video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_3150
|
videos/HRA_part1/3150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, possibly his cub, against the backdrop of a lush, green savanna during golden hour. The adult lion, with its voluminous tawny mane, displays affection, while the cub, sporting a lighter coat and smaller stature, responds with innocent playfulness. The heartwarming interaction unfolds under a vast, cloud-dappled sky, with scattered acacia trees and distant mountains completing the serene African landscape. This intimate moment captures the rare display of tenderness and bonding within the lion family, far from the typical fierce and powerful image associated with these animals.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2243
|
videos/HRA_part0/2243.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic musician, clad in a vibrant yellow raincoat and matching hat, stands under a powerful waterfall in a lush, green forest, playing a harmonica with intense focus. The water cascades over mossy rocks, creating a natural stage for the performer. Suddenly, the musician leaps into the air, harmonica still in mouth, capturing a moment of pure joy and freedom amidst the thundering water and verdant surroundings. The scene is framed by towering trees and ferns, emphasizing the connection between music, nature, and human spirit.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_2173
|
videos/HRA_part2/2173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by its distinctive facial stripes and grizzled gray fur, swims through clear, calm water, showcasing its swimming abilities as it propels itself forward with powerful strokes. Its face is partially submerged, displaying its wet snout and closed eyes, indicating its focus on navigating underwater. The badger's body is fully visible, revealing its muscular build and the water droplets clinging to its fur, highlighting its natural habitat and aquatic skills. The scene is set in a peaceful, natural environment, with the badger's swimming motion captured in detail against a backdrop of still water and lush vegetation.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2735
|
videos/HRA_part0/2735.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished by his gray hair and wearing a black turtleneck, is seen playfully dancing in a studio. Beside him, a giraffe, animatedly rendered with large, expressive eyes and long eyelashes, also dances, adding a whimsical touch to the scene. Both the director and the giraffe exhibit exaggerated, comical dance moves, creating a lighthearted and surreal atmosphere. The studio space is filled with vibrant colors and patterns, further enhancing the playful mood. Throughout the scene, the focus remains on the amusing interaction between the dancing director and the animated giraffe.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1809
|
videos/HRA_part2/1809.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 station orbiting Earth, a waiter clad in a sleek silver uniform gracefully floats, serving exotic dishes to the guests seated at a long, transparent table. The space station, designed with curved edges and illuminated panels, offers breathtaking views of the planet below. The waiter, equipped with magnetic boots to assist in crawling and maneuvering through zero gravity, carefully balances a tray filled with delicacies. As he crawls from one guest to another, the curvature of the space station's interior is visible, creating a unique dining experience among the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2881
|
videos/HRA_part0/2881.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in casual attire consisting of a gray hoodie, blue jeans, and white sneakers, diligently scrubs the bathroom floor with a green cleaning rag. The bathroom is modern, featuring sleek white tiles and fixtures, with a hint of daylight filtering in from a nearby window. The student's focused expression and the repetitive motion of scrubbing convey a sense of determination and responsibility. The scene is set in a clean, well-lit space, emphasizing the student's hard work and attention to detail in maintaining the cleanliness of the bathroom environment.]"
},
{
"from": "gpt",
"value": "Normal. The student's legs in the video have generation issues, fingers are deformed, and the face is blurry."
}
] |
seed42_1528
|
videos/HRA_part0/1528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 hermit crab, adorned with a vibrant red and orange color palette, emerges from its seashell home on a sandy beach. The crab, showcasing its intricate, spiraled shell, scuttles across the sand, leaving a trail of tiny footprints. It pauses to explore its surroundings, its eyes on long stalks scanning the environment. Nearby, a group of similar hermit crabs gather, creating a social scene among the rocks and driftwood, all set against the backdrop of a serene, sunlit beach.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1755
|
videos/HRA_part2/1755.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow safety vest and a hard hat, finds himself in a whimsical scenario where he's crawling on his hands and knees through a narrow, dimly lit tunnel. The setting is enhanced by the presence of a stuffed weasel toy, which has somehow joined him on this unusual journey, adding a touch of humor and unexpectedness to the scene. The engineer's serious expression contrasts with the playful atmosphere created by the stuffed animal, making for a unique and memorable visual.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2138
|
videos/HRA_part2/2138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a navy uniform with a badge and gun holster, is kneeling in a park, intently digging with a small shovel into a patch of dirt surrounded by green grass and shrubs. The scene is set under a clear blue sky, with the officer's focus and determination evident as they meticulously excavate the soil. Moments later, the officer, still in their navy uniform and gear, carefully sifts through the dirt with gloved hands, searching for evidence with a serious expression. The location remains the same, a serene park with lush greenery and a cloudless sky overhead.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, and face of the person in the video are distorted."
}
] |
seed42_1635
|
videos/HRA_part0/1635.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park, a creative director, dressed in a casual yet professional attire, intently observes a small, agile mouse crawling along a weathered wooden fence. The mouse, with its curious eyes and twitching nose, explores its surroundings with cautious determination. The director, holding a clipboard and pen, meticulously studies the creature's movements, occasionally jotting down notes. The scene captures the unique interaction between human observation and the natural behavior of wildlife in the controlled environment of a zoo.]"
},
{
"from": "gpt",
"value": "Normal. The rat's body is twisted, and its claws are distorted."
}
] |
seed44_2144
|
videos/HRA_part1/2144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 a helmet, stands in an open field, engaging in a whimsical dance with a kangaroo. Both figures are silhouetted against a vibrant orange sunset, suggesting a surreal and unexpected partnership. The firefighter's movements are energetic and joyful, while the kangaroo, standing on its hind legs, appears to mimic the dance steps, adding a touch of humor and surprise to the scene. Throughout the dance, the firefighter's gear and the kangaroo's natural stance create a dynamic interplay of form and motion, set against the dramatic backdrop of the fading light.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2603
|
videos/HRA_part1/2603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, smoke-filled environment, a firefighter wearing full gear, including a helmet and breathing apparatus, crawls through a confined space. The setting is a high-tech facility, indicated by the presence of an antimatter containment unit, which is a large, cylindrical container with intricate machinery and glowing blue lights, seen in the background. The firefighter's movements are slow and deliberate, emphasizing the hazardous conditions and the need for caution. Despite the challenging circumstances, the firefighter's determination is evident, as they navigate the narrow passage with a flashlight in hand, illuminating the path ahead. The overall scene conveys a sense of urgency and danger, with the firefighter's mission being critical to the safety of the facility and its personnel.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2467
|
videos/HRA_part2/2467.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, energetic ferret with a tan and black fur pattern leaps from a wooden platform in a spacious room, showing its agility and playfulness. The room is filled with natural light, highlighting the ferret's mid-air jump with a backdrop of a large window and potted plants. The ferret lands gracefully on another platform, part of a series of interconnected wooden structures designed for climbing and exploration. It pauses for a moment, looking curious and alert, before making another sudden leap, showcasing its lively spirit and acrobatic abilities against the serene indoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The ferret's paws are twisted, its body is twisted, and its head is twisted."
}
] |
seed42_1367
|
videos/HRA_part0/1367.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a dark jacket, jeans, and a baseball cap, runs energetically across a futuristic space movie set, filled with intricate machinery and high-tech equipment. The set features large, circular structures and metallic surfaces, giving it a distinctly sci-fi aesthetic. The director's movement conveys a sense of urgency and purpose, as he navigates through the complex environment, surrounded by the vast, industrial-like backdrop of the space station set.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is flying, with dislocation and deformity. The legs also show deformity."
}
] |
seed44_2717
|
videos/HRA_part1/2717.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic lion, with a voluminous mane, walks along a sandy beach at twilight, near luxurious beach resorts with glowing lights and lush greenery. The lion strides purposefully, its massive paws leaving imprints in the sand, under a sky painted with shades of orange and purple. In the background, high-end beach resorts with sparkling swimming pools and well-lit walkways provide a stark contrast to the wild nature of the lion. Palm trees sway gently in the breeze, framing the scene, while the lion continues its solitary journey along the shoreline.]"
},
{
"from": "gpt",
"value": "Normal. The lion's movements in the video are slightly unsmooth."
}
] |
seed42_133
|
videos/HRA_part0/133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, standing in a lush, green meadow dotted with vibrant wildflowers, shakes its body vigorously to rid itself of water, its fur rippling and droplets flying in slow motion against the serene landscape. The wolf, with piercing yellow eyes, then looks directly at the camera, its powerful presence commanding attention against the backdrop of nature's beauty. After shaking, it stands still, water dripping from its thick fur, with the sun casting a warm glow on the scene, highlighting the wolf's resilience and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The wolf's tongue and feet were not generated in the video, and there were issues with the legs."
}
] |
seed46_1752
|
videos/HRA_part2/1752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic industrial setting, a mature man with salt-and-pepper hair and a full beard, wearing a dark jacket, gray shirt, and black pants, gently touches and inspects a large turbine blade from a power plant. The blade is massive, with a metallic sheen, positioned horizontally against a backdrop of complex machinery and pipes, indicative of a hydroelectric or nuclear power facility. The man's tender gesture contrasts with the harsh environment, highlighting a personal connection or professional pride in the technology.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1718
|
videos/HRA_part1/1718.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches on a thin branch, its vibrant plumage of green, blue, and orange feathers catching the sunlight. It has a slender body, a long, pointed tail, and a distinctive, curved beak. The bird's eyes are alert, scanning the surroundings for potential prey. Suddenly, it takes flight, its wings a blur of motion as it darts through the air, chasing after an unsuspecting insect. The scene is set against a backdrop of lush vegetation and clear blue skies, capturing the bird's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Normal. The bee-eater's movements in the video are basically normal, with slight coordination issues."
}
] |
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 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 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": "Good. Basically no problem."
}
] |
seed44_2386
|
videos/HRA_part1/2386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, intricate fish with blue fins and a yellow body swims serenely in a clear, turquoise underwater environment, surrounded by lush green seaweed gently swaying in the current. Nearby, a school of smaller, silvery fish dart and weave, their movements synchronized and graceful, creating a mesmerizing display of aquatic life against the vivid backdrop of the underwater world. Above, rays of sunlight filter through the water's surface, casting dappled light on the scene below, highlighting the beauty and tranquility of the ocean depths.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1672
|
videos/HRA_part2/1672.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 habitat, a dingo, wearing a small spacesuit, curiously explores the hydroponic garden, gently caressing the leaves of vibrant green plants under the glow of artificial lights designed to mimic sunlight. Nearby, an astronaut, clad in a full spacesuit, tenderly pets the dingo, creating a bond between man, animal, and the pioneering spirit of space agriculture, all against the backdrop of a vast, starlit universe visible through the habitat's clear dome.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the body of a wild dog wearing a mini spacesuit."
}
] |
seed42_1642
|
videos/HRA_part0/1642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in a brown jacket and beige pants is seen crawling on his hands and knees through a lush, green forest, with ferns and mossy rocks surrounding him. Moments later, a large moose with a majestic rack of antlers stands tall and vigilant nearby, observing the man's unusual behavior. The scene then focuses on the man's face, showing his determination and focus, while the moose continues to watch from a distance, its presence adding a sense of wildness and unpredictability to the forest setting. Finally, the man and the moose share a silent moment of connection, both existing in harmony within the natural world, the man still crawling and the moose standing tall, creating a unique and unexpected encounter in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the man crawling forward on all fours."
}
] |
seed42_2443
|
videos/HRA_part0/2443.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a gray shirt with a name tag, smiles widely at the camera, standing in front of a bustling factory floor filled with machinery and equipment. The scene is alive with the sounds of industry, yet the engineer's cheerful demeanor stands out, conveying a sense of pride and satisfaction in his work environment. His smile is genuine and inviting, offering a human touch to the typically impersonal setting of a manufacturing plant.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2848
|
videos/HRA_part0/2848.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two young boys, one in a red shirt and the other in a blue shirt, dance gleefully on a wooden floor inside a rustic building with log walls and wooden beams. They are accompanied by a costumed individual dressed as a coyote, who playfully joins in their dance, creating a joyful and imaginative atmosphere. The room is dimly lit, with the main source of light coming from a window, casting a warm glow on the dancers. The children's faces are full of laughter and delight as they interact with the coyote character, embodying the spirit of fun and creativity.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3159
|
videos/HRA_part0/3159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed man, wearing a dark gray t-shirt, sits at a wooden table in a dimly lit room with yellow walls and a red ceiling. He lifts a glass of water to his lips, pausing to drink. His gaze is directed away from the camera, towards another person sitting across from him. The atmosphere is relaxed and intimate, with the man's simple attire and the warm, homey setting creating a sense of comfort and familiarity.]"
},
{
"from": "gpt",
"value": "Normal. The character's fingers in the video are not fully generated."
}
] |
seed42_2390
|
videos/HRA_part0/2390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and unexpected scene, a waiter wearing a traditional French uniform, complete with a black vest, white shirt, black bow tie, and black pants, is shown running alongside a full-grown rhinoceros. Both are moving at a steady pace across a lush, green grassland, under a bright blue sky dotted with white clouds. The waiter maintains a focused expression, while the rhinoceros runs with its head held high, creating a surreal and comical juxtaposition of elegance and wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_108
|
videos/HRA_part2/108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique rural setting, a cashier from a local store, dressed in a red apron and black clothing, interacts gently with a brown horse inside a tunnel made of hay bales, creating a warm, intimate atmosphere. The cashier, wearing a red apron over a black outfit, caresses the horse's nose affectionately, with the textured tunnel walls adding depth to the scene. The connection between the cashier and the horse is emphasized by their eye contact, while the rustic tunnel provides a natural, earthy backdrop. Moments later, the cashier, still clad in the red apron and black attire, strokes the horse's mane softly, the bond between human and animal palpable, all within the cozy confines of the hay tunnel.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous."
}
] |
seed46_1281
|
videos/HRA_part2/1281.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."
}
] |
seed42_1793
|
videos/HRA_part0/1793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, futuristic setting, a skilled musician, dressed in a black leather jacket, plays a gleaming silver electric guitar. Nearby, an enormous, friendly bear, adorned with a red bow tie, listens intently, its paw gently resting on the musician's shoulder in a gesture of companionship. Suddenly, a shimmering wormhole opens behind them, revealing a kaleidoscope of colors and swirling galaxies. The musician and the bear look into the wormhole, their expressions a mix of awe and curiosity, as they contemplate the mysteries of the universe together.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the musician's face and hands, as well as the bear's face and paws, in the video has issues."
}
] |
seed42_2075
|
videos/HRA_part0/2075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, covered in shaggy brown fur, walks through a barren, icy landscape with a heavy, deliberate gait. Its large tusks curve upward, and its trunk dangles loosely as it moves, its massive body leaving deep footprints in the snow. The scene is set against a bleak, overcast sky, emphasizing the creature's isolation and the harshness of its environment.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the mammoth in the video are missing, and there is an issue with the nose generation."
}
] |
seed42_2774
|
videos/HRA_part0/2774.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man with a bushy beard and wearing a brown jacket, blue jeans, and a black cap walks side by side with a coyote on a dirt path. They are set against a background of dense green forest and a sky filled with fluffy white clouds. The man, holding a wooden staff, and the coyote, with its distinctive bushy tail, navigate the wilderness together, their unlikely companionship highlighted by the peaceful, natural setting. Their journey unfolds on a trail marked by fallen leaves and tree roots, with the occasional glimpse of other wildlife in the surrounding woods.]"
},
{
"from": "gpt",
"value": "Normal. The man's hands and feet in the video are generated blurry, and the coyote's head and paws are generated abnormally."
}
] |
seed46_1652
|
videos/HRA_part2/1652.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds where a talented violinist, dressed in a vibrant red cloak, plays a melodious tune while gracefully dancing on a vast, celestial stage illuminated by the ethereal glow of Saturn's rings in the distant cosmic horizon. In the foreground, a majestic white horse adorned with golden bridle and flowing mane leaps in perfect sync with the music, its hooves barely touching the stardust-covered stage, embodying a surreal fusion of artistry, nature, and the cosmos.]"
},
{
"from": "gpt",
"value": "Bad. The body movements of the character in the video are not coordinated, and the actions of the white horse are unsmooth."
}
] |
seed42_1444
|
videos/HRA_part0/1444.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene unfolds, featuring a creative individual sitting at an easel, engrossed in painting a detailed landscape, with a curious squirrel perched on the artist's shoulder. Nearby, a tranquil pond offers a serene contrast, its glassy surface broken only by ripples as a squirrel, perhaps inspired by its surroundings, bravely ventures into the water, swimming with surprising grace. The artist, still absorbed in their work, occasionally glances at the unexpected swimmer, capturing the unique moment on canvas.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel's movements in the video are not smooth."
}
] |
seed46_189
|
videos/HRA_part2/189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a gray hoodie and blue jeans, sits cross-legged on a hardwood floor in a room with large windows, a desk with a laptop, and a bookshelf in the background. A curious cat crawls onto the student's lap, interrupting their study session. The student gently strokes the cat, which is adorned with a red collar, as it snuggles into their lap. The room is filled with natural light from the windows, creating a warm and cozy atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The student's legs in the video are generated unreasonably, the fingers have issues, the cat's limbs are partially missing, the body is distorted, the face is blurry, and the positions of the tail and head are incorrect, with the paws also missing."
}
] |
seed42_3183
|
videos/HRA_part0/3183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, hardworking nurse, identifiable by her scrubs—light blue top and dark blue pants—devotes her day off to organizing her garage. She sorts through items, deciding what to keep, with sunlight streaming in from the open garage door. The nurse, now in a different set of scrubs, green top and dark blue pants, methodically arranges tools and equipment on shelves. She pauses to admire her progress, standing amid her organized belongings, which include a bicycle and various household items. Finally, she wipes her brow, pleased with her efforts, as she surveys the tidy space, now a reflection of her meticulous nature.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the nurse organizing the garage, but the actions are not continuous and smooth, with noticeable jerks."
}
] |
seed42_1685
|
videos/HRA_part0/1685.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two individuals, a man and a woman, are engaged in washing a car in a driveway, with lush green grass and a tree visible in the background. The man, wearing a white t-shirt and dark shorts, is seen using a hose to rinse the vehicle, while the woman, clad in a pink tank top and denim shorts, scrubs the car's side with a sponge. Both are focused on their task, with the man holding the hose and the woman applying soap to the car's exterior. They work together harmoniously, the man rinsing and the woman scrubbing, against a backdrop of a sunny day and a neatly kept suburban home.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video uses a sponge to wipe the car, and the man holds a hose to rinse the vehicle, but their movements are not smooth or coordinated."
}
] |
seed42_2407
|
videos/HRA_part0/2407.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red-tailed hawk soars gracefully through a clear blue sky, its powerful wings outstretched against the backdrop of a lush, green forest below. The hawk's piercing golden eyes scan the landscape for prey, its sharp talons ready to strike. The camera captures the intricate feather patterns on its broad wings and tail, highlighting the beauty and strength of this avian predator. As it glides effortlessly, the wind ruffles its feathers, and the sunlight reflects off its body, creating a mesmerizing display of nature's majesty.]"
},
{
"from": "gpt",
"value": "Bad. The red-tailed hawk's gliding movements in the video are not continuous and smooth, showing a lack of coordination."
}
] |
seed42_1047
|
videos/HRA_part0/1047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned farmer, wearing a white shirt, blue overalls, and a wide-brimmed hat, stands in a lush green field under a clear blue sky. He is in mid-throw, tossing hay bales with ease, his strong arms and focused expression showcasing his expertise. The hay bales are wrapped neatly in plastic, indicating a modern farming technique. The farmer's stance, with one leg forward for balance, adds dynamism to the scene, while the rolling hills and distant trees provide a picturesque rural backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1558
|
videos/HRA_part0/1558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, athletic female nurse with short brown hair, wearing a navy scrubs top and gray pants, stretches her body against a white wall. She performs various stretches, including touching her toes and raising her arms overhead, highlighting her flexibility and physical fitness. The room is brightly lit, with a large window and a whiteboard in the background, providing a clinical yet dynamic setting for her routine. Throughout the sequence, she maintains a focused expression, showcasing her dedication to maintaining her physical health in a medical environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2233
|
videos/HRA_part2/2233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, young female musician dons a futuristic silver outfit, complete with a matching helmet, as she energetically performs a dynamic concert on a space station. Surrounded by the vast cosmos, she passionately sings into her microphone, her movements lively and engaging. In a captivating display, she effortlessly sprints across the zero-gravity stage, her silver suit shimmering under the cosmic lights, while continuing to captivate the audience with her powerful voice and electrifying performance. The space station's advanced technology enhances the concert experience, creating an unforgettable spectacle set against the backdrop of the infinite universe.]"
},
{
"from": "gpt",
"value": "Bad. The musician in the video sings very poorly and the movements are uncoordinated."
}
] |
seed42_2869
|
videos/HRA_part0/2869.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional nurse, clad in a light blue scrubs top and dark blue scrubs pants, sits attentively at a desk in a modern hospital setting, her hands deftly typing on a laptop keyboard. Behind her, the bustling hospital environment is visible, adding context to her role. She wears her hair in a neat bun, and her focused gaze is directed at the screen, indicating her concentration on the task at hand. Despite the busy surroundings, she maintains a calm demeanor, highlighting her dedication to her work in the healthcare field.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's fingers in the video are deformed."
}
] |
seed44_2458
|
videos/HRA_part1/2458.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its dark brown coat and impressive, backward-curving horns, walks steadily across a rocky mountain landscape, offering a close-up view of its sturdy hooves gripping the stone surface. It moves with purpose, navigating the rugged terrain with ease, its alert eyes scanning the surroundings. The ibex continues its journey, the camera capturing the detail of its textured fur and the dramatic mountain scenery that serves as its habitat, highlighting the animal's resilience and adaptability in its natural environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1002
|
videos/HRA_part0/1002.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patient teacher, dressed in a khaki shirt and denim jeans, sits on a wooden pier with fishing gear, teaching a young student the art of fishing. The teacher demonstrates casting a line into a serene lake at sunset, the water reflecting the warm hues of twilight. The student, wearing a red cap and a green vest, attentively watches, holding a fishing rod, as the teacher guides them on the pier. The teacher then hands the student a small fish, caught during the lesson, fostering a connection between nature and learning. Throughout, the teacher wears a wide-brimmed hat and a yellow life jacket, while the student is dressed in a red baseball cap, a green fishing vest, and holds a child-sized fishing rod, both immersed in the peaceful act of fishing by the water's edge.]"
},
{
"from": "gpt",
"value": "Bad. No generation of students holding fishing rods, no generation of small fish, and the teacher is not wearing a yellow life jacket."
}
] |
seed46_1720
|
videos/HRA_part2/1720.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 grouper fish, displaying a mottled brown and white skin pattern, swims serenely in clear blue waters, its wide mouth and curious eyes prominent. It passes by a vibrant coral reef, home to smaller, colorful fish darting in and out of the crevices. The sunlight filters through the water, casting dappled light on the sandy ocean floor and highlighting the intricate details of the grouper's body and its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The mouth of the grouper in the video is exaggerated."
}
] |
seed46_1158
|
videos/HRA_part2/1158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant village nestled near a lush watering hole, a tall giraffe gracefully bends its neck to drink, its spots blending harmoniously with the African landscape. Nearby, village life unfolds, with women carrying water pots on their heads, children playing under the watchful gaze of elders, and men engaged in lively conversations. Suddenly, a group of young boys leap into the refreshing waters, their joyful splashes contrasting with the calm surroundings. The scene is completed by a close-up of a giraffe's face, its large eyes and curious expression capturing the essence of this serene environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1963
|
videos/HRA_part1/1963.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, impeccably dressed in a black suit, white shirt, and black tie, stands against a blurred restaurant background. He holds a cocktail shaker in both hands, vigorously shaking it to mix a drink. His eyes are focused on the task, and beads of condensation form on the metal shaker. The action takes place in a dimly lit, upscale bar setting, with the shaker's metallic surface reflecting the ambient light. Throughout the scene, the waiter maintains his professional demeanor, his crisp attire contrasting with the dynamic motion of his hands as he expertly prepares a beverage.]"
},
{
"from": "gpt",
"value": "Bad. The server's fingers in the video are not fully generated."
}
] |
seed44_144
|
videos/HRA_part1/144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, dressed in a casual striped shirt and beige shorts, walks leisurely on a sandy beach, with the ocean's edge just beyond his feet. He pauses for a moment, looking down thoughtfully, before continuing his stroll. The chef, now wearing a straw hat, is seen from behind, walking with purpose along the shoreline, with the vast sea stretching out behind him. In the final scene, he stands still, gazing out at the horizon, his posture conveying a sense of peace and reflection, all set against the serene backdrop of the beach and sea.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_1649
|
videos/HRA_part1/1649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 bright, modern kitchen with white cabinets and countertops, two young children, a boy and a girl, both wearing red aprons over their clothes and chef hats, are attentively stirring ingredients in separate pans on a large, stainless steel gas stove. The boy, with short brown hair, focuses on his task with a serious expression, while the girl, with long blonde hair tied in pigtails, smiles as she stirs. The camera captures the sizzling sound of the food cooking, emphasizing the lively atmosphere. The room is filled with natural light from a window above the sink, illuminating the children as they cook, with a row of hanging pots and pans visible in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_1144
|
videos/HRA_part1/1144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vibrant kitchen filled with the warm glow of overhead lights, a diverse group of four people, two women and two men, collaborate on preparing a feast. One woman, wearing a patterned apron over a floral dress, chops vegetables on a wooden cutting board placed on a granite countertop. Beside her, a man in a chef's jacket stirs a large pot on a professional stove, steam rising from the simmering contents. Another woman, donning a red bandana and denim jacket, carefully seasons a dish with herbs and spices, while the last man, clad in a checkered shirt, monitors the grill, flipping sizzling meats with tongs. The atmosphere is lively, with laughter and clinking utensils adding to the sense of camaraderie and shared purpose among the cooks.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, the arms are twisted, the hands are severely distorted, and the knife in the woman's hand is twisted."
}
] |
seed42_2941
|
videos/HRA_part0/2941.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate woman in a khaki safari outfit gently caresses the muzzle of a rhinoceros, standing on wooden docks overlooking a tranquil lake. The woman, wearing a wide-brimmed hat and a satisfied smile, connects with the rhino, which has a textured hide and a horn. Both are framed by lush greenery and set against a backdrop of serene water, creating a harmonious scene of human-animal interaction. The woman's affectionate touch and the rhino's calm demeanor, along with the peaceful lake in the background, evoke a sense of mutual respect and tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1100
|
videos/HRA_part2/1100.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 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 parallel universe setting, a firefighter, identifiable by his black helmet with a shiny badge, black uniform, and red suspenders, crawls on all fours through a desolate urban landscape. The cityscape features a large, gray building with broken windows and a dark, cloudy sky. The firefighter's movements are slow and deliberate, as if navigating through a hazardous environment. His gear includes a heavy-duty jacket, sturdy gloves, and a breathing apparatus strapped to his back, alluding to the dangerous conditions he faces. Despite the bleak surroundings, the firefighter's determination is evident in his focused gaze and resolute posture.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands are deformed, and the legs are twisted."
}
] |
seed44_2714
|
videos/HRA_part1/2714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic classroom aboard a space station, a compassionate teacher, dressed in a blue jumpsuit with patches and pins adorning her chest, gently caresses the head of a curious alien student. The student, with large, expressive eyes and a small, round body, sits attentively at a desk cluttered with advanced technology and educational tools. The room is filled with natural light from a large window showing a stunning view of Earth and the vast cosmos beyond, emphasizing the peaceful diplomatic mission of education among the stars.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's facial features in the video are generated in a disharmonious manner, and the teacher's hands are generated in a distorted way."
}
] |
seed44_277
|
videos/HRA_part1/277.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda, with its distinctive black and white fur, sits in a lush bamboo forest. It holds a piece of bamboo in its paw, bringing it to its mouth as if tasting the fresh shoot. Suddenly, the panda wipes its mouth with its paw, a natural gesture after eating, leaving a trail of moisture on its furry face. The panda continues to munch on the bamboo, occasionally pausing to wipe its mouth again, all against the serene backdrop of the bamboo forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2832
|
videos/HRA_part0/2832.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a yellow vest and hard hat, finds an unexpected moment of joy as he dances alongside a graceful antelope in a vast, sunlit prairie. The worker, dressed in blue jeans, a white t-shirt, and sturdy boots, moves with surprising agility, mirroring the antelope's leaps and bounds. The antelope, with its distinctive horns and russet coat, engages in this whimsical dance, seemingly unfazed by the unusual partnership. Together, they create a surreal and delightful scene against the backdrop of a clear blue sky and distant rolling hills.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1164
|
videos/HRA_part2/1164.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, donning a casual striped shirt and khaki pants, meticulously vacuums the living room of her cozy home, her curly brown hair bouncing as she moves. The room is filled with natural light, illuminating the space as she expertly maneuvers the vacuum cleaner, ensuring no spot is left untouched. Her dedication to tidiness is evident in the neat arrangement of books on the shelves and the absence of clutter, creating a peaceful environment. This scene captures the teacher's commitment to cleanliness and order, even in her personal life, as she takes a break from her educational duties to tend to household chores.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's movements with the vacuum cleaner in the video are not smooth."
}
] |
seed42_2312
|
videos/HRA_part0/2312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male chef, donning a white chef's uniform with black stripes and a matching cap, meticulously washes dishes in a commercial kitchen. The room is illuminated by bright overhead lights, casting a glow on the stainless steel sink and countertops. Steam rises from the hot water, creating a misty atmosphere. The chef's sleeves are rolled up to his elbows, revealing tattoos, as he focuses intently on cleaning each plate with precision and care. In the background, the bustling kitchen is visible, with other chefs preparing meals and the sounds of clattering pots and sizzling pans adding to the lively ambiance.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm are deformed and distorted, and the plate in his hand is also deformed."
}
] |
seed44_2938
|
videos/HRA_part1/2938.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, middle-aged nurse with blonde hair tied in a bun, wearing a blue scrub top and black pants, is seen in a small, cluttered kitchen. She's meticulously loading a white ceramic plate into the bottom rack of a stainless steel dishwasher, demonstrating her domestic skills. The kitchen is filled with natural light, casting a warm glow over the room, and the nurse's attention to detail is evident as she carefully arranges the dishes. Despite the busy environment, with pots and pans scattered about, she maintains a sense of calm and order as she performs this household task.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the nurse placing the ceramic plate on the lower rack of the stainless steel dishwasher, with movements that are not continuous and smooth, indicating a lack of coordination."
}
] |
seed44_1513
|
videos/HRA_part1/1513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 conservation worker, dressed in a brown long-sleeved shirt and khaki cargo pants, is crawling on his hands and knees across the grassy terrain of a historical site. He meticulously examines the ancient stone structures, his focus intense as he searches for signs of wear or damage needing repair. The historical site, a series of weathered stone ruins set against a backdrop of lush greenery, is both his workplace and passion. His dedication to preserving history is evident in every careful movement, as he works under the open sky, surrounded by the remnants of the past.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1045
|
videos/HRA_part1/1045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his handsome features and casual attire of a gray T-shirt and khaki pants, rakes a pile of autumn leaves in a backyard, surrounded by lush greenery and a wooden deck. He pauses to gaze thoughtfully into the distance, the rake resting on his shoulder, before resuming his task with renewed vigor. The scene is bathed in the warm, golden glow of late afternoon sunlight, casting long shadows across the yard and highlighting the vibrant colors of the fallen leaves. Throughout, the actor's expressive face conveys a range of emotions, from determination to contemplation, all while engaging in the simple, everyday activity of raking leaves.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand in the video was not generated."
}
] |
seed46_1695
|
videos/HRA_part2/1695.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged musician, wearing a black leather jacket, black jeans, and black boots, checks a smoke detector in a modern, sparsely decorated living room. He stands on a white chair, his guitar hanging from a strap around his neck, as he inspects the device with a focused expression. The room features a large window allowing ample natural light, a white couch, and a white coffee table, creating a contrast against the musician's dark attire. The scene captures a moment of domestic responsibility in the life of an artist.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2568
|
videos/HRA_part0/2568.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A giant panda, clad in a red jacket and black pants, races through a city park surrounded by towering skyscrapers, lush greenery, and a clear blue sky. The panda, sporting sunglasses and a determined look, sprints past urban landmarks, including a towering glass building and a bridge. In another scene, the panda leaps over a log, its athletic prowess on full display against the cityscape backdrop. Finally, it continues its run, moving right to left across the screen, with the vibrant city as its dynamic setting.]"
},
{
"from": "gpt",
"value": "Bad. The sunglasses were not generated, and the direction of the panda's run does not match the text description."
}
] |
seed42_3138
|
videos/HRA_part0/3138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek black panther walks with measured steps through a dense, shadowy forest, its eyes gleaming with an almost otherworldly green hue. The majestic feline's coat shimmers under the dappled sunlight filtering through the thick canopy above. With each confident stride, the panther's muscles ripple beneath its inky fur, exuding raw power and grace. The underbrush parts gently as the panther moves, revealing the intricate play of light and shadow on the forest floor, punctuated by the occasional flash of vibrant foliage.]"
},
{
"from": "gpt",
"value": "Normal. The video shows that the black panther's nose and mouth were not generated, and there are missing parts on its limbs."
}
] |
seed46_2083
|
videos/HRA_part2/2083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 with neatly combed brown hair and a black uniform serves a couple seated at a beachside table, the ocean's horizon providing a romantic backdrop. He carefully places two plates of food on the table, his hands displaying a gentle, caressing motion, as if cherishing the art of serving. The couple looks on appreciatively, the man wearing a gray T-shirt and glasses, the woman adorned in a black dress with a plunging neckline. The scene is set during the golden hour, with the sun's rays casting a warm glow over the ocean and the couple, encapsulating a moment of intimate dining by the sea.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand appears deformed, and a white plate suddenly appears in his hand."
}
] |
seed44_2025
|
videos/HRA_part1/2025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 farmer, donning a green jacket, blue jeans, and a gray cap, stands on a ladder propped against the side of a barn, which features a vibrant red exterior and white trim. He is engaged in cleaning the gutters, using a gloved hand to remove debris. The scene is set against a backdrop of lush greenery and a clear blue sky. Moments later, he pauses to survey his work, a pitchfork leaning against the barn wall beside him. The farmer then continues his task diligently, his attire and the pastoral setting creating a vivid image of rural life.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1025
|
videos/HRA_part2/1025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone seagull perches regally atop a wooden post on a deserted, windswept beach, its pristine white feathers ruffled by the salty breeze. The gull, with its sharp yellow beak and piercing eyes, surveys the vast expanse of sea and sky, seemingly contemplating the horizon. Suddenly, it spreads its wings, launching into flight, the camera capturing the intricate detail of its feathered anatomy as it glides effortlessly over the undulating waves. The seagull then returns to its perch, standing tall against the dramatic backdrop of an overcast sky, embodying the spirit of the coast.]"
},
{
"from": "gpt",
"value": "Bad. The bird's wings and beak in the video have issues."
}
] |
seed46_1582
|
videos/HRA_part2/1582.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 brightly lit, modern kitchen, a middle-aged chef with short brown hair, wearing a clean white apron over a black shirt, looks startled upon encountering an alien. The extraterrestrial being, with large eyes and a small body, hovers near the kitchen counter filled with various cooking tools and ingredients. The scene shifts to the chef running hurriedly down a long corridor, passing by stainless steel appliances and cabinets, while casting a fearful glance back at the unexpected visitor. The chase continues as the chef dashes through the bustling kitchen, dodging staff and equipment, with the alien following closely behind, creating a sense of urgency and chaos.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are distorted, face is contorted, and legs are deformed."
}
] |
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 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 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": "Normal. The chimpanzee's movements in the video are not smooth."
}
] |
seed42_2913
|
videos/HRA_part0/2913.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and black tactical gear, is seen in a residential backyard with green grass and trees in the background. He kneels beside a golden retriever, gently washing it with a hose and a sponge. The dog, wearing a red collar, happily shakes off water, splashing the officer who laughs good-naturedly. The scene conveys a heartwarming moment of care and connection between the officer and the dog, set against a backdrop of blue skies and lush greenery.]"
},
{
"from": "gpt",
"value": "Bad. The officer's face is distorted, the hands are distorted, and the dog's face is distorted."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, 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. No hose, wiper, or large sponge was generated."
}
] |
seed44_23
|
videos/HRA_part1/23.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, tropical dry forest, a small, slender weasel with golden-brown fur and a long, bushy tail is seen interacting with its environment. It gently caresses the rough bark of a tree with its nose, then playfully sniffs and rubs against a vibrant green leaf, showcasing its curious nature. The weasel then explores the forest floor, sniffing at various plants and twigs, before it tenderly touches a fallen branch with its paw, as if showing affection to its natural habitat. Throughout the scene, the rich textures of the forest, from the rugged tree trunks to the lush foliage, are captured in stunning detail, providing a vivid backdrop for the weasel's intimate moments.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1583
|
videos/HRA_part1/1583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, neon-lit diner from another dimension, a badger, dressed in a crisp waiter's outfit complete with a bow tie and apron, is seen energetically tap dancing. The animated badger performs intricate dance steps on a checkered floor, surrounded by surreal, cosmic decor, creating an otherworldly atmosphere. This captivating scene is enhanced by the vibrant, pulsating lights that illuminate the peculiar space, giving it an electrifying, interdimensional vibe. The badger's expressive face and lively movements convey a sense of joy and wonder in this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1461
|
videos/HRA_part1/1461.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green deciduous forest, a local worker wearing a straw hat and khaki clothing kneels near a serene riverbank. Suddenly, a jaguar stealthily emerges from the dense foliage, its golden eyes fixed on the water. The wild cat, exhibiting grace and power, leaps into the river for a refreshing swim, its sleek body cutting through the water effortlessly. The worker watches in awe, a harmonious moment captured between human and nature, all set against the backdrop of the vibrant deciduous forest.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2105
|
videos/HRA_part0/2105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a gray shirt and dark pants, attentively sorts colorful laundry in a busy laundromat filled with vibrant washing machines and dryers. He meticulously folds a yellow shirt, revealing a sense of pride in his work. Next, he checks the laundry, holding up a pair of red socks, demonstrating his thoroughness. Then, he loads the washer with various garments, including a green sweater and blue jeans, his actions methodical and precise. Finally, he closes the washer door, presses the start button, and turns to face the camera, his expression conveying satisfaction in a job well done, all within the bustling environment of the laundromat.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and the item in their hand are distorted."
}
] |
seed42_1879
|
videos/HRA_part0/1879.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, balding teacher sits slumped at a large wooden desk, surrounded by stacks of books and papers, in a dimly lit room. His glasses have slipped down his nose, and his head rests on a pile of graded exams, indicating exhaustion from late-night grading. The cluttered desk, filled with educational materials, suggests a dedicated educator overwhelmed by his workload. Behind him, a window reveals the glow of streetlights outside, hinting at the late hour. The teacher's weary posture and closed eyes depict a moment of much-needed rest amidst the demands of his profession.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2850
|
videos/HRA_part2/2850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a blue scrubs top and black pants, stands in a verdant garden filled with lush greenery and colorful flowers. She is engaged in digging a hole with a small spade, her face expressing determination and focus. The sunlight filters through the leaves above, casting dappled shadows on the rich soil beneath her feet. Despite her work, her demeanor conveys a sense of peace and purpose, as if tending to the earth is just another form of care she provides.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2204
|
videos/HRA_part0/2204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a suit jacket, shirt, tie, and glasses, interacts with a porcupine on the edge of a swimming pool. The lawyer gently reaches out to touch the porcupine, which remains calm and still. In another scene, the lawyer is seen swimming in the pool, while the porcupine watches from the side, both under the clear blue sky. The lawyer then sits on a pool chair, the porcupine nestled in his lap, as they both enjoy the sunny day beside the pool, surrounded by lush greenery.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the lawyer swimming in the pool or sitting on a pool chair with a porcupine."
}
] |
seed44_1199
|
videos/HRA_part1/1199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative writer, donning a brown wide-brimmed hat, green shirt, and khaki pants, tends to a lush garden, surrounded by vibrant flowers and verdant plants. She kneels on a green kneeling pad, carefully planting a sapling into the rich soil. Next, she waters the plants with a silver watering can, her actions gentle and nurturing. Then, she pauses to admire her work, a trowel in her hand, a satisfied smile on her face, with the garden in full bloom behind her. Lastly, she sits on a wooden bench, pen in hand, notebook open, capturing her thoughts inspired by the beauty of nature, the garden's colors and textures providing a stunning backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video moves unsmoothly."
}
] |
seed42_2575
|
videos/HRA_part0/2575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young children, a boy and a girl, are energetically shoveling snow in their front yard, surrounded by a wooden fence. The boy wears a brown jacket, gray pants, and a matching hat and mittens, while the girl is dressed in a purple jacket, jeans, and a pink hat and mittens. Both are using small red shovels to clear a path through the fresh, fluffy snow, their faces showing determination and joy. The scene is set against a backdrop of a suburban house, with windows reflecting the bright, sunny day, and a green minivan parked in the driveway, partially covered in snow. The atmosphere is one of cheerful family activity on a crisp, wintry day.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1842
|
videos/HRA_part1/1842.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 capybara runs energetically across a grassy plain, its ears perked up and alert, showcasing its distinctive rodent features. It sprints with determination, its body low to the ground, through a lush, green environment dotted with trees. The capybara's movement is fluid and powerful, its legs propelling it forward with each stride, as it navigates the vibrant landscape under a bright, open sky.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's face, legs, and head are distorted in the video."
}
] |
seed44_1579
|
videos/HRA_part1/1579.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space 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": "Normal. The faces and hands of the alien audience in the video have issues."
}
] |
seed42_143
|
videos/HRA_part0/143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, dressed in a white lab coat over khaki cargo pants and brown leather shoes, runs through a lush, green jungle environment. In his right hand, he holds a clear, plastic container housing a live lizard, which scurries about inside. The doctor navigates through the dense foliage, dodging vines and leaping over fallen logs, his face set with determination as he focuses on his mission. The vibrant greenery of the jungle provides a stark contrast to the doctor's attire, highlighting the unusual nature of this scenario.]"
},
{
"from": "gpt",
"value": "Normal. The character's body is distorted, the face is twisted, the arms are deformed, and the legs are contorted."
}
] |
seed42_2778
|
videos/HRA_part0/2778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform with a badge and a hat, walks alongside a large, majestic rhinoceros. Both traverse a rugged terrain under a bright, sunny sky, creating an unusual yet compelling juxtaposition of authority and wildlife. The officer, equipped with a walkie-talkie on his belt, maintains a calm demeanor, while the rhinoceros, sporting a single horn and thick, wrinkled skin, ambles beside him. The scene unfolds in a spacious, natural environment, far from the urban settings typically associated with law enforcement.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the rhinoceros walking, but the movements are not very continuous and smooth, and there is some lack of coordination."
}
] |
seed44_1712
|
videos/HRA_part1/1712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinctive black markings, perches on a stone statue in the middle of a bustling city square. It has a full, rounded body, and its wings are slightly spread, revealing a flash of green and purple iridescence near the base. Its head, adorned with a small red beak, turns to face the camera, displaying its alertness and curiosity. The bird's legs, pink and sturdy, grip the statue firmly, while its red eyes, surrounded by yellow orbital rings, watch the surroundings keenly. The pigeon is set against a backdrop of urban life, with pedestrians, buildings, and traffic providing a sense of scale and context.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1545
|
videos/HRA_part0/1545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray shirt and khaki pants is seen in a whimsical scene, holding a small mouse on a wheel that matches the color of his shirt. The wheel rotates rapidly as the man watches, his gaze fixed on the active rodent. The scene is set against a plain, white backdrop, with the man's casual attire and focused expression contrasting with the unusual sight of the mouse energetically running on the miniature wheel.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers are not generated in the video, and the rat is generated blurry."
}
] |
seed44_2006
|
videos/HRA_part1/2006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 Evans, is seen in a minimalist living room with white walls and wooden floors, assembling a piece of furniture. He wears a fitted gray T-shirt, dark jeans, and a watch, his short hair perfectly styled. The room is sparsely decorated, featuring a potted plant and a small painting on the wall. The furniture he's building is a sleek, modern design, and he uses a variety of tools, including a screwdriver and an Allen wrench, demonstrating his handyman skills with ease and confidence.]"
},
{
"from": "gpt",
"value": "Normal. The male actor's hand generation in the video is abnormal."
}
] |
seed44_2782
|
videos/HRA_part1/2782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative musician, clad in a black shirt and black jeans, is seen in a studio, wiping down a zebra-striped bass guitar with a cloth. The room is filled with musical instruments and equipment, including a drum set, a keyboard, and various guitars. The musician's focus is intense as they meticulously clean the unique instrument, the zebra-striped bass guitar, ensuring it remains in pristine condition. The scene is intimate, capturing the musician's dedication to their craft amidst a backdrop of musical passion and creativity.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2603
|
videos/HRA_part1/2603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, smoke-filled environment, a firefighter wearing full gear, including a helmet and breathing apparatus, crawls through a confined space. The setting is a high-tech facility, indicated by the presence of an antimatter containment unit, which is a large, cylindrical container with intricate machinery and glowing blue lights, seen in the background. The firefighter's movements are slow and deliberate, emphasizing the hazardous conditions and the need for caution. Despite the challenging circumstances, the firefighter's determination is evident, as they navigate the narrow passage with a flashlight in hand, illuminating the path ahead. The overall scene conveys a sense of urgency and danger, with the firefighter's mission being critical to the safety of the facility and its personnel.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_2997
|
videos/HRA_part0/2997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush tropical dry forest, two smiling children, a boy and a girl, are seen caressing a friendly wild animal, possibly a capybara, against the backdrop of a dense forest with tall trees and patches of sunlight filtering through the leaves. The children wear simple clothing suitable for outdoor adventures, and their joyful expressions convey a sense of connection with nature. They sit on the forest floor covered with dry leaves and twigs, surrounded by various plants and vegetation typical of a tropical dry forest environment. The scene captures a tender moment of human-animal interaction in a natural setting, highlighting the innocence and curiosity of childhood amidst the wonders of the natural world.]"
},
{
"from": "gpt",
"value": "Bad. The number of boys in the video was generated incorrectly, and the action of children petting wild animals was not generated."
}
] |
seed46_2733
|
videos/HRA_part2/2733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 individuals sit side by side on wooden stools, engrossed in the meticulous task of hemming pants. One person, wearing a plaid shirt, focuses intently on the fabric spread across their lap, while the other, donning a gray sweater, holds a pair of scissors, ready to trim the excess material. Both use a sewing machine placed on a rustic wooden table, the sound of the needle punctuating the air as they work diligently. The scene is filled with tools of the trade, including spools of thread, a tape measure, and pins, all set against the backdrop of a warm, welcoming space adorned with shelves of craft supplies.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1852
|
videos/HRA_part0/1852.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, with a casual hairstyle and wearing a dark green jacket over a gray t-shirt, leans against a white wall with a wooden panel. She holds a book titled \"The Great Gatsby\" by F. Scott Fitzgerald, reading it intently during a break. The scene is set in a grocery store aisle, with shelves stocked with products like canned goods and boxes of cereal visible in the background. The cashier's relaxed posture and focused gaze on the classic novel convey a sense of peace and personal time amidst her work environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2381
|
videos/HRA_part1/2381.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cormorant, distinguished by its sleek black body, yellow lower mandible, and piercing eyes, is captured mid-flight over a tranquil lake, showcasing its powerful wingspan against the serene waters below. It then perches on a branch, drying its wings, revealing its unique ability to spread its feathers. Next, the bird plunges into the water, its form streamlined as it hunts beneath the surface, demonstrating its aquatic prowess. Finally, it emerges victorious, a small fish clasped in its beak, highlighting its hunting skills in the wild. Throughout, the cormorant's natural habitat, from the calm lake to the surrounding foliage, is depicted in vivid detail.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and undergo sudden changes."
}
] |
seed42_1414
|
videos/HRA_part0/1414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate female nurse, wearing a traditional white uniform and cap, sits at a vintage wooden desk in a quaint room adorned with antique medical equipment. She attentively sketches a detailed anatomical heart in red pencil on a large pad of white paper, showcasing her artistic skills. The room is illuminated by a single, focused lamp, casting a warm glow over her work. Beside her, a shelf displays various medical tools and books, emphasizing her professional environment. Throughout the scene, she remains engrossed in her drawing, her dedication and precision evident in each stroke.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's actions in the video are basically normal, with slight disharmony."
}
] |
seed44_3172
|
videos/HRA_part1/3172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a navy suit with a crisp white shirt and a patterned tie, sits at an opulent wooden desk. The room is richly decorated with leather-bound books and classic art pieces. He lifts a fork filled with a gourmet meal to his mouth, savoring each bite. The table is set with fine china and silverware, a half-empty glass of red wine standing beside a nearly finished plate of food, indicating a moment of leisure in his busy schedule. Soft ambient light from a nearby lamp illuminates the scene, casting warm shadows across the polished wood surface.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1374
|
videos/HRA_part1/1374.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room, two young siblings, a boy and a girl, are fast asleep in their cozy beds, surrounded by an assortment of toys. The boy, wearing a red superhero costume, lies sprawled across his bed, one arm hanging over the side, with a toy dinosaur resting on his chest. The girl, dressed in a pink nightgown adorned with stars, sleeps peacefully with her favorite teddy bear clutched tightly in her arms. A nightlight shaped like a moon casts a warm glow over the scene, highlighting the innocence and tranquility of childhood sleep.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2604
|
videos/HRA_part0/2604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown leather jacket and stylish glasses, stands confidently at the edge of a swimming pool, meticulously observing an ibex gracefully swimming underwater. The ibex, a sure-footed mountain-dwelling mammal, is shown in a surreal scene, effortlessly gliding through the clear blue water, its horns visible above its head. The director's focused gaze and the ibex's unusual aquatic activity create a captivating and thought-provoking visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The video shows abnormal generation of the bharal, with distorted and deformed limbs in the middle frames."
}
] |
seed46_2143
|
videos/HRA_part2/2143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crystal-clear waters, a vibrant butterfly fish, marked by striking black, yellow, and white patterns, gracefully hovers near a coral reef bustling with life. Sunlight filters through the water, casting a warm glow on the fish and its surroundings. The butterfly fish, known for its intricate design featuring a bold black stripe through the eye and a false eye spot on its tail, explores the nooks and crannies of the reef. It flutters among the corals, which are home to various sea creatures, adding to the dynamic underwater scene. Against this rich backdrop, the butterfly fish's fluid movements and striking colors stand out, creating a captivating display of marine beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1218
|
videos/HRA_part2/1218.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A diligent male artist applies paint to a large, colorful abstract artwork on a vertical easel, positioned outdoors against a sunny, clear blue sky. Dressed in a simple white tank top and khaki cargo shorts, he works intently, surrounded by various tools of his trade including brushes, a palette, and a small table holding additional supplies. His focused expression and the vibrant colors of the painting contrast sharply with the natural greenery and clear sky in the background, creating a dynamic scene of creative energy and artistic passion.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1571
|
videos/HRA_part0/1571.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 capybara is seen swimming across a tranquil body of water, its ears and nose poking above the surface as it propels itself forward with powerful kicks from its webbed feet. The scene is set against a lush, green forest backdrop, with sunlight filtering through the trees and casting dappled shadows on the water. Peaceful ripples spread out from the capybara's movements, creating a serene and captivating view of this aquatic rodent in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's eyes and nose were not generated in the video."
}
] |
seed42_2099
|
videos/HRA_part0/2099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, donning a yellow hard hat, orange safety vest, and blue jeans, sits on a wooden crate at a bustling construction site. Surrounded by scaffolding, concrete mixers, and cranes, he meticulously draws architectural plans using a pencil and a large blueprint sheet laid out on a makeshift plywood table, illustrating his dual skills in both physical labor and design. The scene captures his focused expression and the gritty urban environment, highlighting the blend of creativity and labor in his work.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1094
|
videos/HRA_part0/1094.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space worker, clad in a high-tech, neon-accented spacesuit, traverses a vast, ethereal galactic nebula, the swirling cosmic clouds of reds and purples forming a breathtaking backdrop. The figure moves with purpose, the lights from their suit casting dramatic shadows against the interstellar gas and dust. A closer shot reveals the worker's faceplate, reflecting the mesmerizing nebula, highlighting their isolated journey among the stars. As they walk, the nebula's colors swirl around them, creating a stunning visual of a human amidst the grandeur of the universe.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.