video_id
stringlengths
8
11
video
stringlengths
22
25
conversations
listlengths
2
2
seed44_2073
videos/HRA_part1/2073.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, a slender gazelle, marked by its distinctive tan coat and white underbelly, is shown crawling on the ground, its posture conveying a sense of caution or rest. The scene is framed by lush green grass and distant acacia trees, creating a tranquil yet alert atmosphere. The gazelle's delicate features and attentive ears are highlighted, capturing the essence of its cautious behavior in the wild. Against this serene backdrop, the animal's careful movements are emphasized, offering a unique perspective on the gazelle's survival instincts in its natural habitat.]" }, { "from": "gpt", "value": "Bad. The limbs of the gazelle in the video are missing, and there are issues with the ears." } ]
seed44_1905
videos/HRA_part1/1905.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, imposing goose stands tall on the bank of a misty lake, its yellow beak agape as it emits a loud honk. Its body is a mix of gray and white feathers, with a distinctive black mark around one eye. The goose's webbed feet are visible as it wades into the water, creating ripples that disturb the stillness of the early morning. Against the backdrop of a cloudy sky, the goose swims gracefully, its head held high, exuding an air of confidence and territorial dominance. The scene is set in a natural, serene environment, with the goose being the focal point, highlighting its majestic presence in the wild.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_12
videos/HRA_part0/12.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and gun holster, leaps into the air in the middle of a vast, temperate grassland. The landscape is dominated by knee-high green grasses and a few scattered oak trees, with the horizon stretching far into the distance. The officer's feet leave the ground, capturing a moment of action and energy, as the rolling hills and clear blue sky provide a serene contrast to the dynamic scene. The officer's movements are sharp and decisive, embodying the spirit of law enforcement in the open, wild environment of the grasslands.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2773
videos/HRA_part0/2773.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate female teacher, clad in a gray blazer, white blouse, and dark pants, walks purposefully across a bustling university campus, animatedly discussing the recent discovery of a habitable exoplanet. She gestures enthusiastically, engaging with her students who walk alongside her, their faces alight with curiosity and excitement. The backdrop shifts subtly from the interior of a modern lecture hall, filled with attentive students, to the outdoor campus, where the teacher continues her captivating lesson under the open sky, emphasizing the significance of the exoplanet find. Throughout the scene, the teacher's energy and dedication to teaching are evident, inspiring her students to explore the wonders of the universe.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_142
videos/HRA_part1/142.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of a fresh, whole mackerel fish, glistening under bright lights, lies on a bed of ice. The fish features intricate, dark-blue stripes over a silver body, a hallmark of its species. Its eyes are clear and shiny, indicating freshness, while its mouth is slightly open. The tail fin is curled, and the dorsal fins stand erect, showcasing the fish's natural beauty and texture. Surrounding the mackerel are ice crystals, reflecting light and adding to the icy, clean presentation of the seafood.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_274
videos/HRA_part0/274.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the heart of a vast desert, two young children, a boy and a girl, clad in vibrant red shirts and denim shorts, leap into the air in unison, their silhouettes framed against the golden dunes and a clear blue sky. They jump from a sandy mound, their faces alight with joy and the wind tousling their hair, encapsulating the spirit of youthful adventure. Behind them, a series of similar sand dunes stretch towards the horizon, while the sun casts a warm glow over the entire scene, highlighting the texture of the sand and the children's animated expressions.]" }, { "from": "gpt", "value": "Normal. The character's face, hands, arms, and legs are distorted in the video." } ]
seed46_2927
videos/HRA_part2/2927.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a rural backyard filled with lush greenery and wooden fences, two young children, a boy in a red shirt and blue shorts and a girl in a yellow dress, chase after a lively chicken, their laughter echoing in the sunny afternoon. The boy, with short brown hair, and the girl, her hair tied in pigtails, gleefully pursue the bird across the yard. Their playful antics are framed by a background of vibrant green trees and shrubs, with the chicken's colorful feathers standing out against the natural setting. The scene captures a moment of innocent childhood joy, with the children's faces alight with excitement and the chicken adding a touch of whimsy to the idyllic outdoor space.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_2304
videos/HRA_part0/2304.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, identifiable by his white uniform and toque, finds himself in an unexpected scenario, sharing a swimming pool with a large, brown bear. The pool, surrounded by lush greenery, offers a surreal setting as the chef, showing no fear, calmly floats on an inflatable raft, while the bear swims nearby, seemingly enjoying the water. Both characters coexist peacefully in this unusual scene, the chef maintaining his composure and the bear displaying a gentle demeanor, all under the clear blue sky.]" }, { "from": "gpt", "value": "Normal. The brown bear's eyes in the video are generated slightly forward." } ]
seed42_1912
videos/HRA_part0/1912.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bald musician, donning a black turtleneck, focuses intently on fixing a leaky faucet in an upscale bathroom with marble countertops. Initially, he looks thoughtful, holding a wrench and examining the faucet. Moments later, he is seen tightening the faucet with the tool, his sleeves rolled up, revealing a tattoo on his arm. He then tests the faucet, turning it on and off, ensuring no leaks remain. Finally, he wipes his hands on a towel, looking satisfied with his handiwork, all set against the backdrop of a luxurious bathroom with a marble sink and countertop.]" }, { "from": "gpt", "value": "Bad. The musician's hands, faucet, and wrench in the video have generation issues, with the musician's hands distorted in the middle frames." } ]
seed44_1928
videos/HRA_part1/1928.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, live lobster is displayed prominently in the center of the frame, set against a dark, shadowy background that accentuates its vibrant red shell. The creature's two massive claws are bound by twine, and it rests on a bed of fresh, green seaweed. Its long, segmented body curves slightly, and its many legs are splayed out, giving the impression of strength and vitality. The intricate details of the lobster's textured shell and its small, bead-like eyes are clearly visible in high-definition detail, making this a striking and memorable image.]" }, { "from": "gpt", "value": "Normal. The lobster's legs in the video were not fully generated, and the eyes were not generated at all." } ]
seed44_1029
videos/HRA_part1/1029.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown rat, with patches of white fur, walks methodically across a weathered wooden surface. It pauses momentarily, its whiskers twitching, before continuing its journey. The rat's movements are deliberate, each step calculated, as it navigates the worn planks. Its tail, long and pink, sways gently behind it, adding to the creature's curious demeanor. Throughout the scene, the rat remains the sole focus, walking with purpose on the textured wood, creating a compelling narrative of survival and exploration.]" }, { "from": "gpt", "value": "Normal. The mouse's paws are twisted, its face is deformed, and its tail is slightly deformed." } ]
seed44_1665
videos/HRA_part1/1665.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 full golden mane and regal features, is sprinting across a barren quarry landscape, its powerful muscles rippling under tawny fur. The terrain is rocky and arid, dotted with sparse vegetation, as the lion runs with focused determination, showcasing its strength and agility in the wild. The quarry's rough, uneven ground stretches out behind the lion, while the horizon frames the scene with distant mountains and a clear blue sky, highlighting the vastness of the lion's natural habitat.]" }, { "from": "gpt", "value": "Normal. The lion's running in the video is uncoordinated." } ]
seed46_1300
videos/HRA_part2/1300.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a brown jacket and beige pants, paints a vivid mural featuring a gorilla on a brick wall, surrounded by lush greenery. The gorilla, depicted in motion, seems to be running across the artwork, blending seamlessly with the real-world setting. The artist's focused gaze and deft brushstrokes capture the essence of movement and life, merging the realms of art and nature in a captivating scene.]" }, { "from": "gpt", "value": "Normal. The character's hands are distorted, and the face is twisted." } ]
seed42_1583
videos/HRA_part0/1583.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": "Bad. The apron mentioned in the caption does not appear in the video." } ]
seed42_2943
videos/HRA_part0/2943.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An ibex, distinguished by its dark brown coat and long, curved horns, is captured mid-stride as it sprints across a rocky terrain. The detailed shot focuses on the ibex's powerful legs and hooves, which grip the stone surface, propelling it forward with agility and strength. The ibex's body is outlined against a backdrop of rugged mountains and a clear blue sky, emphasizing its natural habitat. The video highlights the animal's endurance and speed as it navigates the challenging landscape with ease.]" }, { "from": "gpt", "value": "Normal. The goat's movements in the video are not smooth." } ]
seed44_2824
videos/HRA_part1/2824.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and gun holster, leaps over a hurdle set up in a dark matter research facility. The background is filled with high-tech equipment and scientists in lab coats observing the unusual training session. The officer's face is focused, showing determination as they navigate the obstacle course designed to test agility in low-light conditions. The scene highlights the unique intersection of law enforcement training and cutting-edge scientific research.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_2188
videos/HRA_part2/2188.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, dreamlike scene, a firefighter wearing a spacesuit and helmet, equipped with a traditional yellow fire axe, is seen wiping the surface of the moon. The lunar landscape, with its stark contrast of dark shadows and bright highlights, is visible behind him. The firefighter's gloved hand, holding a cloth, carefully cleans a spot on the moon's dusty terrain, creating a stark visual against the desolate background. The American flag, planted nearby, adds a patriotic touch to the unusual juxtaposition of a firefighter performing a mundane task in an extraordinary setting.]" }, { "from": "gpt", "value": "Bad. The firefighter's hands and feet, and the axe were generated abnormally in the video." } ]
seed46_2474
videos/HRA_part2/2474.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a black outfit with a leather jacket, walks down a dimly lit street at night, a guitar case in hand, as a lizard scurries across the cobblestones beside him. The scene is set under the glow of a single streetlamp, casting long shadows and highlighting the textured walls of the surrounding buildings. The musician, with tousled dark hair and a determined look, strides purposefully forward, while the agile lizard, with its distinctive green and brown scales, moves swiftly alongside, both seemingly on a mysterious journey through the urban landscape.]" }, { "from": "gpt", "value": "Bad. The musician's face and hands, as well as the lizard, are abnormally generated, with the lizard severely distorted in the middle frames." } ]
seed44_2027
videos/HRA_part1/2027.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green swamp environment teeming with life, two young children, a boy and a girl, are seen energetically running and exploring. The boy wears a red t-shirt and khaki shorts, while the girl dons a yellow dress, both dressed appropriately for the outdoors. They splash through shallow water, their faces lit up with joy and wonder, surrounded by tall cattails and lily pads. A wooden bridge can be glimpsed in the background, adding to the sense of adventure in this vibrant natural setting.]" }, { "from": "gpt", "value": "Bad. The video clearly shows children running and exploring, but there is a lack of coordination." } ]
seed44_134
videos/HRA_part1/134.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, identifiable by their beret and smock, kneels on a lush, alien landscape, sketching a capybara. The capybara, depicted in a relaxed posture, is the focal point, sitting amidst Martian flora. The scene is illuminated by the vibrant hues of a Martian sunset, casting an ethereal glow across the terrain. The artist's concentrated expression and the capybara's calm demeanor create a sense of tranquility, enhanced by the distant, rugged Martian mountains and the unique atmospheric conditions of the planet, which contribute to the vivid sunset colors. The artist's tools, including a palette and brushes, are scattered nearby, adding to the creative atmosphere of the scene.]" }, { "from": "gpt", "value": "Bad. The character's face is distorted, and the hands are twisted." } ]
seed42_2087
videos/HRA_part0/2087.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 prison, dimly lit by neon blue lights, two figures, a male and female inmate, plot their daring escape. They wear matching orange jumpsuits with black stripes, symbolizing their confined status. Suddenly, they engage in a synchronized dance, using their movement as a clever ruse to distract guards. Their dance, a blend of hip-hop and contemporary styles, captivates the robotic guards, allowing the inmates to stealthily make their way towards freedom. The prison's cold, metallic interior contrasts sharply with the dynamic energy of their dance, highlighting the tension between confinement and liberation. Throughout, the focus remains on the two dancers, their precise movements and the prison's stark, oppressive environment.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_3060
videos/HRA_part0/3060.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, wearing a white tank top, blue jeans, and black sneakers, meticulously cleans a car using a sponge and bucket filled with soapy water, under a clear blue sky. He begins by pouring water from a green hose nozzle onto the vehicle, the bubbles catching the sunlight. Next, he uses a sponge to scrub the car's hood, his focused gaze and dedicated posture conveying his commitment to the task. Then, he rinses the suds away with the hose, revealing the car's now gleaming surface. Lastly, he wipes down the clean car door with a cloth, the contrast between the dirty rag and the shiny paintwork highlighting the effectiveness of his efforts.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_2185
videos/HRA_part2/2185.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an unexpected juxtaposition, a small, fluffy hamster wearing a red life jacket floats in a clear plastic ball filled with water. This unique scene unfolds against the backdrop of an industrial area, complete with factories, smokestacks, and large metal containers. The hamster appears content and relaxed, paddling gently within the ball as it bobs on the water's surface near the edge of a pool. The industrial landscape, featuring tall buildings, cranes, and machinery, provides a striking contrast to the innocent and playful hamster enjoying its unconventional swim.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_2025
videos/HRA_part2/2025.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, 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 walking action appears deformed, and the man's legs and arms show deformities and distortions." } ]
seed44_1898
videos/HRA_part1/1898.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, wearing a straw hat and blue overalls, is seen playfully splashing water at a curious jackal on the banks of a serene lake during golden hour. The farmer then dives into the water, swimming with ease, while the jackal cautiously wades in, its ears perked up and attentive. They engage in a lighthearted game, the farmer swimming and the jackal paddling near the shore, both enjoying the cool waters under the warm, golden glow of the setting sun.]" }, { "from": "gpt", "value": "Normal. The farmer's action of quietly diving into the water to swim is mostly normal, but there is a slight lack of coordination." } ]
seed42_2462
videos/HRA_part0/2462.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, distinguished by its large ears and robust body, is sprinting across a sunlit savanna, leaving a trail of dust in its wake. Its skin, textured and gray, contrasts beautifully with the lush green vegetation surrounding it. The elephant's tusks, curved and formidable, add to its regal appearance as it runs with surprising speed and grace through the open plains, showcasing the powerful muscles rippling beneath its thick skin.]" }, { "from": "gpt", "value": "Normal. The elephant's running in the video is basically normal, but there is slight movement disharmony." } ]
seed42_1737
videos/HRA_part0/1737.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, wearing a brown jacket and khaki pants, sits on a wooden chair in a spacious, empty room with high ceilings and large windows, stitching a button onto his garment with a look of intense concentration. The button, which matches the color of his jacket, is being sewn back on with a strong thread, as the man holds the fabric taut with his free hand. The room is bathed in soft, natural light, casting gentle shadows across the floor and highlighting the dust motes that dance in the air. The janitor's face is set in a serious expression, his brow furrowed in determination as he carefully guides the needle through the fabric, ensuring the button is securely fastened. Behind him, a row of neatly arranged brooms and cleaning supplies stand against the wall, a testament to his hard work and dedication to keeping the space clean and orderly.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2854
videos/HRA_part2/2854.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone coyote, with a gray and cream coat, runs across a sunlit prairie, its ears perked and tail held low. It bounds through the tall grass, leaving a slight dust cloud in its wake, indicating speed and purpose. The coyote's focused gaze and agile movements showcase its hunting prowess, as it navigates the open landscape under a clear blue sky. Moments later, it leaps over a small obstacle, demonstrating its agility and grace, all while maintaining its steady pace across the vast, golden plains.]" }, { "from": "gpt", "value": "Bad. The video clearly shows the coyote running and jumping on the grassland, but the movements are not continuous and smooth, and there is a lack of coordination." } ]
seed46_1587
videos/HRA_part2/1587.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of a grouse's head showcases its distinctive red facial wattles and curious, alert expression, set against a blurred forest background. The bird's intricate feather patterns are highlighted, particularly the dark speckles on its brownish-grey plumage. Its sharp, intelligent eyes and slightly open beak convey a sense of awareness and readiness in its woodland habitat. The grouse is perched on a branch, surrounded by lush greenery, with rays of sunlight filtering through the leaves, illuminating its feathers and the rugged bark of the tree.]" }, { "from": "gpt", "value": "Normal. The generation of chicken in the video is unreasonable." } ]
seed46_3064
videos/HRA_part2/3064.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged male doctor stands in a well-lit hospital corridor, wearing a stethoscope around his neck and a white lab coat over a crisp, button-down shirt and slacks. He holds a clipboard in his right hand, reviewing patient records intently. Behind him, the hallway is bustling with medical personnel and equipment, conveying the busy atmosphere of a healthcare facility. The scene captures the essence of a dedicated healthcare professional in the midst of his duties, surrounded by the sights and sounds of a working hospital.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_2844
videos/HRA_part1/2844.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a khaki shirt and beige pants, is seen wiping down an ancient, weathered stone structure at a historical site, with a dingo curiously observing from a distance. The engineer, wearing safety glasses and latex gloves, meticulously cleans the surface using a microfiber cloth, revealing intricate carvings and details. The dingo, standing on the lush grass nearby, watches intently with its ears perked up, adding a touch of wildlife intrigue to the scene. The historical site, featuring crumbling stone walls and archways, is bathed in warm sunlight, casting dramatic shadows and highlighting the textures and history of the location.]" }, { "from": "gpt", "value": "Normal. The character's movements in the video are basically normal, with slight awkwardness." } ]
seed46_2630
videos/HRA_part2/2630.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lustrous, red-cooked lobster is presented on a simple white plate, its large, meaty tail curled gracefully. The claws, one broken open to reveal tender, succulent flesh, are garnished with fresh, green parsley. Steam gently rises from the hot shell, hinting at its recent emergence from boiling water. The setting is a rustic wooden table, adorned with a crisp, white cloth, where the lobster takes center stage under natural lighting, casting a subtle shadow that accentuates its texture and color. A small cup of clarified butter sits nearby, ready to enhance the rich, briny flavor of the lobster meat.]" }, { "from": "gpt", "value": "Normal. The lobster's head was not generated in the video, and the body is incomplete." } ]
seed46_1519
videos/HRA_part2/1519.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 middle-aged doctor, wearing a white lab coat over a navy blue shirt, sits in a cozy, dimly lit pub, sipping a glass of red wine. The pub is filled with the warm glow of hanging lights and a fireplace, creating a relaxed atmosphere. The doctor, with short brown hair and a neatly trimmed beard, leans back in his chair, holding the stem of the wineglass, and gazes thoughtfully into the distance. The scene conveys a sense of calm and tranquility, with the doctor enjoying a moment of respite from his busy medical career.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2165
videos/HRA_part2/2165.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, ancient-looking turtle with a mossy, textured shell slowly moves across a lush, green forest floor, surrounded by vibrant ferns and fallen leaves. Its wise, gentle eyes and wrinkled skin reflect its age and resilience. Nearby, a small stream glistens in the dappled sunlight, while tall trees tower overhead, creating a serene, natural habitat for this majestic creature. The turtle continues its unhurried journey, embodying the peaceful, enduring spirit of the forest.]" }, { "from": "gpt", "value": "Normal. The turtle's movement in the video is basically normal, but there is slight uncoordination." } ]
seed42_1110
videos/HRA_part0/1110.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a crisp white shirt and black vest, sprints across a vast, barren lunar landscape, the iconic first steps of Neil Armstrong visible in the distance. Dust from the moon's surface billows behind him as he races, his movements fluid and effortless in the low gravity environment. A lunar module sits in the background, a stark contrast to the elegant attire of the sprinting waiter, who carries a silver serving tray in one hand, merging the worlds of fine dining and space exploration in a surreal scene.]" }, { "from": "gpt", "value": "Bad. The human leg shows deformities and mutations." } ]
seed44_1426
videos/HRA_part1/1426.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, clad in a white shirt, beige cardigan, and khaki pants, abandons his usual set to embark on a new project - painting a room. Surrounded by the tools of this different trade, including a paint can, roller, and painter's tape, he applies blue paint to the walls with precision and focus. His directorial experience is evident in the way he methodically transforms the space, bringing the same level of detail and vision to this task as he would to directing a scene. The room, filled with natural light, highlights the process as he adds color to the previously neutral walls.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_2795
videos/HRA_part1/2795.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a gray beard, wearing a gray t-shirt, blue jeans, and green rubber boots, tends to his garden on a bright, sunny day. He begins by standing near a lush green hedge, holding a pair of gardening shears, ready to prune. In the next scene, he is seen pruning the hedge with precision and care, showcasing his expertise. Then, he carries a large brown bag, possibly for collecting clippings, while walking across his well-manicured lawn. Finally, he waters the plants with a hose, ensuring each one receives the necessary hydration, all set against the backdrop of a clear blue sky.]" }, { "from": "gpt", "value": "Bad. The character's face, hands, and arms are distorted in the video." } ]
seed44_149
videos/HRA_part1/149.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, clad in a tailored gray suit, white shirt, and striped tie, rearranges furniture in a sophisticated office space. Initially, he thoughtfully observes the room, considering the layout. Then, he pushes a modern desk aside, revealing a keen eye for design. Next, he skillfully pulls a sleek office chair into place, demonstrating attention to detail. Finally, he stands back, hands on hips, surveying his newly organized workspace with satisfaction, the room's minimalist decor and natural light enhancing the professional atmosphere.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_2894
videos/HRA_part1/2894.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy kitchen with wooden cabinets and cream walls, two young children, a boy and a girl, stand on small stools by the sink, their sleeves rolled up. They are happily washing dishes together, the girl scrubbing a plate with a pink sponge, while the boy rinses a glass under the faucet. The room is filled with natural light from a window above the sink, casting a warm glow on the soap bubbles and wet surfaces. A few clean dishes are stacked neatly on a drying rack nearby, and a colorful dishcloth hangs over the tap, completing the scene of domestic harmony and teamwork.]" }, { "from": "gpt", "value": "Bad. The facial generation of children in the video is blurry, and the fingers are deformed." } ]
seed46_1594
videos/HRA_part2/1594.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green zoological park, a dedicated zookeeper clad in khaki shorts, a gray T-shirt, and a cap runs along a path lined with palm trees, demonstrating his commitment to fitness within the serene surroundings. The camera captures him passing by enclosures housing various animals, highlighting the unique setting of his workout. As he jogs, the peaceful atmosphere of the park is evident, with glimpses of giraffes, elephants, and monkeys in the background, creating a vivid contrast between human activity and the natural world.]" }, { "from": "gpt", "value": "Normal. The character's body is twisted, with distorted arms and legs." } ]
seed42_1785
videos/HRA_part0/1785.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, wearing a casual gray shirt, is captured in high definition as he dances alone on a vast, luxurious resort balcony. The setting sun illuminates the horizon, casting a warm glow on the scene. He moves gracefully, his body language expressing pure joy and freedom. In the background, a sprawling, upscale resort with numerous balconies and lush greenery can be seen, highlighting the exotic location. The actor's movements are fluid and expressive, conveying the essence of a carefree spirit embracing the beauty of his surroundings.]" }, { "from": "gpt", "value": "Normal. The character's movements are not smooth." } ]
seed42_2806
videos/HRA_part0/2806.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, wearing a dark blue jacket, beige pants, and carrying a brown backpack, runs along the docks on a misty day, passing by large ships and industrial buildings. He stops momentarily to gaze at the water, his reflection visible in the wet pavement. Continuing his run, he passes wooden benches and green spaces, with the city skyline in the distance. Throughout his journey, he remains engrossed in his thoughts, occasionally glancing down at a notebook tucked into his backpack, the colors of the docks' wood and metal contrasting against the muted tones of the surroundings.]" }, { "from": "gpt", "value": "Normal. The video shows the writer running along the dock, the movements are basically normal but slightly uncoordinated." } ]
seed44_2217
videos/HRA_part1/2217.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed writer, wearing a gray t-shirt, sits at a desk in a modern, minimally decorated room with large windows and a wooden floor, yawning widely as he leans back in his chair. The room is sparsely furnished, featuring a desk lamp and a painting on the wall. As the scene progresses, the yawning writer, now seen from the side, wears a black cap and glasses, revealing more of his appearance. He continues to yawn, appearing tired yet relaxed, as he rests his head on his hand, gazing out the window. Throughout, the setting remains a contemporary space with ample natural light and simple decor.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_2898
videos/HRA_part2/2898.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large bull moose, distinguished by its dark brown fur and impressive rack of antlers, strides purposefully through a shallow, crystal-clear river. The water, teeming with lush vegetation, reflects the vibrant greenery of the surrounding forest, creating a serene and picturesque scene. The moose, with its shaggy coat and large, expressive eyes, moves with a graceful determination, its massive body rippling with each step it takes across the riverbed. The dense forest looms in the background, casting dappled shadows onto the water's surface, adding depth and texture to the landscape.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_2149
videos/HRA_part2/2149.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant display under the aurora-lit sky, several figures clad in traditional fur coats and hats, reminiscent of indigenous Siberian attire, gather around a blazing bonfire set amidst the dense taiga forest. They begin to sway in unison, their movements a harmonious blend of ancient and modern dance styles. The firelight flickers across their faces, casting dramatic shadows as they leap and twirl, their feet barely touching the snow-covered ground. The camera captures the dancers from various angles, emphasizing the connection between their lively steps and the serene, starlit wilderness that surrounds them.]" }, { "from": "gpt", "value": "Bad. The character in the video has a twisted body, head, feet, legs, and arms." } ]
seed42_2182
videos/HRA_part0/2182.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dedicated nurse, wearing a classic white uniform and cap, is seen attentively checking a series of smoke detectors in a pristine hospital corridor. She methodically inspects each device, her actions conveying a sense of responsibility and care for patient safety. With a focused gaze and a tool in hand, she demonstrates her commitment to ensuring that the smoke alarms are functioning properly, maintaining a vigilant stance against potential hazards in the healthcare facility. Throughout the process, she moves from one detector to another, her white shoes echoing softly on the polished floor, reinforcing the importance of routine safety checks in a medical environment.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_2654
videos/HRA_part0/2654.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a black jacket, jeans, and a gray shirt, stands on a bustling movie set under bright lights. Holding a megaphone in one hand and gesturing emphatically with the other, he directs actors and crew members with passion and precision. The set is filled with vintage cars from the 1950s, indicating a period drama, while the director's focused gaze and expressive body language convey his dedication to capturing the perfect shot. Surrounded by a diverse cast and crew, he moves with purpose, demonstrating his leadership and vision in the dynamic environment of a film production.]" }, { "from": "gpt", "value": "Normal. The loudspeaker, the director's face and hands, and the generation of actors and staff in the video are abnormal." } ]
seed46_2727
videos/HRA_part2/2727.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin leaps from the crystal-clear ocean waters, its streamlined body glistening in the sunlight. The vibrant blue and silver hues of its scales contrast beautifully against the turquoise backdrop. In another scene, the marlin swims gracefully beneath the surface, its elongated bill leading the way as it navigates the underwater world. Surrounded by schools of smaller fish and the lush marine environment, the marlin embodies the power and elegance of life beneath the waves.]" }, { "from": "gpt", "value": "Bad. The video did not generate the long beak of the sailfish, and the sailfish overall does not match reality." } ]
seed42_2976
videos/HRA_part0/2976.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal space setting illuminated by cosmic lights, a brave firefighter in full gear, complete with a helmet and breathing apparatus, stands solemnly beside a wise-looking badger, both participating in a mysterious, otherworldly religious ceremony. The ceremony takes place on a floating platform surrounded by stars, galaxies, and celestial bodies. The scene then shifts underwater, where the firefighter and the badger are swimming gracefully in a clear, tranquil pool, with the firefighter's gear now adapted for aquatic environments. The pool is encircled by ancient, space-themed ruins, giving the impression of an extraterrestrial civilization. Throughout the sequence, the two characters maintain a sense of reverence, as if honoring a sacred tradition in this unique blend of terrestrial heroism, woodland wisdom, and cosmic spirituality.]" }, { "from": "gpt", "value": "Normal. The badger's movements in the video are not smooth." } ]
seed44_2890
videos/HRA_part1/2890.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, meticulously irons his clothes in a modern, minimalist bedroom. The room features wooden floors, a large window with white blinds, and a white bed. The doctor stands at an ironing board placed next to a wooden dresser, focusing intently on smoothing out the wrinkles in a garment. The scene conveys a sense of professionalism and attention to detail, as the well-groomed doctor prepares his attire with care.]" }, { "from": "gpt", "value": "Bad. The character's face is distorted, hands are distorted, and the item in hand is distorted." } ]
seed42_2462
videos/HRA_part0/2462.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic African elephant, distinguished by its large ears and robust body, is sprinting across a sunlit savanna, leaving a trail of dust in its wake. Its skin, textured and gray, contrasts beautifully with the lush green vegetation surrounding it. The elephant's tusks, curved and formidable, add to its regal appearance as it runs with surprising speed and grace through the open plains, showcasing the powerful muscles rippling beneath its thick skin.]" }, { "from": "gpt", "value": "Normal. The limbs of the elephant in the video are missing, and there is an issue with the tail generation." } ]
seed42_1466
videos/HRA_part0/1466.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished male lawyer, clad in a dark suit and white shirt, sits in a modern office environment. He is backlit by a large window, casting a subtle shadow on his face as he leans forward, hands clasped together. His eyes are closed, and his facial expression conveys deep concentration, possibly during a moment of meditation or focused breathing exercises. The office is sparsely decorated, featuring only a desk, chair, and the window, emphasizing the man's presence and the tranquility of the scene.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2348
videos/HRA_part0/2348.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dressed in traditional African garb, comprised of a tan shirt, green shorts, and brown sandals, performs an impressive jump over a prone hyena in the middle of a sandy desert. The hyena, positioned on the ground with its head turned toward the man, exhibits a relaxed demeanor. The man's leap is captured mid-air, showcasing his athletic prowess against the stark, arid landscape, with distant mountains providing a scenic backdrop. The scene conveys a sense of adventure and cultural intrigue, highlighting the unique interaction between human and wildlife in a dramatic, yet peaceful, encounter.]" }, { "from": "gpt", "value": "Normal. The man's legs and arms slightly deform when he jumps." } ]
seed42_2673
videos/HRA_part0/2673.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in casual attire, leaps into the air against the backdrop of a vibrant village scene. The village is set amidst lush greenery, with colorful houses lining the cobblestone streets. The student, wearing a yellow t-shirt and denim shorts, is captured mid-jump, their arms spread wide in exhilaration. The scene is filled with natural beauty, from the verdant foliage to the clear blue sky above. As the student jumps, they seem to embody the spirit of youth and adventure, their face alight with joy and energy. Behind them, the village bustles with life, with locals going about their daily routines and children playing nearby. The overall effect is one of vitality and happiness, capturing a fleeting moment of pure delight in a picturesque village setting.]" }, { "from": "gpt", "value": "Bad. The student's jumping in the video is very unsmooth, and the movements are uncoordinated." } ]
seed46_2110
videos/HRA_part2/2110.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a gray jacket and khaki pants, sits cross-legged on a lush green meadow, gently caressing a docile water buffalo. The buffalo, with its large frame and distinctive horns, stands calmly beside a small body of water, accepting the student's affectionate touch. The student's serene facial expression and the peaceful surroundings, including trees and distant mountains, create a harmonious atmosphere. The scene is bathed in warm sunlight, casting a golden hue over the student and the buffalo, highlighting the tender connection between human and animal in a rural setting.]" }, { "from": "gpt", "value": "Normal. The student's actions of petting the water buffalo in the video are basically normal, but there is some lack of coordination." } ]
seed42_2883
videos/HRA_part0/2883.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant scene unfolds as a talented musician, clad in a red fox-themed costume, plays a golden saxophone under the neon lights of a bustling city street. The fox's expressive face, complete with whiskers and gleaming eyes, comes alive as it dances energetically, captivating the crowd with its infectious rhythm. Surrounded by urban graffiti and the glow of city lights, the fox's movements are fluid and dynamic, its tail swaying in time with the music. The atmosphere is electric, with onlookers swaying to the beat, all drawn into the enchanting performance of this unique fox-musician.]" }, { "from": "gpt", "value": "Normal. The musician wearing a fox costume has a twisted head, twisted hands, and the object in their hands is also twisted." } ]
seed46_1264
videos/HRA_part2/1264.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, wearing a maroon shirt, navy vest, beige khaki pants, and brown hiking boots, pauses on a trail to gaze at a breathtaking mountain vista, his backpack leaning against a tree. Moments later, he sits on a rock, attentively examining something in his hands, perhaps a map or a natural specimen, with the stunning landscape as his backdrop. Then, he hikes uphill, trekking poles in hand, his outfit unchanged, as the lush greenery and distant mountains frame his journey. Finally, he stands at a scenic overlook, savoring the panoramic view, his maroon shirt, navy vest, beige pants, and brown boots standing out against the natural beauty.]" }, { "from": "gpt", "value": "Normal. The character's movements in the video are not smooth." } ]
seed46_1835
videos/HRA_part2/1835.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [On a futuristic space movie set, a life-size animatronic moose, sporting a metallic silver spacesuit, is being wiped down by a crew member in a pristine white lab coat. The set is dominated by a large, circular spaceship door with hexagonal bolts, and features a control panel with green buttons and switches. The moose, with its antlers adorned with blinking red lights, stands against a backdrop of sleek, metallic walls and a floor grid, creating a surreal juxtaposition of nature and sci-fi technology. The crew member meticulously wipes the moose's suit, ensuring it's ready for its intergalactic scene, while the set's high-tech details add to the otherworldly atmosphere.]" }, { "from": "gpt", "value": "Bad. No control panel with flashing red lights, green buttons, and switches was generated." } ]
seed42_2195
videos/HRA_part0/2195.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, temperate deciduous forest during autumn, a dedicated park ranger wearing a brown uniform and a wide-brimmed hat runs along a winding dirt trail. Surrounded by tall, leafy trees with vibrant orange and red foliage, the ranger navigates the path with focused determination. As the camera follows, we see the ranger's strong legs propelling them forward, their breath visible in the crisp air, and their eyes alert for any signs of wildlife or forest health issues. The scenery is alive with the sounds of rustling leaves, chirping birds, and the occasional distant call of a wild animal, all contributing to the immersive experience of running in a breathtaking natural environment.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed42_2203
videos/HRA_part0/2203.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic man named Jay, donning a gray blazer, black t-shirt, and jeans, stands in a dimly lit room with a warm color tone. Initially, he is seen in profile, gazing into the distance with a reflective look. Jay then turns to face the camera, his expression conveying a sense of determination and strength. Next, he smiles warmly, exuding confidence and approachability. Finally, Jay closes his eyes, appearing to savor a private moment of joy, all while the ambient lighting enhances the intimate atmosphere of the scene.]" }, { "from": "gpt", "value": "Normal. Missing the final scene of closing eyes." } ]
seed44_190
videos/HRA_part1/190.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic jaguar, marked by its distinctive black spots on tawny fur, walks purposefully across a lush, green savanna landscape under the dappled shade of scattered trees. Its powerful muscles ripple beneath its coat as it strides with feline grace, the camera capturing every detail in high definition. The surroundings are alive with the sounds of nature, from chirping birds to the distant call of other wildlife, creating an immersive environment that highlights the beauty and power of this wild cat in its natural habitat.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_2710
videos/HRA_part1/2710.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling Colin Farrell, is seen walking through a dense forest with tall trees, wearing a brown jacket, jeans, and boots. Suddenly, the scene changes to reveal a prehistoric setting, where the actor now finds himself casually strolling beside a woolly mammoth. Both the actor and the mammoth continue their leisurely walk together, with the mammoth's massive frame towering over the actor, who appears unfazed by the extraordinary situation. They meander through the ancient landscape, surrounded by lush vegetation and underbrush, creating a surreal juxtaposition of eras and species.]" }, { "from": "gpt", "value": "Bad. The video shows the actor walking leisurely alongside a long-haired elephant, but the movements are not very continuous and there is a lack of coordination." } ]
seed46_1931
videos/HRA_part2/1931.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [On a sandy beach under clear blue skies, three young children, two boys and a girl, wearing colorful swimsuits and sunglasses, jump gleefully into the air in slow motion. Their silhouettes are highlighted by the sun, casting playful shadows on the sand. They leap again, this time with the vast ocean as their backdrop, their laughter echoing in the warm coastal breeze. Their final jump is captured mid-air, faces full of joy and wonder, the sea gently lapping at the shore behind them, encapsulating the essence of carefree childhood summers.]" }, { "from": "gpt", "value": "Bad. The children's legs and arms have become deformed and misshapen, and their bodies have also undergone twisting deformities." } ]
seed46_2574
videos/HRA_part2/2574.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a yellow safety vest and black trousers, stands amidst the towering structures of an oil refinery under the vast sky. He is seen wiping down the massive pipes, his actions emphasizing the scale of the mammoth industrial landscape around him. The refinery, with its intricate network of pipes and tanks, looms large in the background, highlighting the solitary figure of the worker engaged in his task. The setting is dominated by the industrial aesthetics of the oil refinery, with the worker's presence adding a human element to the otherwise imposing scene.]" }, { "from": "gpt", "value": "Bad. The person's arm is twisted, the hand is twisted, and the face is distorted." } ]
seed42_2087
videos/HRA_part0/2087.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space prison, dimly lit by neon blue lights, two figures, a male and female inmate, plot their daring escape. They wear matching orange jumpsuits with black stripes, symbolizing their confined status. Suddenly, they engage in a synchronized dance, using their movement as a clever ruse to distract guards. Their dance, a blend of hip-hop and contemporary styles, captivates the robotic guards, allowing the inmates to stealthily make their way towards freedom. The prison's cold, metallic interior contrasts sharply with the dynamic energy of their dance, highlighting the tension between confinement and liberation. Throughout, the focus remains on the two dancers, their precise movements and the prison's stark, oppressive environment.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed44_2628
videos/HRA_part1/2628.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an unexpected urban scene, a wild bobcat stands alert near a glassy skyscraper, its reflection visible on the building's facade. Beside it, a sleek swimming pool shimmers under the city lights, invitingly clear and calm. The bobcat, with its distinctive tufted ears and sharp gaze, seems unperturbed by the towering structures, its presence creating a striking contrast against the urban landscape. The pool, framed by the towering skyscrapers, offers a serene oasis, its still waters reflecting the night sky and the surrounding architecture.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous, there are sudden changes." } ]
seed46_1494
videos/HRA_part2/1494.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful young student, dressed in casual attire, gently caresses a chimpanzee seated beside her, both looking straight ahead. The scene is set against the backdrop of a busy industrial area, with large oil refineries visible in the background, emitting plumes of smoke into the hazy sky. Despite the industrial setting, the focus remains on the tender interaction between the student and the chimpanzee, conveying a sense of connection and empathy amidst the urban landscape.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed44_1065
videos/HRA_part1/1065.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station illuminated by vibrant neon lights, a worker, dressed in a sleek gray jumpsuit and wearing protective goggles, gently caresses the metallic arm of a Robot astronaut. The Robot, clad in a polished silver spacesuit adorned with intricate wiring and glowing blue accents, stands motionless yet imposing against the backdrop of high-tech equipment and advanced machinery. The scene captures a tender moment of human-robot interaction, highlighting the bond between the worker and the Robot astronaut in the vast expanse of outer space.]" }, { "from": "gpt", "value": "Bad. The middle frame of the video shows the staff's caressing action is not smooth, and the body proportions are not well-coordinated." } ]
seed42_2569
videos/HRA_part0/2569.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of fresh mackerel, glistening under bright lights, is presented on a bed of ice. The fish has distinctive vertical stripes, a sign of its freshness, and its eyes are clear and shiny. The camera then zooms out to reveal the fishmonger's stall, bustling with activity, where various species of fish are displayed on ice. The mackerel takes center stage, surrounded by other seafood, emphasizing its appeal among the array of options. Throughout, the high-definition footage captures the vibrant colors and textures of the fish market, focusing on the mackerel as the star attraction.]" }, { "from": "gpt", "value": "Bad. The mackerel head generation in the video has issues." } ]
seed46_3217
videos/HRA_part2/3217.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a classic white chef's uniform and black pants, meticulously dusts antique wooden furniture in a well-lit room. He pauses to check his appearance in a mirror, revealing a pristine outfit complete with a chef's hat. Continuing his task, he dusts a table with care, his attire reflecting his professional role. Lastly, he polishes a wooden chair, his chef's jacket and black trousers standing out against the vintage setting, emphasizing his dual roles as a culinary expert and attentive caretaker of his dining space.]" }, { "from": "gpt", "value": "Bad. The chef's facial features and fingers are distorted in the video, and the chef passes through furniture in the middle frames, which is unrealistic." } ]
seed42_1334
videos/HRA_part0/1334.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is presented on a clean, white plate, its textured surface and irregular shape contrasting against the smooth, pristine background. The fish's left side faces upward, revealing its distinct dark brown coloration on top and lighter underside. Its eyes are both positioned on the darker left side, glistening and intact, indicating its freshness. The halibut's skin bears a natural pattern of spots and lines, and its mouth is slightly open, showing its small teeth. The setting is simple and unadorned, allowing the fish to be the focal point, perfect for a culinary or educational video feature.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_1075
videos/HRA_part2/1075.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, clad in a brown jacket and khaki pants, stands in a lush, green forest clearing, gently wiping mud off the antlers of a majestic deer using a soft cloth. The deer, with large, inquisitive eyes, tolerates the man's ministrations, standing still as the man carefully cleans each tine of the impressive antlers. Sunlight filters through the canopy above, casting dappled shadows on the scene below, highlighting the tender interaction between the man and the wild creature.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_1682
videos/HRA_part1/1682.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European badger, distinguished by its black and white striped face and gray fur, runs across a lush green meadow dotted with yellow flowers. The badger, with a serious expression, moves purposefully through the grassy landscape under a cloudy sky. It pauses briefly, standing upright on its hind legs, before continuing its run. Throughout the scene, the badger maintains its focus and direction, showcasing its agility and determination in the outdoors.]" }, { "from": "gpt", "value": "Bad. The facial features of the European badger in the video are distorted, the claws are missing, and there are also parts of the limbs missing." } ]
seed42_2981
videos/HRA_part0/2981.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a cheerful cashier, donning a green apron and a nametag, is playfully dancing with a friendly horse inside a vibrant, cartoonish grocery store. The cashier, with short brown hair and a wide smile, leads the horse in a lively jig down the aisles, filled with brightly colored products. The horse, adorned with a polka-dotted bowtie and a pair of oversized sunglasses, happily trots alongside, its hooves gently tapping the checkered floor. Shoppers look on in amused surprise, some pausing to capture the unexpected spectacle on their phones, while others continue browsing the shelves, seemingly unfazed by the unusual dance party unfolding before them.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed42_3129
videos/HRA_part0/3129.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, adorned in a red apron with a white floral pattern, sits on a wooden chair in a sunlit room filled with art supplies. She gently caresses a chicken, which is perched on her lap, its head adorned with a vibrant red comb. The room is decorated with colorful paintings, a large easel, and a variety of art tools, creating a warm and creative atmosphere. The artist's face, framed by curly brown hair, expresses love and connection as she interacts with the bird, highlighting the unique bond between the two.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_2011
videos/HRA_part1/2011.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sandy desert under a clear blue sky, a lone camel, distinguished by a single hump, leaps gracefully into the air. Its action is captured mid-jump, with all four feet off the ground, showcasing its unique ability to navigate the dunes. The camel's tan fur contrasts beautifully with the blue sky and golden sand, highlighting its natural habitat. As it springs forward, the surrounding landscape of dunes and distant mountains provides a stunning backdrop, emphasizing the creature's agility and the serenity of its environment.]" }, { "from": "gpt", "value": "Good. Basically no issues." } ]
seed46_2543
videos/HRA_part2/2543.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a vibrant orange pipefish, resembling a seahorse, gracefully hovers near a bed of lush green seagrass, its elongated body and small fins elegantly propelling it through the crystal-clear waters. Its distinctive snout extends forward as it explores its environment, surrounded by the swaying blades of seagrass that provide a stunning contrast to its unique form. The sunlight filters through the water, casting dappled light on the scene, highlighting the intricate details of the pipefish's skin and the delicate movements of its fins as it navigates its aquatic habitat.]" }, { "from": "gpt", "value": "Bad. The facial and fins generation of Hai Long in the video has problems." } ]
seed42_1602
videos/HRA_part0/1602.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman in a red dress walks purposefully through the grand lobby of a luxurious hotel, her high heels clicking on the marble floor. The opulent space features tall windows, plush velvet sofas, and an elegant chandelier, all bathed in warm, inviting light. As she strides confidently, she passes by the reception desk, where a concierge is busy assisting guests. In the background, a group of tourists consults a map, adding a touch of bustling activity to the otherwise refined atmosphere. The woman's poise and the hotel's grandeur create a captivating scene of urban sophistication.]" }, { "from": "gpt", "value": "Normal. The character's arm is twisted, the hand is distorted, and the foot is twisted." } ]
seed44_2118
videos/HRA_part1/2118.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds where a skilled jazz musician, clad in a vibrant yellow polo shirt and black trousers, plays a saxophone solo with closed eyes, embodying the music's soul. Behind him, a large hippopotamus swims in a serene body of water, its head and back partially submerged, creating a harmonious coexistence between nature and artistry. The musician's passionate performance and the hippo's peaceful aquatic presence form a captivating juxtaposition, set against a backdrop of lush greenery and a tranquil sky.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed46_1506
videos/HRA_part2/1506.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent tiger, mid-leap, propels itself from a large rock into a lush, green forest, its body stretched out in a powerful arc. The tiger, with its distinctive orange coat patterned with black stripes, exhibits raw strength and grace as it jumps, surrounded by dense foliage and towering trees that provide a natural habitat. The action is captured in stunning detail, focusing on the tiger's muscular form, intense concentration, and the dynamic motion of its leap, encapsulating the essence of wild freedom.]" }, { "from": "gpt", "value": "Normal. The tiger's movements in the video are not smooth." } ]
seed42_3211
videos/HRA_part0/3211.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, embodying the essence of a 'quantum leap,' sprints across a futuristic cityscape under a vibrant aurora borealis sky, wearing a neon green tracksuit that illuminates against the dark urban background. The artist's forward motion is captured in a series of dynamic poses, showcasing the fluidity and power of their stride. The cityscape, featuring sleek skyscrapers and holographic billboards, reflects the energy of the run. The aurora's ethereal glow adds a mystical touch to the scene, highlighting the artist's journey as a metaphorical leap into the unknown. Throughout the sequence, the artist's determination and the pulsating city life create a visual narrative of innovation and progress.]" }, { "from": "gpt", "value": "Normal. The artist's body is twisted, head is twisted, legs are twisted, feet are twisted, arms are twisted, and hands are twisted." } ]
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a gray 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": "Normal. The man's eyes in the video have generation issues." } ]
seed44_1380
videos/HRA_part1/1380.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ruggedly handsome actor, sporting a full beard, stands in a rural setting under an overcast sky, gently caressing a brown horse with white markings. He wears a gray shirt, blue jeans, and a brown belt, while the horse stands placidly in a grassy area dotted with small trees. The actor's affectionate interaction with the animal conveys a sense of peace and connection in the pastoral environment. The horse, with its mane and tail blowing slightly in the wind, is clearly comfortable with the actor, who continues to stroke its neck with tenderness and respect.]" }, { "from": "gpt", "value": "Good. The character's movements in the video are smooth, and the hand actions are practical." } ]
seed42_2074
videos/HRA_part0/2074.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-end restaurant, a well-dressed waiter, wearing a black vest and tie, pulls out a chair for a customer at a candlelit table set with fine china and crystal glasses. The background features other patrons enjoying their meals, adding to the ambiance of a busy, upscale dining experience.]" }, { "from": "gpt", "value": "Normal. The man's hand and arm appear deformed." } ]
seed42_2002
videos/HRA_part0/2002.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mallard duck floats placidly on the surface of a glassy lake, its vivid green head glistening in the sunlight, while its mottled brown back blends harmoniously with the natural surroundings. Nearby, cattails and reeds frame the serene scene, swaying gently in the breeze. The duck then proceeds to dip its head underwater, searching for food among the submerged plants, its body remaining visible above the waterline. As it surfaces, droplets of water scatter from its bill, capturing the tranquility and beauty of a day at the lake.]" }, { "from": "gpt", "value": "Normal. The green-headed duck's movements in the video are basically normal, but there is slight disharmony." } ]
seed44_263
videos/HRA_part1/263.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 majestic zebra, adorned with its distinctive black and white stripes, stands at the edge of a crystal-clear pool located in a vast, open mine. The zebra, with its striking pattern, contrasts beautifully against the barren landscape of the mine. Suddenly, it gracefully plunges into the water, swimming effortlessly as it explores the submerged depths of the mine, the sunlight filtering through the water's surface creating a mesmerizing play of light and shadow around the zebra. This unique scene unfolds in a large, abandoned mine, now filled with water, providing an unexpected aquatic habitat for wildlife.]" }, { "from": "gpt", "value": "Bad. The number of zebras in the video is incorrect." } ]
seed44_1274
videos/HRA_part1/1274.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged fisherman, clad in a yellow raincoat and matching hat, stands waist-deep in the water, his gaze fixed on the horizon. His hands, weathered from years of labor, expertly handle the fishing net as he casts it into the vast, shimmering sea. The early morning sun bathes the scene in a golden glow, casting long shadows and highlighting the droplets of water clinging to the net. Seagulls circle overhead, their calls adding to the serene atmosphere of the coastal landscape. In the distance, the silhouette of a small fishing village can be seen, smoke rising from the chimneys of the quaint houses, a reminder of the community that thrives on the fruits of the sea.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_191
videos/HRA_part1/191.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, cosmic setting, a cashier, clad in a unique space suit adorned with symbols of diplomacy, traverses the mammoth hall of an intergalactic embassy. She walks with purpose, passing through a grand archway, her eyes set on a distant goal. Behind her, a massive window reveals the breathtaking expanse of stars and galaxies, highlighting the enormity of her mission among the celestial bodies. Her every step echoes in the spacious corridor, resonating with the gravity of her role in maintaining galactic peace.]" }, { "from": "gpt", "value": "Normal. The face of the person in the video is distorted, as well as the hands and arms." } ]
seed42_1614
videos/HRA_part0/1614.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 opera performance, a farmer wearing a traditional straw hat and a patched apron over a checkered shirt runs across the stage under a backdrop of stars and planets. Simultaneously, a life-sized robotic tiger, designed with intricate circuitry patterns, races alongside him, both moving with a sense of urgency. The farmer's face is set in determination, and the tiger's robotic eyes glow with programmed intensity, highlighting the dramatic chase sequence unfolding against the cosmic setting.]" }, { "from": "gpt", "value": "Normal. The man's legs and arms are deformed, and his face is also distorted." } ]
seed42_2219
videos/HRA_part0/2219.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a yellow shirt with a black apron, stands in a modern kitchen classroom filled with stainless steel appliances, teaching a group of attentive students how to stir-fry vegetables. She masterfully tosses vibrant bell peppers, carrots, and broccoli in a large wok over high heat, creating an engaging lesson on cooking techniques. The students, clad in matching aprons, watch intently as she demonstrates the art of stir-frying, her actions punctuated by the sizzling sounds of the hot oil and vegetables. Throughout the scene, the teacher's enthusiasm and expertise shine as she shares her culinary knowledge with her eager pupils.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_1036
videos/HRA_part0/1036.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crow perches on a thin branch, set against a vivid orange sunset, its silhouette stark and striking. The bird has ruffled feathers, indicating a recent bout of activity, and it looks directly at the camera with one intense eye. Its beak is slightly open, as if about to call out into the dusky sky, which is ablaze with fiery hues of red and gold, casting a warm glow on the crow's form. The branch it rests on is delicate, barely able to support its weight, adding a sense of precarious balance to the scene. Behind the crow, the last rays of sunlight filter through the gaps in the bare tree branches, creating a dramatic interplay of light and shadow.]" }, { "from": "gpt", "value": "Normal. The crow's head is generated slightly distorted, and the claws are not generated." } ]
seed42_2457
videos/HRA_part0/2457.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, smiling female musician, wearing a gray sweater, sits against a rustic wooden backdrop. She holds knitting needles and yarn in her hands, crafting a vibrant orange scarf. Her fingers, adorned with rings, skillfully manipulate the needles as she knits. Next, she wears a maroon beret and continues knitting, her eyes focused on her work. Then, she looks up from her knitting, her hazel eyes meeting the camera with a warm smile. Lastly, she proudly holds up the completed scarf, now a beautiful addition to her outfit, against the backdrop of wooden planks, showcasing her dual talents in music and knitting.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_2788
videos/HRA_part2/2788.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a flannel shirt, worn jeans, and a wide-brimmed straw hat, meticulously repairs a wooden fence under the golden glow of the setting sun. His hands, strong and capable, are wrapped around a hammer as he replaces a broken slat, embodying a rugged, down-to-earth character. The rural landscape stretches behind him, dotted with tall grass and distant trees, creating a serene backdrop for his focused labor. The fence, now mended, stands as a testament to his efforts, while the actor takes a moment to lean against it, surveying his work with a sense of accomplishment and satisfaction.]" }, { "from": "gpt", "value": "Bad. The actor's repair of the wooden fence in the video is very unsmooth, and the movements are uncoordinated." } ]
seed46_1066
videos/HRA_part2/1066.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinctive black markings, is perched on a concrete ledge. It has a full, round body and is situated in an urban environment, as indicated by the presence of a streetlight and a partial view of a building's facade with windows. The bird faces right, its head turned slightly toward the viewer, revealing one bright, alert eye. Its beak is open, perhaps mid-call, and its feet grasp the edge of the ledge firmly. The scene is set against a backdrop of a clear, blue sky, offering a simple yet effective contrast to the textured details of the pigeon.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_3111
videos/HRA_part0/3111.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a gray sweater and blue jeans, steps out from a charming cottage, holding a small trash bag. She walks purposefully down a stone path, surrounded by lush greenery and flowers, to reach a large wooden bin. The scene is set in the golden hour, with soft sunlight filtering through the trees, casting a warm glow on the idyllic setting. The writer pauses for a moment, looking contemplative, before depositing the trash bag into the bin. The peaceful atmosphere and natural beauty of the surroundings provide the perfect backdrop for her daily routine, offering a glimpse into the simple yet meaningful moments in the life of an artist.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed44_1640
videos/HRA_part1/1640.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate chef, donning a classic white chef's jacket and black pants, is filmed in high definition as he masterfully prepares an exquisite dinner in a bustling restaurant kitchen. The scene opens with him seasoning a sizzling steak with precision, the flames from the grill casting dramatic shadows. Next, he's shown tossing vibrant vegetables in a pan with a practiced flick of his wrist, the steam rising and enhancing the aroma. Then, he carefully plates the finished dish, garnishing it with fresh herbs, each movement demonstrating his culinary expertise. Lastly, the chef adds a final touch, drizzling a rich sauce over the dish, the colors and textures popping against the pristine white plate, ready to delight the senses.]" }, { "from": "gpt", "value": "Bad. The chef's fingers in the video are not fully generated." } ]
seed42_1491
videos/HRA_part0/1491.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, dressed in a gray hoodie and blue jeans, diligently sweeps the wooden planks of a front porch bathed in natural sunlight, the fibers of the broom bristles catching the light as they sweep away dust and leaves. The porch railing, painted white, contrasts against the weathered wood, and the lush greenery of the surrounding landscape provides a vibrant backdrop. The young man pauses for a moment, leaning on the broom, revealing a tidy, swept area underfoot, before continuing his task with a focused expression, the sunlight casting a warm glow over the entire scene.]" }, { "from": "gpt", "value": "Bad. The broom in the person's hand appears deformed, the person teleports at one point, and the person's hands and feet are distorted." } ]
seed46_1523
videos/HRA_part2/1523.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, wearing a gray suit, white shirt, and red tie, is seen in a wide office space, mopping the floor with a green mop and bucket. The office features a large window, a desk with a computer, and a bookshelf filled with law books, creating a professional atmosphere. The lawyer, with short brown hair and glasses, demonstrates an unexpected side as he diligently cleans the floor, highlighting the versatility and hardworking nature of legal professionals.]" }, { "from": "gpt", "value": "Normal. The human hand appears deformed, and the mop handle is bent." } ]
seed44_2574
videos/HRA_part1/2574.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a yellow safety vest and black trousers, stands amidst the towering structures of an oil refinery under the vast sky. He is seen wiping down the massive pipes, his actions emphasizing the scale of the mammoth industrial landscape around him. The refinery, with its intricate network of pipes and tanks, looms large in the background, highlighting the solitary figure of the worker engaged in his task. The setting is dominated by the industrial aesthetics of the oil refinery, with the worker's presence adding a human element to the otherwise imposing scene.]" }, { "from": "gpt", "value": "Bad. The person's arm is twisted, head is twisted, hand is twisted, and the item in hand is twisted." } ]
seed42_1899
videos/HRA_part0/1899.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown bear, standing on its hind legs on a wooden stage, wears a red and gold traditional Russian costume, complete with a matching hat. The bear, seemingly performing for an unseen audience, dances energetically to lively music, swaying its body and moving its paws in time with the beat. The stage is decorated with colorful banners and twinkling lights, creating a festive atmosphere, while the bear's expressive face conveys a sense of playful enjoyment in its unusual dance performance.]" }, { "from": "gpt", "value": "Normal. The brown bear's movements in the video are basically normal, with slight coordination issues in the limbs." } ]