
|
videos/HRA_part0/1595.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, complete with a receding hairline, glasses, and a gray beard, is depicted in a series of vignettes scrubbing various surfaces in a bathroom. In the first frame, he vigorously cleans the bathtub, wearing a black turtleneck sweater, khaki pants, and black shoes, his attire contrasting with the task at hand. Next, he is seen on his knees, scrubbing the floor tiles with the same intensity, his clothing now slightly disheveled. Then, he appears focused on cleaning the toilet bowl, his attire unchanged, showcasing his determination to tackle household chores. Lastly, he is shown wiping down the sink countertop, his attire still formal despite the domestic activity, highlighting the juxtaposition of his professional persona with the mundane task of bathroom cleaning.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous."
}
] |
seed42_1874
|
videos/HRA_part0/1874.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 navy blue uniform with a badge and a black belt, runs through a vast meadow filled with lush green grass and vibrant wildflowers. The landscape stretches to the horizon, dotted with distant trees. His expression is one of determination, eyes focused ahead, and he strides with purpose, leaving a faint trail in the dewy grass. The sun, partially obscured by a cloud, casts a soft, golden light over the scene, highlighting the officer's movement as he navigates the uneven terrain, demonstrating commitment and urgency in his duty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_206
|
videos/HRA_part0/206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, distinguished by its black and white striped face and brown fur, scurries through a network of intricately dug tunnels in a dimly lit sett. The animal, with its stocky build and sharp claws, moves swiftly and purposefully, navigating the narrow passages with ease. As it runs, the texture of the tunnel walls, composed of earth and roots, becomes apparent, providing a natural contrast to the badger's movement. Throughout the sequence, the focus remains on the badger's journey within the tunnel system, emphasizing its agility and familiarity with its subterranean habitat.]"
},
{
"from": "gpt",
"value": "Bad. The European badger in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed42_1281
|
videos/HRA_part0/1281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a gray jacket over his uniform, stands at the edge of a dense forest, contemplating his next move. He is holding hiking gear, including a walking stick, a backpack, and a water bottle, indicating his readiness for an outdoor adventure. The forest features tall, lush trees and a clear, sunny day, with a trail leading into the woods. The janitor begins his hike, walking confidently down the trail, his equipment in tow, as he explores the natural beauty of the forest surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2927
|
videos/HRA_part1/2927.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural backyard filled with lush greenery and wooden fences, two young children, a boy in a red shirt and blue shorts and a girl in a yellow dress, chase after a lively chicken, their laughter echoing in the sunny afternoon. The boy, with short brown hair, and the girl, her hair tied in pigtails, gleefully pursue the bird across the yard. Their playful antics are framed by a background of vibrant green trees and shrubs, with the chicken's colorful feathers standing out against the natural setting. The scene captures a moment of innocent childhood joy, with the children's faces alight with excitement and the chicken adding a touch of whimsy to the idyllic outdoor space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1296
|
videos/HRA_part0/1296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female worker sits on a wooden chair under the shade of a tree, knitting a long, colorful scarf with red, green, and yellow yarns. She wears a simple cotton dress and sandals, her hair tied back in a bun. The scene is set in a small courtyard surrounded by lush greenery and blooming flowers, with sunlight filtering through the leaves, casting dappled shadows on the ground. The woman's hands move deftly, the knitting needles clicking together in a steady rhythm, as she focuses intently on her work, occasionally glancing up to enjoy the peaceful surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2108
|
videos/HRA_part1/2108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an imaginative scene, a waiter, dressed in a classic black suit and tie, carefully balances a tray of cocktails above his head as he swims underwater. Surrounding him are porcupines, wearing tiny swim caps and goggles, swimming alongside in a synchronized pattern, all submerged in a vast, clear pool under soft, ambient lighting. The waiter's face, visible beneath the water, shows a mix of concentration and amusement at the unusual company he keeps during his aquatic beverage service.]"
},
{
"from": "gpt",
"value": "Normal. The waiter in the video moves slowly, and the hedgehogs move slowly."
}
] |
seed42_2359
|
videos/HRA_part0/2359.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a vibrant pink uniform and wearing a traditional cap, joyfully dances alongside a large, gentle elephant in a lush, green outdoor setting. The pair moves in perfect harmony, their spirits uplifted by the warm sunlight filtering through the leaves overhead. The nurse's face is aglow with happiness, her eyes closed in blissful abandon, while the elephant sways gracefully, its trunk raised in a playful salute to their shared moment of pure delight.]"
},
{
"from": "gpt",
"value": "Bad. The person's body is twisted, the head is twisted, the legs are twisted, the arms are twisted, the elephant's head is twisted, the face is twisted, the legs are twisted."
}
] |
seed42_1971
|
videos/HRA_part0/1971.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer with short brown hair, wearing a gray shirt, sits at a modern office desk cluttered with electronics and tools, knitting a red scarf with large needles. The focus is on her hands as they deftly manipulate the yarn and needles, while a laptop with coding screensaver and a blueprint of a circuit board are visible in the background. The office space is filled with tech gadgets, books, and papers, highlighting her professional environment, yet she finds time for a personal hobby, creating a vivid red scarf amidst the technical surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's fingers in the video are not fully generated, there are missing parts in the yarn and needles, and there are issues with the computer screen and keyboard generation."
}
] |
seed46_1579
|
videos/HRA_part2/1579.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courtroom with an intricate, geometric design, a distinguished actor, portraying a space captain, strides purposefully down the aisle. He wears a tailored uniform, complete with silver insignias, and carries himself with the air of someone accustomed to command. The room is filled with alien spectators of various species, seated on elevated benches, observing the unfolding drama. The lighting is dramatic, casting stark shadows and highlighting the tension in the scene. As the actor walks, the camera follows him, capturing every confident step and the intensity in his eyes, setting the stage for a pivotal moment in the space court trial.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3098
|
videos/HRA_part0/3098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest environment, two individuals wearing khaki safari outfits are seen running alongside a chimpanzee, engaged in playful interaction. The scene is vibrant and full of life, with the humans and the chimpanzee moving together in harmony. They dash across a dirt path, surrounded by dense vegetation, as the chimpanzee exhibits its natural agility and strength. The trio's energetic run is captured in high detail, highlighting the dynamic movement and the unique bond between humans and this primate in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The person wearing the khaki explorer outfit shows deformities in their body and limbs while running, and the gorilla's legs also appear deformed when running."
}
] |
seed44_3162
|
videos/HRA_part1/3162.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 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 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": "Bad. The musician's hand is deformed in the video, and the cheetah is generated abnormally."
}
] |
seed46_1207
|
videos/HRA_part2/1207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a vast, sandy beach, a waiter, dressed in a white button-down shirt and black pants, crawls towards a table set with fine dining ware, a bottle of wine, and two glasses, indicating an unusual yet intriguing service style. The waiter, wearing a name tag and sporting a neatly trimmed beard, continues crawling on the sand, his posture and facial expression suggesting determination. He crawls under a beach umbrella, highlighting the unique setting for this dining experience, with the calm sea and clear blue sky providing a picturesque backdrop. Finally, the waiter reaches the table, still crawling, as he prepares to serve the patrons, creating a memorable and unconventional beachside dining scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_31
|
videos/HRA_part0/31.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pufferfish, round and plump, navigates the vibrant coral reef with its intricate patterns and varied marine life, showcasing the wonders of the underwater world. Its body, inflated to twice its normal size, displays a mesmerizing display of geometric shapes in muted tones against the backdrop of the deep blue sea. The fish's small, beady eyes stand out prominently on its distended form, while its fins propel it gracefully through the water, surrounded by an array of colorful corals and other sea creatures. This underwater scene highlights the unique survival mechanism of the pufferfish in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1250
|
videos/HRA_part1/1250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit tailor shop, a friendly cashier, dressed in a maroon collared shirt and khaki pants, assists a customer. The cashier, with neatly trimmed facial hair, sits at a sewing machine, carefully hemming a pair of gray pants, demonstrating expertise and precision. The scene highlights the skilled craftsmanship and personal service provided in the store, with the cashier's focused expression and the sewing machine's rhythmic sound adding to the atmosphere. The customer, standing nearby, watches attentively, expressing satisfaction and trust in the cashier's abilities.]"
},
{
"from": "gpt",
"value": "Normal. There is an issue with the generation of the cashier's hands, and the sewing machine is not used in the video."
}
] |
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 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": "Normal. The firefighter's crawling motion in the video is not smooth and coordinated."
}
] |
seed46_2225
|
videos/HRA_part2/2225.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a gray jacket over a button-down shirt and black pants, meticulously mops the floor in a wide, empty corridor with high ceilings. His movements are deliberate as he pushes the mop back and forth, creating a rhythmic pattern on the wet floor. The lighting is bright, illuminating the space and highlighting the sheen on the freshly cleaned surface. In one shot, the janitor pauses, mop in hand, as he looks down the length of the hallway, assessing his work. Throughout, the focus remains on him and the task at hand, capturing the quiet dedication of his labor.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1135
|
videos/HRA_part2/1135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a utility belt, leaps into the air against a backdrop of cosmic dust swirling in the night sky, creating a surreal and dramatic scene. The officer's silhouette is highlighted by the celestial phenomenon, with the dust storm's ethereal glow illuminating the surroundings. The jump, captured mid-air, adds a dynamic element to the composition, juxtaposing the grounded authority figure with the otherworldly cosmic event.]"
},
{
"from": "gpt",
"value": "Bad. The officer's arm is not generated in the video."
}
] |
seed46_1314
|
videos/HRA_part2/1314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-dusted wilderness, two majestic bison stand side by side, their large, sturdy bodies nearly touching. One bison gently nudges the other with its snout in a tender caress, their breath visible in the crisp air. Their shaggy coats ripple slightly in the wind, and their eyes meet, conveying a deep bond. The scene is peaceful and intimate, set against a backdrop of distant mountains and a clear blue sky, highlighting the gentle nature of these powerful creatures.]"
},
{
"from": "gpt",
"value": "Normal. The bison's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_115
|
videos/HRA_part2/115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 actor, with short, neatly styled brown hair and a neatly trimmed beard, sits at a wooden table under the glow of a vintage-style light bulb. He is sewing a button onto a garment with focused determination, his eyes intently fixed on the task. Dressed casually in a gray shirt, he works diligently, demonstrating unexpected domestic skills. The close-up shot captures his serious expression and the intricate details of his sewing technique, creating an intriguing contrast between his profession and this ordinary activity.]"
},
{
"from": "gpt",
"value": "Bad. The needle and thread mentioned in the caption did not appear in the video."
}
] |
seed46_2544
|
videos/HRA_part2/2544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space courtroom under the glow of neon lights, two children, a boy in a gray t-shirt and a girl in a pink dress, engage in a mock trial, surrounded by an audience of plush toys and action figures. The boy, acting as the judge, holds a gavel, while the girl, serving as the defendant, wipes away pretend tears with a small tissue, both participants fully immersed in their roles amidst the imaginative setting. Behind them, a large window reveals the vastness of outer space, complete with stars and planets, adding to the fantastical atmosphere of this unique children's play scenario.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1570
|
videos/HRA_part2/1570.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, high-tech laboratory filled with advanced equipment, a dedicated scientist, wearing a white lab coat over a dark shirt and jeans, gently caresses a sophisticated device used in dark matter research. The scientist, sporting short hair and glasses, exhibits a deep connection with the apparatus, conveying the tender care required in handling delicate scientific instruments. The background features a complex arrangement of machinery and computer screens, highlighting the cutting-edge nature of the research being conducted. This intimate interaction between the researcher and the technology underscores the human element in the pursuit of understanding the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Bad. The scientist's fingers in the video were not fully generated, and the eyes were not generated."
}
] |
seed46_1341
|
videos/HRA_part2/1341.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, exhibiting a powerful build with thick, dark fur and a muscular physique, runs across a lush, green savanna landscape under a bright, sunlit sky. The chimp's expressive face, featuring a wide mouth and intense eyes, conveys determination as it moves with agility and strength. Running in a hunched posture typical of its species, the chimpanzee demonstrates its natural locomotion, bounding over the terrain with a sense of purpose. The scene captures the essence of wild chimpanzees in motion, highlighting their dynamic physicality and the vibrant environment they inhabit.]"
},
{
"from": "gpt",
"value": "Normal. The gorilla's arm appears deformed."
}
] |
seed42_3093
|
videos/HRA_part0/3093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, modern space education center, a diligent janitorial worker, clad in a gray uniform, meticulously wipes down an expansive, glass-topped display table. The room is filled with futuristic exhibits, including a large model of the solar system hanging from the ceiling, and interactive screens showing detailed information about planets and galaxies. The worker's attention to detail is evident as they ensure every inch of the table is spotless, allowing visitors to fully appreciate the educational materials displayed beneath the clear surface. The backdrop of the space-themed decor highlights the importance of cleanliness in maintaining a conducive learning environment for students eager to explore the cosmos.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's face in the video is generated blurry, hands are deformed, and the cleaner passes through the glass display table in the middle frames, which is unrealistic."
}
] |
seed44_2054
|
videos/HRA_part1/2054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and holding a fire hose, is seen wiping the nose of a meerkat standing on its hind legs, both against a backdrop of a controlled fire burning in a contained area. The firefighter wears a yellow fire-resistant suit, a black helmet, and gloves, while kneeling to gently wipe the meerkat's face with a cloth. The meerkat, curious and seemingly unbothered by the flames in the background, stands upright as the firefighter tends to it, creating an unusual yet touching interaction between the two.]"
},
{
"from": "gpt",
"value": "Bad. No water hose or cloth was generated."
}
] |
seed42_2661
|
videos/HRA_part0/2661.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hotel with large windows revealing the vast cosmos beyond, a lone gray wolf, wearing an orange collar with a glowing green tag, stands on its hind legs, using its front paws to wipe down a stainless steel countertop. The wolf's movements are deliberate and efficient, as if it has performed this task many times before. The space hotel interior is sleek and modern, with curved walls and soft, ambient lighting that casts a warm glow on the surfaces. Through the windows, stars twinkle in the distance, providing a stunning backdrop to the unusual scene of a wolf performing cleaning duties in zero gravity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2904
|
videos/HRA_part0/2904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bull moose, antlers wide and impressive, runs through a lush, green meadow under a clear blue sky, with a distant mountain range visible on the horizon. Its powerful legs propel it forward in a graceful gallop, kicking up small clouds of dust from the dry earth beneath its hooves. The moose's coat is a deep brown, nearly black, and its large body ripples with muscles as it bounds across the landscape, the embodiment of wild strength and freedom. In the background, tall trees frame the edges of the clearing, their leaves whispering softly in the breeze, while birds take flight, startled by the majestic creature's sudden movement.]"
},
{
"from": "gpt",
"value": "Normal. The moose's running motion in the video is not smooth and coordinated."
}
] |
seed46_1407
|
videos/HRA_part2/1407.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer clad in a blue shirt and gray pants is seen interacting with a chimpanzee in a laboratory setting. The chimpanzee, sitting upright on a chair, holds a wipe in its hand and begins wiping a surface, demonstrating tool use under the watchful guidance of the engineer. The scene captures the unique bond between human and primate in a research context, highlighting the chimpanzee's ability to mimic and perform tasks typically associated with human dexterity and intelligence.]"
},
{
"from": "gpt",
"value": "Bad. A human hand disappears at a certain moment, and the ape's hand appears deformed."
}
] |
seed44_2796
|
videos/HRA_part1/2796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow high-visibility jacket and hard hat, stands near a bobcat excavator on a construction site. He wipes down the machinery with a cloth, revealing the brand name on the excavator's arm. The scene is set against a backdrop of dirt and gravel, with other construction equipment visible in the background. The engineer's actions showcase the maintenance aspect of his job, highlighting his commitment to keeping the equipment clean and operational.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2060
|
videos/HRA_part0/2060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a stunning array of coral formations takes center stage. Hard corals in various shades of brown and orange create a textured landscape, while neon green and blue soft corals sway gently in the current. Brightly colored fish, such as yellow tangs and red snappers, dart in and out of the coral structures. The water above is crystal clear, allowing sunlight to filter down and illuminate the rich colors of the coral reef. In the distance, the silhouette of a large sea turtle can be seen gliding through the water, adding to the serene atmosphere of this underwater paradise.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1298
|
videos/HRA_part2/1298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt, black vest, and black trousers, is seen playfully dancing with an otter. The otter, wearing a tiny bow tie, mirrors the waiter's movements, adding to the surreal atmosphere. The two are surrounded by a softly lit, elegant dining room, with tables set for dinner and fine art adorning the walls. The waiter, with his professional attire, and the otter, with its playful nature, create a harmonious and unexpected dance partnership, captivating the audience with their synchronized steps.]"
},
{
"from": "gpt",
"value": "Bad. The video generated an additional otter, and the bow tie was not generated on the otter."
}
] |
seed44_211
|
videos/HRA_part1/211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene set within the confines of an art gallery, a firefighter clad in full gear and a helmet, carrying an axe, sprints down a wide hallway lined with large paintings and modern art sculptures. The overhead lights cast shadows, adding to the intensity of the moment. Behind him, the glow of an encroaching fire illuminates the space, its orange and red hues contrasting starkly with the artworks. Amidst the chaos, the firefighter's purposeful stride conveys determination and urgency, his mission to save lives and preserve priceless art pieces from the raging inferno.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2579
|
videos/HRA_part0/2579.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 herd of African buffalo, numbering in the hundreds, thunder across an expansive savanna, kicking up clouds of dust as they run. The buffaloes, with their distinctive large horns and sturdy bodies, move in unison, creating an awe-inspiring display of collective power and movement. The scene is set against a backdrop of distant acacia trees and a clear blue sky, emphasizing the vastness of the African wilderness. The herd's movement is so intense that it sends smaller animals scattering in all directions, highlighting the raw energy and strength of these magnificent creatures in motion.]"
},
{
"from": "gpt",
"value": "Good. The water buffalo's running action in the video is basically normal."
}
] |
seed44_1848
|
videos/HRA_part1/1848.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, reminiscent of Chris Hemsworth, is seen in a modern living room with large windows, assembling furniture with ease. He wears a fitted gray t-shirt and dark jeans, highlighting his muscular physique. In one scene, he skillfully hammers a nail into a wooden board, his biceps flexing. Next, he aligns and secures two pieces of furniture with a screwdriver, showcasing his handyman skills. Then, he tightens a bolt on a metal frame, demonstrating precision and focus. Finally, he proudly admires the completed furniture, which includes a sleek wooden table and matching chairs, his satisfied smile adding a touch of charm to the domestic scene.]"
},
{
"from": "gpt",
"value": "Bad. The human hand shows deformities in the fingers."
}
] |
seed44_2055
|
videos/HRA_part1/2055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling train station, a middle-aged doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, carries a brown leather bag. He walks purposefully past a massive, lifelike mammoth skeleton displayed as a scientific exhibit, the structure towering above the busy commuters. The scene captures the juxtaposition of the prehistoric and the modern, with the well-lit, contemporary train station bustling with people going about their day, while the imposing mammoth skeleton looms as a reminder of Earth's ancient past.]"
},
{
"from": "gpt",
"value": "Bad. The man's facial features in the video are distorted, the mammoth's eyes are not generated, and there are problems with the limbs generation."
}
] |
seed42_1497
|
videos/HRA_part0/1497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged male student, wearing a grey jacket and blue jeans, is crawling along a grassy path on a university campus, surrounded by trees and foliage indicative of early autumn. The scene opens with him crawling under a wooden park bench, suggesting playful or unusual behavior. Next, he crawls beneath the low-hanging branches of a tree, highlighting his determination or whimsy. Then, he crawls across a stone walkway, the textured stones providing a tactile contrast to the grass. Finally, he crawls through a tunnel formed by intersecting tree branches, the dappled sunlight creating a dynamic interplay of light and shadow on his form.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the face is distorted, the arms are twisted, and the legs are contorted."
}
] |
seed46_3167
|
videos/HRA_part2/3167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, clad in a simple black one-piece swimsuit, swims calmly in a vast, prehistoric lake, with a woolly mammoth standing watchfully nearby on the shore, its massive frame and shaggy coat a stark contrast against the serene water. The setting sun casts a warm glow over the scene, highlighting the woman's strokes and the mammoth's still form, creating a captivating juxtaposition of ancient and modern elements in a natural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The woman's face generation in the video is uncoordinated, her hands are severely distorted, and the mammoth is incompletely generated."
}
] |
seed46_2990
|
videos/HRA_part2/2990.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red jacket and brown trousers, runs along the edge of a harbor, the water glistening under the bright sun. Accompanied by a large, energetic dog with a tan coat, they traverse the harbor perimeter, surrounded by lush greenery. The farmer, showing a sense of urgency, sprints with focused determination, while the dog bounds alongside, mirroring his pace. Together, they navigate the harbor's edge, the water's surface reflecting sunlight in sparkling patterns, creating a dynamic scene of movement and companionship.]"
},
{
"from": "gpt",
"value": "Normal. The person's face, hands, arms, feet, and legs are distorted in the video, as well as the dog's body, head, and legs."
}
] |
seed46_1440
|
videos/HRA_part2/1440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic individual named Jay, donning a dark blue cap, aviator sunglasses, and a gray shirt, is captured in high-definition. Initially, he is seen against a backdrop of lush greenery, standing tall with his hands on his hips, exuding confidence. The scene then focuses on his face, highlighting his stylish appearance and a slight smile. Next, Jay is shown from behind, gazing out at a stunning mountainous landscape, conveying a sense of adventure. Finally, he raises his right arm, pointing at something exciting in the distance, his silhouette framed by the natural beauty around him, encapsulating the essence of an outdoor enthusiast.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1249
|
videos/HRA_part2/1249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic depiction begins with a painter wearing a white apron, standing before a large canvas in a spacious studio filled with art supplies, painting a panda in vibrant colors. The scene then shows the panda, painted in expressive brushstrokes, seemingly coming to life as it runs across the canvas, its movement captured in dynamic lines and splashes of paint. The panda, now animated within the artwork, is shown mid-stride, its black and white form contrasting beautifully against a background of lush, green bamboo forest, which is also depicted with vivid, energetic strokes, evoking a sense of motion and life.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there is a sudden change. The panda's running action is uncoordinated."
}
] |
seed44_3103
|
videos/HRA_part1/3103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chimpanzee dressed as a waiter in a red bow tie and apron over a white shirt and black pants, stands against a green screen backdrop. Initially, the chimp looks directly at the camera with its hands on its hips. Then, it begins to dance, swaying its body and moving its arms energetically to an unseen beat. The chimp's facial expressions range from serious to playful, adding to the surreal atmosphere of the scene. Throughout, the green screen remains unchanged, allowing the focus to remain on the dancing chimpanzee-waiter.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's movements in the video are not smooth."
}
] |
seed44_1387
|
videos/HRA_part1/1387.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt and black vest, finds himself dancing amidst towering trees in a dense forest. As he gracefully twirls, a majestic bison watches from the shadows, its powerful presence adding a touch of wildness to the surreal encounter. The forest, filled with lush greenery and dappled sunlight, provides a natural stage for this unexpected dance performance, where the lines between human and nature blur in a harmonious display.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1621
|
videos/HRA_part0/1621.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional lawyer, dressed in a dark gray suit with a light gray shirt and red tie, prepares coffee in a modern kitchen. The lawyer, wearing glasses, carefully measures coffee grounds into a French press, adding hot water from a sleek electric kettle. The scene captures the lawyer's meticulous attention to detail, from pouring the water to stirring the mixture gently. The lawyer then presses down the plunger slowly, ensuring a rich brew, all while surrounded by stainless steel appliances and minimalist design elements, creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate glasses."
}
] |
seed46_1344
|
videos/HRA_part2/1344.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, drenched in water, swims across a serene lake, its eyes fixed ahead with unwavering determination. The wolf's powerful legs propel it forward through the crystal-clear water, while its sleek fur glistens under the soft, diffused sunlight filtering through the overcast sky. The surrounding lush forest provides a verdant contrast to the tranquil body of water, and in the distance, snow-capped mountains rise majestically, completing the breathtaking natural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth, and there are sudden changes in the limbs."
}
] |
seed44_1983
|
videos/HRA_part1/1983.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large brown bear, with its shaggy fur glistening in the sunlight, is seen swimming gracefully in a serene lake, surrounded by lush greenery and tall trees. Its powerful forearms propel it through the crystal-clear water, creating ripples that expand outward. The bear's alert eyes and nostrils are just above the waterline, showcasing its keen senses as it navigates the aquatic environment with ease. The peaceful setting, with the occasional splash and the gentle lapping of water against the shore, highlights the bear's natural ability to swim in its tranquil habitat.]"
},
{
"from": "gpt",
"value": "Normal. The brown bear's paws in the video have issues."
}
] |
seed44_2931
|
videos/HRA_part1/2931.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction site bustling with activity, filled with hard hats and heavy machinery, serves as the backdrop for a massive crane towering overhead. The crane, painted in bold yellow and black stripes, extends its long arm skyward, with a hook dangling below. Sunlight glints off the metal, highlighting the intricate framework and gears that enable the crane's powerful movements. At the top, a small cabin shelters the operator, who skillfully maneuvers the crane to lift and place heavy steel beams, essential for building the city's skyline. Dust and debris swirl around the base, where workers guide the crane's actions with precise hand signals, contributing to the urban landscape's ongoing transformation.]"
},
{
"from": "gpt",
"value": "Bad. The scene lacks workers, and there is no depiction of lifting and placing heavy steel beams."
}
] |
seed42_1154
|
videos/HRA_part0/1154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, dressed in a black vest and white shirt, walks purposefully through a series of art galleries, each filled with unique paintings and sculptures. He carries a small, white tray with two wine glasses, moving from one gallery to another, passing by various artworks. In the first gallery, he walks past a large, abstract painting in red and yellow tones. In the second, he strolls by a modern sculpture, and in the third, he passes under a chandelier, all while maintaining a focused demeanor, showcasing the dynamic interplay between service and art.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand appears deformed."
}
] |
seed46_3121
|
videos/HRA_part2/3121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense forest setting, a middle-aged man dressed in a green jacket and gray pants is seen wiping a wooden signpost with a cloth. The signpost, which bears the name of the forest trail, is set against a backdrop of lush greenery and tall trees. The man, likely a park ranger or caretaker, focuses intently on his task, ensuring the sign is clean and legible for visitors. The scene captures a moment of maintenance in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The man's action of wiping the wooden signpost in the video is not smooth."
}
] |
seed46_2510
|
videos/HRA_part2/2510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman with gray hair and glasses sits in a cozy room filled with bookshelves, natural light, and warm tones. He wears a blue shirt and a brown cardigan, appearing thoughtful and engrossed in a thick hardcover book. Moments later, he looks up from reading, revealing a pensive expression. He then turns the page, his eyes scanning the text intently, before pausing again to reflect on what he has read. Throughout the scene, he remains seated in the same position, his attire and surroundings unchanged, creating a calm and intellectual atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand appears deformed, and the pages of the book warp when they are flipped."
}
] |
seed44_3018
|
videos/HRA_part1/3018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, wearing a red jacket and khaki pants, races across a grassy field with a small, bushy-tailed fox hot on their heels. The student's face is full of determination and joy, their shoes kicking up clumps of grass as they sprint. The fox, equally playful, bounds alongside, its red fur matching the student's jacket. The scene is set against a backdrop of autumn trees, their leaves turning shades of gold and orange, with the sun casting long shadows across the landscape, highlighting the energetic chase between the student and the fox.]"
},
{
"from": "gpt",
"value": "Bad. The video shows two small foxes, not just one."
}
] |
seed44_1921
|
videos/HRA_part1/1921.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged doctor, wearing a white lab coat over casual clothes, finds himself unexpectedly digging with a shovel in the middle of a large, empty lot overgrown with grass, as if searching for something specific. The contrast between his professional attire and the task at hand highlights the unusual nature of the situation. He pauses to wipe sweat from his brow, revealing a look of intense determination. In another scene, he continues to dig with the same shovel, now more dirt-stained, while the afternoon sun casts a warm glow over the desolate lot, emphasizing the solitary and strenuous nature of his endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The middle-aged doctor's arm and hand are deformed, and the shovel in his hand is also distorted."
}
] |
seed46_2191
|
videos/HRA_part2/2191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds, focusing solely on zebrafish within a clear, cylindrical fish tank. The vibrant striped patterns on the zebrafish stand out against the neutral background of the tank, which is devoid of any plants or decorations. The water is crystal clear, allowing every detail of the zebrafish, from their distinctive black and white stripes to their delicate fins, to be visible. The tank is illuminated by overhead lighting, casting a soft glow over the swimming zebrafish, highlighting their movement and the rippling effect they create in the water.]"
},
{
"from": "gpt",
"value": "Bad. The fish's body is twisted, and its head is twisted."
}
] |
seed42_3112
|
videos/HRA_part0/3112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, clad in a blue button-down shirt and khaki pants, kneels beside an indoor track designed for mice. The track, illuminated by overhead lights, features a small mouse energetically running within its confines. The engineer observes intently, notebook in hand, ready to record data from the experiment. Behind him, a lab coat hangs on a hook, and a shelf displays various scientific instruments and books, alluding to the academic setting. Throughout the scene, the mouse continues its steady pace on the track, under the watchful eye of the dedicated engineer.]"
},
{
"from": "gpt",
"value": "Normal. The mouse in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1427
|
videos/HRA_part0/1427.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician wearing a brown cap, gray jacket, and blue jeans ascends a rocky cliff face, demonstrating his adventurous spirit. He skillfully plays a small drum-like instrument called a tambourine, attached to his harness, merging his passion for music with his love for climbing. The scene captures his fearless determination, with the tambourine adding a unique touch to his climbing gear, as he conquers the steep rock formation against a dramatic, cloudy sky.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are distorted, face is deformed, legs are twisted, and the hand drum is deformed."
}
] |
seed42_2035
|
videos/HRA_part0/2035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape, a large, hairy mammoth tenderly caresses a smaller mammoth with its trunk, creating a touching scene of familial affection. The larger mammoth, covered in thick, shaggy fur, gently touches the younger one, who stands beside it, also covered in a coat of dark, coarse hair. Both creatures possess impressive tusks, with the adult displaying a more formidable set. They are surrounded by green vegetation and tall trees, with a waterfall visible in the distance, contributing to the serene atmosphere of this ancient bonding moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1032
|
videos/HRA_part0/1032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in a navy uniform with a badge, cap, and sunglasses, stands at the edge of a zoo's flamingo enclosure, where vibrant pink birds congregate. The scene shifts slightly to reveal a clear blue pool within the zoological park, where the officer now interacts with the public, demonstrating water safety techniques. Nearby, children and families watch, some seated on benches under the shade of lush trees, while others lean on the railing, observing the swimming demonstration with interest. Throughout, the police officer remains engaged and attentive, fostering a sense of community and safety among the zoo visitors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1157
|
videos/HRA_part0/1157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station pool, a courageous nurse, wearing a protective spacesuit with a clear helmet, fearlessly swims alongside a non-venomous cobra, which has been specially adapted for space travel. The nurse's spacesuit is adorned with patches representing various medical organizations, highlighting her dedication to healthcare even in the cosmos. The cobra, now a docile companion, glides effortlessly through the water, its scales reflecting the artificial lighting of the space station. This extraordinary scene showcases the integration of healthcare, exotic animals, and space tourism in a serene aquatic environment, encapsulating the essence of adventure and innovation in the final frontier.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_18
|
videos/HRA_part2/18.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 porcupine, identified by its dark brown fur and quills, is seen jumping with surprising agility from branch to branch in a dense forest. The scene captures the porcupine's unique climbing skills as it leaps from one limb to another, highlighting its ability to navigate its arboreal habitat. The video focuses on the porcupine's movements, emphasizing the contrast between its slow, deliberate gait when on solid ground and its sudden bursts of energy as it propels itself through the air. The forest surroundings provide a natural setting, with sunlight filtering through the canopy to illuminate the porcupine's quills during its jumps.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the porcupine jumping as mentioned in the caption."
}
] |
seed46_2835
|
videos/HRA_part2/2835.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet tender scene, a large brown bear gently caresses a smaller, lighter-brown bear against the backdrop of a vast savanna landscape. The two bears sit on the golden grass, under a clear blue sky dotted with a few white clouds. The big bear has its arm around the smaller one, while the other paw is softly stroking the smaller bear's head. Both bears wear collars, indicating they might be part of a conservation program. This heartwarming interaction unfolds in a protected area of the savanna, where wildlife coexists in harmony.]"
},
{
"from": "gpt",
"value": "Normal. The brown bear in the video is basically normal, with slight disharmony."
}
] |
seed46_1730
|
videos/HRA_part2/1730.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown shirt and glasses, is seen in a unique scenario, engaging with a hyena at a public swimming pool. The director, standing at the edge of the pool, interacts with the wild animal, which is swimming in the water, creating an extraordinary juxtaposition of human and beast in an unexpected urban setting. The director's attire, complete with brown shirt and glasses, contrasts with the untamed presence of the swimming hyena, capturing a surreal and captivating moment.]"
},
{
"from": "gpt",
"value": "Normal. The head and limbs of the hyena in the video are generated incorrectly, with the limbs disappearing suddenly in the middle frames."
}
] |
seed44_3142
|
videos/HRA_part1/3142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 an otherworldly ecosystem on an alien planet, a unique creature resembling Earth's beaver crawls through a dense, bioluminescent forest. Its brown fur stands out against the vibrant, glowing flora. The beaver-like being navigates the intricate terrain, its flat tail dragging slightly, as it explores the mysterious landscape filled with towering, luminescent trees and strange, colorful plant life. This extraterrestrial environment, illuminated by an eerie yet beautiful light, provides a surreal setting for the beaver's curious journey.]"
},
{
"from": "gpt",
"value": "Bad. The biological generation in the video is abnormal."
}
] |
seed42_3009
|
videos/HRA_part0/3009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 police officer, clad in a high-tech suit with neon accents, runs across a rugged asteroid surface illuminated by the distant stars. The officer, equipped with a helmet and breathing apparatus, sprints past mining equipment and industrial structures, indicating an asteroid mining operation. With each stride, the officer's suit glows under the harsh lighting of the asteroid's environment, highlighting the action and determination in this dynamic scene set against the backdrop of space exploration and law enforcement.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3207
|
videos/HRA_part2/3207.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 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 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": "Normal. The meerkat in the video is abnormally distorted."
}
] |
seed46_2834
|
videos/HRA_part2/2834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded musician, clad in a black leather jacket and jeans, performs an intense, passionate crawling motion across a vast, icy glacier landscape, his electric guitar amplifying the dramatic scene. The stark, snow-covered mountains and glaciers provide a breathtaking, icy backdrop, contrasting with the musician's raw energy. Throughout the sequence, he continues to crawl, his body language conveying determination and struggle, while the icy wilderness remains a constant, awe-inspiring presence.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1185
|
videos/HRA_part2/1185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning kingfisher bird perches regally on a weathered branch that extends over a serene body of water, its vibrant blue and orange feathers glistening in the sunlight. The bird's piercing gaze is fixed on the water below, hinting at its hunting prowess. Suddenly, it takes flight, its wings a blur of color against the tranquil backdrop of the pond, surrounded by lush green foliage. As it hovers above the water, about to dive, the scene captures the kingfisher's agility and the beauty of nature in a single, captivating moment.]"
},
{
"from": "gpt",
"value": "Bad. The kingfisher's wings and tail in the video have issues, and the kingfisher's beak suddenly disappears at the end."
}
] |
seed46_324
|
videos/HRA_part2/324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating underwater scene, a cluster of moon jellyfish gracefully floats within a vibrant blue ocean, their translucent bell-shaped bodies illuminated by sunlight filtering through the water. These mesmerizing creatures, with their delicate tentacles trailing below, are framed against a backdrop of gently swaying seaweed and distant coral formations, creating a serene and ethereal atmosphere in the depths of the sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2433
|
videos/HRA_part1/2433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished by his brown hair and beard, along with round glasses, is seated in a director's chair on a set resembling a grassland heath. He interacts with a small gerbil, which scurries across the set's surface. The director is shown wiping his glasses with a cloth, revealing his blue eyes, while the gerbil continues its exploration nearby. The backdrop depicts a sunny day on the heath, complete with a blue sky and green vegetation, adding a natural element to the studio setting. Throughout, the director's focus alternates between the gerbil and wiping his glasses, capturing the unique dynamic between the two.]"
},
{
"from": "gpt",
"value": "Bad. The character's face in the video is distorted, the hamster's body is twisted, and the head is distorted."
}
] |
seed42_2585
|
videos/HRA_part0/2585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with a full beard, wearing a straw hat and a checkered shirt, stands waist-deep in a clear blue pond, smiling at the camera. Beside him, a dingo with a red coat and a black-tipped tail swims energetically, its head held high above the water. The farmer's right arm is raised, showing a relaxed and joyful posture, while the dingo continues to swim, its eyes fixed on the farmer. The scene is set against a backdrop of lush greenery and tall trees, creating a serene and picturesque environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.