video_id
stringlengths
8
11
video
stringlengths
22
25
conversations
listlengths
2
2
seed42_2857
videos/HRA_part0/2857.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant flamingo stands tall and proud on a sandy shore, its pink feathers glowing under the golden rays of the setting sun. Its long, slender legs elegantly support its body as it gazes out over the calm waters, creating a serene and picturesque scene. The flamingo's curved neck gracefully bends, while its beak rests gently on its chest, exuding a sense of tranquility and contentment. Surrounding palm trees sway gently in the breeze, adding to the idyllic atmosphere of this stunning coastal landscape.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_1681
videos/HRA_part2/1681.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-covered tundra landscape, a small, furry badger emerges from its burrow, the entrance barely visible among the icy terrain. It cautiously crawls out, its round body and short legs moving slowly against the stark white backdrop. The badger, with its distinct black and white striped face, looks around with beady eyes, alert and ready to retreat at any sign of danger. Its movements are deliberate and measured as it explores the frigid environment, searching for food beneath the snow. The scene is framed by the endless expanse of the tundra, dotted with sparse, low-lying shrubs and ice formations, creating a sense of isolation and survival in the harsh wilderness.]" }, { "from": "gpt", "value": "Normal. The badger in the video moves basically normally, with slightly uncoordinated movements." } ]
seed42_1175
videos/HRA_part0/1175.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, with short brown hair and a neatly trimmed beard, laughs wholeheartedly while sitting on a brown leather sofa. He wears a dark gray turtleneck sweater, black jeans, and a silver wristwatch, set against a warm-toned living room backdrop. The room features wooden floors, a large window with natural light, and a lush green plant, creating a cozy atmosphere. The actor's laughter is genuine and infectious, his eyes crinkling at the corners as he leans back on the couch, enjoying a private joke.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_1606
videos/HRA_part2/1606.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a high-tech facility with glowing blue accents, a muscular firefighter, wearing a full-body protective suit and helmet, stands against a backdrop of advanced machinery. He holds an antimatter containment device, a sleek silver sphere with intricate detailing, which emits a faint blue glow, signifying its active state. The setting shifts subtly to reveal the firefighter engaging in a lively dance, maintaining a firm grip on the containment device, now resting on his hip. The dance moves fluidly from a standing position into a crouched stance, with the firefighter's hands moving dynamically, all while keeping the device secure. Throughout the sequence, the futuristic setting, characterized by clean lines and blue accents, remains visible, adding a dramatic touch to the dancing firefighter's performance.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_1309
videos/HRA_part0/1309.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a yellow fire-resistant jacket, leads a calm brown horse into a shallow, clear lake during a sunny day. The firefighter gently guides the horse, which is adorned with a red blanket, into the water. Both the firefighter and the horse are knee-deep in the refreshing lake, surrounded by lush greenery and a peaceful environment, creating a heartwarming and unexpected scene of tranquility.]" }, { "from": "gpt", "value": "Normal. The firefighter's arm is twisted, the face is distorted, the horse's legs are twisted, and the face is slightly deformed." } ]
seed46_1921
videos/HRA_part2/1921.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged doctor, wearing a white lab coat over casual clothes, finds himself unexpectedly digging with a shovel in the middle of a large, empty lot overgrown with grass, as if searching for something specific. The contrast between his professional attire and the task at hand highlights the unusual nature of the situation. He pauses to wipe sweat from his brow, revealing a look of intense determination. In another scene, he continues to dig with the same shovel, now more dirt-stained, while the afternoon sun casts a warm glow over the desolate lot, emphasizing the solitary and strenuous nature of his endeavor.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed46_237
videos/HRA_part2/237.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lush subtropical moist forest, a young, athletic female cashier, donning a green vest and khaki shorts, is depicted running with intense focus, her eyes fixed ahead. Suddenly, a cobra slithers across her path, its hood dramatically spread. Unfazed, she leaps gracefully over the snake, her action capturing a powerful moment of survival instinct. As she continues her run, the dense vegetation and towering trees of the subtropical environment envelop her, highlighting her determination and agility amidst the wild setting.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_2807
videos/HRA_part1/2807.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an antelope, distinctively marked with white underbelly and brown coat, is shown crawling on its belly across the grassland, a behavior rarely observed. The scene opens with the antelope lying down, then it proceeds to crawl, its horns visible, as it moves slowly through the tall grass. Throughout the sequence, the antelope remains low to the ground, its body almost parallel to the earth, showcasing this unusual behavior in great detail against the backdrop of the African savanna.]" }, { "from": "gpt", "value": "Normal. The limbs of the antelope in the video are missing, multiple horns are generated and deformed, the ears are not generated, and the tail is not generated." } ]
seed46_3125
videos/HRA_part2/3125.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, holding a green notebook, dances energetically on a busy street in Tokyo, her movements conveying a sense of freedom and joy. She wears a gray turtleneck sweater, a brown leather jacket, and a maroon beret, her style blending seamlessly with the urban environment. As she dances, the bustling city life continues around her, with people walking, cars passing, and neon signs illuminating the scene. Her expressive face, framed by her beret, reflects pure delight, and her body language conveys the story of a creative soul finding inspiration in the vibrant heart of Tokyo.]" }, { "from": "gpt", "value": "Bad. The writer's walking in the video is very unsmooth, and the movements are uncoordinated." } ]
seed44_2880
videos/HRA_part1/2880.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a flowing white dress, interacts with a majestic lion in a surreal setting, emphasizing their connection. She crawls on a surface covered with lush green grass, facing the lion with a relaxed demeanor. The lion, also crawling, responds to her with curiosity, its golden eyes locked onto hers. Both the woman and the lion are framed by the vibrant greenery of their surroundings, highlighting the unusual yet peaceful encounter between human and beast.]" }, { "from": "gpt", "value": "Bad. The woman's head is distorted in the video, as well as the lion's head." } ]
seed46_1794
videos/HRA_part2/1794.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown beret, red scarf, and green jacket, walks through a quaint, snow-covered village. The scene focuses on shops with wooden signs and red brick facades, reminiscent of a European winter market. Among the crowd, the artist carries a large painting wrapped in brown paper, attracting curious looks from passersby. In the background, a life-sized beaver statue stands outside a shop, adding a whimsical touch to the picturesque setting. The artist continues walking, blending into the festive atmosphere, with the beaver statue remaining a quirky focal point among the bustling shoppers.]" }, { "from": "gpt", "value": "Bad. The human face is deformed, and the facial features are distorted. The artist's fingers are also deformed." } ]
seed42_1225
videos/HRA_part0/1225.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda-costumed police officer sits in the cockpit of a futuristic space vehicle, navigating through the vast cosmos with a serious yet adorable demeanor. Moments later, the panda officer is shown swimming gracefully underwater, fully clad in the panda suit and police uniform, including a badge and a cap, creating a surreal and humorous contrast against the aquatic environment. The scene is set in a large, clear, space-themed aquarium, with stars and planets adorning the backdrop, merging elements of space travel and aquatic life in a playful and unexpected manner.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2943
videos/HRA_part2/2943.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An ibex, distinguished by its dark brown coat and 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": "Good. No obvious problems." } ]
seed44_1768
videos/HRA_part1/1768.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid, close-up shot, a sleek, black king cobra emerges from the underbrush, its distinctive hood fully spread as it propels itself forward with surprising speed. Its body, covered in smooth scales, undulates gracefully over the forest floor, showcasing the powerful muscles beneath. The cobra's intense, amber eyes remain fixed ahead, conveying a sense of purpose and determination as it navigates the complex terrain with agility and precision. The lush greenery and dappled sunlight create a dynamic contrast against the snake's dark form, highlighting the primal energy of this extraordinary creature in motion.]" }, { "from": "gpt", "value": "Normal. The cobra's eyes in the video were not generated." } ]
seed46_1540
videos/HRA_part2/1540.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy white dog runs alongside a futuristic lunar buggy as it traverses the desolate, rocky terrain of the moon's surface, illuminated by the distant Earth shining brightly in the sky. The dog, wearing a red bandana and a small backpack, bounds energetically over the rugged landscape, while the lunar buggy, equipped with large, treaded wheels and a solar panel roof, cruises steadily beside it. Inside the buggy, a figure in a spacesuit can be seen piloting the vehicle, their helmet visor reflecting the barren lunar scenery. The Earth hangs low on the horizon, casting a pale blue glow over the stark, airless environment.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed46_2586
videos/HRA_part2/2586.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a walkie-talkie attached to his belt, kneels in a zoological park, intently observing a crawling creature. The lush greenery and trees of the park provide a serene backdrop. The officer's focus is directed at a small animal slowly making its way across the ground, highlighting a unique interaction between law enforcement and wildlife in an urban zoo setting.]" }, { "from": "gpt", "value": "Bad. The police officer's movements in the video have no obvious problems, but the reptile's movements are very unsmooth and uncoordinated." } ]
seed44_2193
videos/HRA_part1/2193.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with brown hair tied back in a ponytail, wearing a gray cardigan over a white blouse and jeans, meticulously dusts furniture in a classroom. She moves with precision, her facial expression one of concentration. The room is filled with sunlight, illuminating the specks of dust floating in the air. She pauses for a moment, her hands on her hips, surveying her work before continuing. The classroom is mostly empty, save for a few desks and chairs, giving the impression of a quiet, orderly space. Throughout the scene, she remains focused on her task, her movements deliberate and efficient.]" }, { "from": "gpt", "value": "Bad. The woman's movements while cleaning the furniture in the video are discontinuous and have abrupt changes." } ]
seed44_1562
videos/HRA_part1/1562.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 innovative engineer, clad in a spacesuit and helmet, walks through a futuristic space station, where advanced agricultural technology is used to cultivate crops in zero gravity. Accompanied by a friendly fox, who curiously observes the floating plants and high-tech equipment, the engineer tends to the verdant greenery, demonstrating the feasibility of farming in outer space. The pair moves through the well-lit, sterile environment, highlighting the potential for sustainable food production beyond Earth's atmosphere.]" }, { "from": "gpt", "value": "Normal. The engineer's hands and the fox's head generation in the video have issues." } ]
seed44_1659
videos/HRA_part1/1659.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cap, walks through a bustling space casino, neon lights casting an otherworldly glow on the patrons. Among them, a meerkat stands upright, wearing a tiny tuxedo, its eyes wide with wonder as it navigates the futuristic gaming tables, slot machines, and alien creatures. The officer, maintaining a watchful eye, ensures order in this eclectic mix of species and activities, all set against the backdrop of a grand, space-themed casino.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_2279
videos/HRA_part1/2279.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 farmer, clad in a brown jacket, beige trousers, and a wide-brimmed hat, dances jovially in a mountainous landscape, the distant peaks shrouded in mist. A deer, with a full rack of antlers and a curious gaze, watches him from the edge of a lush forest. The farmer's movements are lively and carefree, his arms raised in the air, as if celebrating the beauty of nature that surrounds him. The deer, sensing no threat, cautiously approaches, its ears perked, adding a touch of whimsy to the scene. The mountains loom majestically in the background, their slopes dotted with trees and patches of greenery, providing a stunning natural backdrop to this unexpected dance.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_3048
videos/HRA_part2/3048.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a traditional white uniform and cap, takes a break from her medical duties to paint a hospital room a soothing shade of light blue. Holding a paintbrush in her gloved hand, she carefully applies the paint to the wall, creating a fresh and welcoming environment for the patients. The room is brightly lit, with medical equipment neatly arranged on a side table, and a window letting in natural light, casting a warm glow on the freshly painted walls. The nurse's dedication to improving the space highlights her commitment to patient care beyond her regular responsibilities.]" }, { "from": "gpt", "value": "Normal. The nurse's fingers in the video are deformed, and there are issues with the eyes." } ]
seed42_2718
videos/HRA_part0/2718.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [At a busy city bus stop, two cheerful children wearing swimsuits and holding floaties wait alongside their mother, who wears a yellow dress. The scene is vibrant, with the bus stop shelter adorned with colorful graffiti and the city skyline visible in the background. Suddenly, a double-decker bus approaches, its exterior painted with a striking zebra pattern. As the bus pulls up, the children look up in awe, their excitement palpable as they prepare to board for what seems like an adventurous day ahead.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed46_1665
videos/HRA_part2/1665.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 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 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": "Bad. The lion's limbs are missing in the video, and the paws have not been generated." } ]
seed42_1854
videos/HRA_part0/1854.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, clad in a brown leather jacket and jeans, walks alongside a cheetah in a natural savanna setting, both figures dwarfed by the vast, open landscape. The writer, wearing a beige hat, sunglasses, and holding a pen and notebook, looks thoughtful as they stroll together. The cheetah, sporting a tracking collar, walks parallel to the writer, its gaze forward, reflecting a sense of purpose and freedom. Together, they traverse the grassy terrain, the writer occasionally jotting down notes, while the cheetah remains vigilant, embodying the spirit of the wild.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed46_2921
videos/HRA_part2/2921.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet harmonious scene, a veterinarian, dressed in a khaki safari outfit, carefully tends to a young rhinoceros in a spacious, fenced enclosure, with lush greenery visible in the background. The compassionate doctor gently examines the rhino, which is lying on a sandy surface, seemingly at ease. The rhinoceros, displaying signs of improvement, attempts to crawl forward on its front legs, indicating a recovery from a recent ailment or procedure, all under the watchful eye of the dedicated wildlife doctor.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_1767
videos/HRA_part0/1767.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary buzzard perches majestically on a barren branch, its piercing eyes scanning the vast, sunlit savannah below for any signs of movement. The bird, with its distinct brown and white plumage, contrasts starkly against the muted tones of the landscape. Suddenly, it spreads its impressive wingspan and takes flight, gliding effortlessly over the terrain. Its sharp talons are clearly visible as it descends with laser-like precision towards a potential meal, showcasing the raw power and agility of this apex predator. The scene is set against a backdrop of rolling hills and scattered trees, bathed in the warm glow of the afternoon sun.]" }, { "from": "gpt", "value": "Bad. The eagle's wings and claws are distorted in the video." } ]
seed46_2252
videos/HRA_part2/2252.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a green sweater and brown trousers, kneels on a lush, grassy field as they observe a graceful gazelle. The writer, with a notebook in hand, carefully documents the gazelle's movements from a crawling position, capturing the serene atmosphere under a clear blue sky. The scene highlights the writer's dedication to their craft, as they immerse themselves in nature to gather inspiration, while the gazelle, unaware of the observer, continues its elegant grazing nearby.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth, and the gazelle's movements are not smooth." } ]
seed42_2154
videos/HRA_part0/2154.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 charming hedgehog, adorned with a miniature top hat and a tiny pair of spectacles, pirouettes gracefully on a wooden floor, surrounded by a medley of autumn leaves. The scene is imbued with a warm, golden light, casting gentle shadows that sway in harmony with the hedgehog's dance. As the music swells, the hedgehog leaps into a joyful jig, its quills bouncing playfully with each step. In the final moments, the hedgehog pauses, bowing elegantly to an invisible audience, the leaves rustling softly in applause, all set against the backdrop of a rustic barn door.]" }, { "from": "gpt", "value": "Bad. The hedgehog's body, head, claws, and face are distorted in the video." } ]
seed44_1562
videos/HRA_part1/1562.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An innovative engineer, clad in a spacesuit and helmet, walks through a futuristic space station, where advanced agricultural technology is used to cultivate crops in zero gravity. Accompanied by a friendly fox, who curiously observes the floating plants and high-tech equipment, the engineer tends to the verdant greenery, demonstrating the feasibility of farming in outer space. The pair moves through the well-lit, sterile environment, highlighting the potential for sustainable food production beyond Earth's atmosphere.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_25
videos/HRA_part1/25.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly capybara, adorned with a miniature nurse's hat and a stethoscope around its neck, crawls across a colorful, childlike set filled with oversized medical-themed toys. The capybara moves deliberately, as if performing a check-up on a giant teddy bear patient lying on a playful examination table, surrounded by an array of oversized bandages, cotton balls, and a smiling face thermometer, creating a heartwarming and imaginative playtime scenario.]" }, { "from": "gpt", "value": "Bad. The capybara's head and paws in the video have generation issues." } ]
seed44_1200
videos/HRA_part1/1200.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly contrasting scene, two young boys, one wearing a red life jacket and the other in swimming trunks, are seen engaging with a camel on a sandy shore near shallow water, under a clear blue sky. The camel, adorned with a colorful saddle, dips its head into the turquoise water, while the children look on with delight. One boy, in the red life jacket, reaches out to touch the camel, capturing a moment of unexpected interaction between land and sea creatures. The setting sun illuminates the scene, casting warm hues across the water and highlighting the unique connection between the children and the camel in this coastal environment.]" }, { "from": "gpt", "value": "Bad. The child in the red clothes has a twisted arm and a deformed head, the camel has a twisted neck, a deformed head, and a twisted body." } ]
seed46_2190
videos/HRA_part2/2190.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a brown beret and glasses, sits in a dimly lit studio filled with art supplies and paintings, engrossed in reading a book about art history. The camera captures the artist's hands turning the pages, revealing colorful illustrations of famous artworks. In another shot, the artist is seen from behind, sitting in front of a large canvas with paintbrushes in hand, contemplating the next stroke while a book on art techniques lies open nearby. Throughout the video, the artist's passion for both creating and studying art is evident in the careful attention given to both the book and the canvas.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed44_2290
videos/HRA_part1/2290.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a maroon hoodie and gray sweatpants, diligently wipes down a large, brown bison statue with a white cloth, showing care and attention to detail. The scene takes place on a grassy campus, with trees in the background, highlighting the unique connection between the student and the symbolic animal figure. The student's focused expression and the careful motion of wiping the bison's surface convey a sense of respect and tradition associated with university life.]" }, { "from": "gpt", "value": "Bad. The student's hand and the statue's head in the video have generation issues." } ]
seed44_137
videos/HRA_part1/137.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda wearing a spacesuit floats in zero gravity, gently wiping a tear from its eye with a small cloth. Beside it, two astronauts, also in full space gear, share a tender kiss, signifying a unique 'space wedding'. The panda, adorned with a bow tie and holding a bouquet, serves as a heartwarming witness to this celestial union, all taking place against the backdrop of a starlit universe, with Earth visible through the window of the spacecraft.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed42_1958
videos/HRA_part0/1958.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station habitat, an anthropomorphic chimpanzee, clad in a silver spacesuit and helmet, performs an energetic dance against a backdrop of advanced technology and starlit windows. The chimp's movements are lively and expressive, conveying a sense of joy and freedom in the zero-gravity environment. Accompanied by upbeat music, the chimpanzee's dance includes playful jumps and twirls, highlighting its adaptability and charisma in the unique setting of a space station, where screens display vibrant colors and the vastness of outer space provides a stunning contrast to the lively performance.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_125
videos/HRA_part0/125.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a vibrant yellow apron over a casual outfit of a gray t-shirt and black leggings, her brown hair tied back in a ponytail, is seen cooking in a modern kitchen. She expertly chops vegetables on a wooden cutting board using a sharp knife, the overhead lights reflecting off the stainless-steel appliances behind her. Her hands, adorned with rings, move with practiced ease as she seasons the ingredients in a large skillet on a gas stove, steam gently rising from the pan. Throughout, she maintains a warm smile, occasionally glancing up from her task, creating an inviting atmosphere in the well-lit kitchen space.]" }, { "from": "gpt", "value": "Normal. The character's movements in the video are basically normal, with slight awkwardness." } ]
seed42_3028
videos/HRA_part0/3028.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a brown beret, a beige button-down shirt, and glasses, sits at a wooden desk illuminated by a brass table lamp. He leans back in a brown chair, holding a book with an intense look of concentration. The room is adorned with his own artwork, including a large painting on an easel behind him and smaller framed pieces on the walls. Sunlight filters into the room from a window to the right, casting a warm glow on the artist and his surroundings as he reads. The artist's hands, which hold the book, are decorated with rings, adding a personal touch to the scene.]" }, { "from": "gpt", "value": "Good. Basically no issues." } ]
seed44_3132
videos/HRA_part1/3132.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, wearing a navy blue blazer, sits against a dark, textured background, nodding sagely as he listens to an off-screen voice. His salt-and-pepper hair, trimmed beard, and wire-rimmed glasses add to his sophisticated appearance. Throughout the scene, he continues to nod in agreement, his expressions conveying understanding and engagement. The focus remains tight on his face, capturing every nuanced gesture and emotion, highlighting his acting prowess in this intimate setting.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1751
videos/HRA_part0/1751.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, wearing a blue striped shirt and khaki pants, is seen in a backyard, carefully washing a small brown dog with a hose. The dog, standing on a white table, looks content as the teacher, wearing rubber gloves, gently scrubs its fur with a sponge. The scene is set against a backdrop of green grass and a wooden fence, creating a peaceful and nurturing environment. The teacher's caring demeanor and the dog's relaxed stance convey a sense of trust and affection between them, making for a heartwarming moment captured in high definition.]" }, { "from": "gpt", "value": "Normal. The teacher's hand appears deformed and distorted." } ]
seed44_1610
videos/HRA_part1/1610.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its black ears and eye patches, crawls through a lush, green bamboo grove within the expansive botanical gardens. The panda's methodical movements are highlighted against the vibrant backdrop of the garden, filled with diverse plant life. It crawls on all fours, showcasing its distinctive gait, with the botanical gardens' rich vegetation and meticulously maintained pathways framing the scene. The panda's actions are set against this verdant setting, emphasizing its natural habitat within the carefully curated environment of the botanical gardens.]" }, { "from": "gpt", "value": "Bad. The limbs of the panda in the video are missing, and the sizes of its facial features and ears are inconsistent." } ]
seed46_2716
videos/HRA_part2/2716.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, clad in a white spacesuit with a NASA logo, crawls across the Martian landscape under a starlit sky. The camera captures her movements as she stops to gaze upwards, her helmet visor reflecting the celestial panorama. The focus is on her figure against the rugged terrain, with the distant stars and the curvature of Mars' horizon providing a dramatic backdrop. Her spacesuit, adorned with medical insignia, stands out against the red soil, emphasizing her unique role as a caregiver in the vastness of space.]" }, { "from": "gpt", "value": "Normal. The video does not show the nurse crawling forward as mentioned in the caption." } ]
seed44_1466
videos/HRA_part1/1466.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished 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." } ]
seed46_140
videos/HRA_part2/140.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitorial worker, clad in a crisp, light blue uniform shirt and black pants, meticulously rearranges furniture in a spacious, modern office during the daytime. He lifts a wooden chair with a green seat cushion, revealing a clean, polished floor beneath. Next, he pushes another chair into place, aligning it perfectly with the desk. Then, he adjusts a sleek, white office table, ensuring it is straight and centered. Finally, he steps back, hands on hips, surveying his work with a sense of pride and accomplishment, the room now neatly organized and ready for use.]" }, { "from": "gpt", "value": "Bad. The character's arms are twisted, hands are distorted, face is deformed, and legs are twisted." } ]
seed44_2421
videos/HRA_part1/2421.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female teacher, wearing a green sweater and brown hair, gently caresses a large leaf from a temperate rainforest tree during an educational field trip, her face expressing wonder and reverence for nature. Moments later, she holds a branch from a temperate rainforest, engagingly teaching her attentive students about the ecosystem. Then, she lovingly touches a moss-covered log, her actions conveying the importance of the rainforest environment, with the students looking on. Finally, she carefully strokes a fern frond, her demeanor highlighting the beauty and fragility of the temperate rainforest, all while surrounded by lush greenery and the natural world.]" }, { "from": "gpt", "value": "Bad. The female teacher in the video has missing finger generation, issues with eye generation, and slight facial blurriness." } ]
seed46_1020
videos/HRA_part2/1020.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, dressed in a navy pea coat, beige trousers, and brown shoes, is gracefully dancing in a large, empty room with polished wooden floors and high ceilings. In the background, a magnificent cat leaps playfully, its silhouette outlined by the warm glow of the rising sun, which streams through a window, casting a soft light on a potted plant. Mercury, visible as a bright star in the twilight sky outside, adds a celestial touch to the scene. The director's dance moves, captured in a series of fluid poses, convey a sense of joy and creative inspiration, while the cat's energetic jumps mirror the director's movements, creating a harmonious connection between the two.]" }, { "from": "gpt", "value": "Bad. A third hand appears when the character performs actions, and the cat's legs are deformed." } ]
seed46_1681
videos/HRA_part2/1681.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-covered tundra landscape, a small, furry badger emerges from its burrow, the entrance barely visible among the icy terrain. It cautiously crawls out, its round body and short legs moving slowly against the stark white backdrop. The badger, with its distinct black and white striped face, looks around with beady eyes, alert and ready to retreat at any sign of danger. Its movements are deliberate and measured as it explores the frigid environment, searching for food beneath the snow. The scene is framed by the endless expanse of the tundra, dotted with sparse, low-lying shrubs and ice formations, creating a sense of isolation and survival in the harsh wilderness.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_1553
videos/HRA_part2/1553.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male bassist passionately plays a sleek, black upright bass, his eyes closed in concentration, against a dark stage background. He wears a black turtleneck sweater and jeans, exuding confidence and skill. His right hand expertly plucks the strings while his left hand positions the notes on the fingerboard. The bass, adorned with white fret markers, resonates with each stroke, creating deep, rich tones. The musician's dedication and the instrument's elegance are highlighted under the dim stage lights, captivating the audience with the bass's powerful sound.]" }, { "from": "gpt", "value": "Normal. The man's hand in the video is blurry, and some fingers are missing." } ]
seed42_2105
videos/HRA_part0/2105.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a gray shirt and dark pants, attentively sorts colorful laundry in a busy laundromat filled with vibrant washing machines and dryers. He meticulously folds a yellow shirt, revealing a sense of pride in his work. Next, he checks the laundry, holding up a pair of red socks, demonstrating his thoroughness. Then, he loads the washer with various garments, including a green sweater and blue jeans, his actions methodical and precise. Finally, he closes the washer door, presses the start button, and turns to face the camera, his expression conveying satisfaction in a job well done, all within the bustling environment of the laundromat.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed46_2648
videos/HRA_part2/2648.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating depths of an aquarium, a sleek European eel gracefully navigates through a meticulously designed Japanese garden, complete with stone lanterns and bridges. The eel, with its elongated body and smooth movements, explores the intricate waterways, passing beneath miniature bridges and alongside delicate aquatic plants. The tank is filled with clear, shimmering water, enhancing the mesmerizing display of the eel's fluid motions as it interacts with the serene environment. The harmonious blend of nature and culture creates a stunning visual narrative centered around the elegant creature.]" }, { "from": "gpt", "value": "Bad. The eel's head generation in the video has issues." } ]
seed46_306
videos/HRA_part2/306.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, donning a white tank top, beige shorts, and brown leather sandals, assembles a wooden table in a bright room with large windows and a view of greenery outside. He starts by carefully examining the instructions, his brows furrowed in concentration. Next, he skillfully uses a screwdriver to attach the legs to the tabletop, showcasing his handyman abilities. Then, he wipes his forehead with the back of his hand, a small smile on his lips, indicating satisfaction in his progress. Finally, he stands back to admire the finished product, hands on hips, revealing the completed table in the well-lit space, surrounded by lush vegetation visible through the window.]" }, { "from": "gpt", "value": "Bad. The video does not generate a scene where the actor stands with hands on hips admiring the completed table, nor does it include an instruction manual." } ]
seed42_3208
videos/HRA_part0/3208.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful male chef, wearing a traditional white chef's uniform with a red neckerchief and a brown apron, stands in a modern kitchen. He holds a large, open recipe book in his hands and writes with a silver pen, his face expressing deep concentration. The kitchen is filled with stainless steel appliances and shelves stocked with various cooking ingredients, creating a professional culinary atmosphere. The chef's sleeves are rolled up, revealing a watch on his wrist, and he occasionally glances up from the book, likely checking the progress of dishes being prepared in the bustling kitchen environment.]" }, { "from": "gpt", "value": "Good. Basically no issues." } ]
seed46_2814
videos/HRA_part2/2814.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a royal blue scrubs top and light blue pants, stands against a white wall with a large, welcoming smile. She waves energetically with her right hand, her dark brown hair styled in a bun. Behind her, a row of lockers can be seen, adding context to the hospital setting. Her left arm rests by her side, and she wears a silver watch on her wrist. The nurse's eyes are closed as she waves, conveying genuine warmth and friendliness to the viewer.]" }, { "from": "gpt", "value": "Bad. The nurse's face generation is disharmonious, fingers are deformed, and the watch lacks a dial." } ]
seed42_1844
videos/HRA_part0/1844.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a friendly-looking cashier, wearing a red apron with a name tag, works behind a counter at an airport gift shop. Unexpectedly, a small, playful ferret emerges from the pocket of the cashier's apron, peeking its head out curiously. The background features a bustling airport terminal with passengers and luggage, emphasizing the unusual combination of elements. Moments later, the focus shifts to a clear swimming pool, where the same cashier, now in swimwear, happily swims with the ferret floating nearby on a small inflatable raft, both enjoying a break from the busy airport environment.]" }, { "from": "gpt", "value": "Bad. In the airport terminal gift shop scene, there are issues with the generation of the cashier's hand and the ferret's paws; in the swimming pool scene, there are abnormalities in the generation of the ferret, the cashier's face, and limbs." } ]
seed42_2241
videos/HRA_part0/2241.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 farmer, donning a brown shirt and blue overalls, stands in a lush green field under a clear blue sky, smiling as he observes a rabbit. The rabbit, located near the center of the frame, leaps into the air with excitement, its hind legs propelling it forward in a graceful arc. The farmer's joyful expression and the rabbit's energetic jump create a heartwarming scene, capturing the simple pleasures of rural life. The setting is enhanced by the vibrant green grass and the warm sunlight, which bathes the scene in a golden glow.]" }, { "from": "gpt", "value": "Bad. The movements are not continuous, there are sudden changes." } ]
seed42_1895
videos/HRA_part0/1895.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid outdoor setting, two young boys, one wearing a red t-shirt and the other in a white shirt, engage with a curious monkey sitting on a wooden table. The monkey, holding a banana, looks intently at the children. One boy, in a red t-shirt, wipes the monkey's face with a cloth, while the other, in a white shirt, watches with amusement, capturing a tender moment of interaction between the children and the primate. The scene is set against a backdrop of lush greenery and a clear blue sky, adding to the idyllic atmosphere of the encounter.]" }, { "from": "gpt", "value": "Bad. An extra boy was generated." } ]
seed44_1971
videos/HRA_part1/1971.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 with short brown hair, wearing a gray shirt, sits at a modern office desk cluttered with electronics and tools, knitting a red scarf with large needles. The focus is on her hands as they deftly manipulate the yarn and needles, while a laptop with coding screensaver and a blueprint of a circuit board are visible in the background. The office space is filled with tech gadgets, books, and papers, highlighting her professional environment, yet she finds time for a personal hobby, creating a vivid red scarf amidst the technical surroundings.]" }, { "from": "gpt", "value": "Bad. The engineer's movements in the video are very unsmooth and uncoordinated." } ]
seed42_184
videos/HRA_part0/184.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin waddles comically on a frosty, snow-covered surface, its sleek black-and-white feathers gleaming under the bright, clear sky. It pauses for a moment, standing upright with its wings tucked by its side, before continuing its journey across the icy terrain. Suddenly, it slips and falls onto its belly, but quickly regains its composure, getting back up with a burst of energy. The penguin then takes a dive into the frigid waters, swimming gracefully with its webbed feet and streamlined body, all while the vast, icy landscape stretches out behind it.]" }, { "from": "gpt", "value": "Normal. The penguin's eyes in the video have issues, and there are missing parts in the wings and feet." } ]
seed44_2207
videos/HRA_part1/2207.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skillful musician, clad in a black beret, black jacket, and blue jeans, sits on a wooden bench amidst lush vineyards, playing a vintage guitar with focused intensity. Nearby, a curious squirrel crawls along a vineyard post, its bushy tail swaying as it observes the musical performance from a safe distance. The rolling hills and rows of grapevines provide a picturesque backdrop, with the musician's passionate playing and the squirrel's attentive stance creating a harmonious scene in nature.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1345
videos/HRA_part0/1345.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman dances joyously at a luxurious beach resort, adorned in a flowing, patterned dress that complements her radiant smile and the tropical surroundings. With the sun setting behind her, casting a warm glow over the sandy shore, she moves gracefully, her bare feet sinking into the soft sand. Palm trees sway gently in the breeze, framing the scene as she twirls, embodying the spirit of celebration and freedom under the clear, star-studded sky.]" }, { "from": "gpt", "value": "Normal. The woman's body and facial features in the video are deformed." } ]
seed42_2225
videos/HRA_part0/2225.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a gray jacket over a button-down shirt and black pants, meticulously mops the floor in a wide, empty corridor with high ceilings. His movements are deliberate as he pushes the mop back and forth, creating a rhythmic pattern on the wet floor. The lighting is bright, illuminating the space and highlighting the sheen on the freshly cleaned surface. In one shot, the janitor pauses, mop in hand, as he looks down the length of the hallway, assessing his work. Throughout, the focus remains on him and the task at hand, capturing the quiet dedication of his labor.]" }, { "from": "gpt", "value": "Normal. The character's movements in the video are slightly unsmooth." } ]
seed42_2247
videos/HRA_part0/2247.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene, a janitor in a space museum is seen cleaning near a large, detailed model of the International Space Station, which is submerged in a serene indoor pool. Wearing a yellow vest, gray pants, and a white shirt, he carefully maneuvers around the underwater exhibit, highlighting his unique cleaning duties. The water around him is crystal clear, allowing viewers to appreciate the intricate details of the space station replica. As he works, the ambient lighting from above gently illuminates the water, creating a mesmerizing visual effect that blends the worlds of space exploration and aquatic tranquility.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_1435
videos/HRA_part0/1435.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a dark green shirt and a brown fedora, is captured in a close-up shot, staring intensely into the distance with a pensive look. His rugged appearance, complete with a well-groomed beard, conveys a sense of depth and artistic contemplation. The focus is on his expressive eyes, which seem to hold stories of experiences and inspiration, hinting at the creative energy simmering beneath the surface. Behind him, a dimly lit stage with musical instruments hints at his profession, while the overall atmosphere exudes a mood of anticipation and reflection.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_316
videos/HRA_part2/316.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a black beret, glasses, and a gray beard, is seen mopping the floor of a large, empty room with high ceilings and a wooden floor, while carrying a guitar on his back. The room is illuminated by soft, ambient lighting, casting a warm glow over the space. The musician, with his distinctive hat, glasses, and gray facial hair, exhibits a sense of dedication as he performs the mundane task of cleaning, accompanied by his trusty instrument. Despite the ordinary activity, his attire and the presence of the guitar hint at his artistic identity.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_1402
videos/HRA_part2/1402.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with glasses, wearing a dark green sweater over a button-down shirt, stands on a chair to change a light bulb in a room with wooden floors and a desk filled with books and writing materials. He holds the new light bulb in his right hand while his left hand grasps the existing bulb, which is attached to a simple ceiling fixture. Behind him, a large window reveals a gray, rainy day outside. The room is dimly lit by a small lamp on the desk, illuminating the clutter of papers, notebooks, and a vintage typewriter. The writer's casual attire, including khaki pants and brown shoes, contrasts with the focused determination on his face as he completes this mundane task amidst his literary surroundings.]" }, { "from": "gpt", "value": "Normal. The character's face is distorted, hands are twisted, and arms are deformed." } ]
seed42_2771
videos/HRA_part0/2771.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A visionary director, dressed in a classic pinstripe suit, stands in a vast, dimly lit studio, skillfully orchestrating a surreal scene. Nearby, a Robot astronaut, adorned in a sleek silver spacesuit with gleaming gold accents, follows the director's guidance as it begins to dance. The robot's movements are fluid and precise, a captivating fusion of technology and artistry, set against the backdrop of cinematic equipment and the director's watchful gaze, creating a mesmerizing spectacle where reality meets imagination.]" }, { "from": "gpt", "value": "Bad. The robot's movements in the video are not smooth." } ]
seed42_2337
videos/HRA_part0/2337.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a crisp, white lab coat stands within a futuristic, neon-lit control room, his face reflecting determination as he gazes intently at a holographic interface displaying complex schematics. Suddenly, the scene changes to reveal the same engineer navigating through a parallel universe, where technology and nature intertwine in unexpected ways. He wipes away a layer of mist from a transparent panel, revealing an intricate circuit design beneath, symbolizing the merging of worlds and the power of innovation. The engineer's focused expression and the vivid, otherworldly landscapes around him emphasize the limitless possibilities of exploration and discovery.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_2499
videos/HRA_part0/2499.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, known for its brown fur and flat tail, swims underwater in a clear, glassy lake during the daytime. It surfaces, revealing its full body, including the distinctive markings on its face and body. The beaver then proceeds to swim along the bottom of the riverbed, showcasing its webbed hind feet propelling it forward. Throughout the video, the beaver remains submerged, occasionally coming up for air, with the tranquil water and lush green vegetation along the riverbank providing a serene backdrop for this aquatic mammal's natural behavior.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2367
videos/HRA_part0/2367.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, known for his mastery of the banjo, takes a break from his art to sweep his wooden porch on a sunny day. Dressed casually in a gray shirt and khaki pants, he methodically sweeps with a broom made of natural fibers, revealing the clean, weathered wood beneath. The porch, adorned with potted plants and a rustic rocking chair, overlooks a lush garden filled with vibrant flowers and greenery. In the background, a vintage acoustic guitar leans against the wall, hinting at the musician's passion for music, while the peaceful, suburban neighborhood provides a serene setting for this ordinary yet captivating task.]" }, { "from": "gpt", "value": "Normal. Missing a rocking chair." } ]
seed46_2197
videos/HRA_part2/2197.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the arid scrublands under a vast, cloud-dappled sky, a golden jackal pauses mid-stride, its russet fur gleaming in the sunlight. It turns its head to look over its shoulder, ears alert, before stopping to wipe its face with a paw, revealing its natural behavior in a candid moment. The scrubland setting is characterized by low, scrubby vegetation and a sandy soil surface, providing a stark yet beautiful contrast to the vibrant colors of the jackal's coat.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous, there are sudden changes." } ]
seed42_1832
videos/HRA_part0/1832.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scenario, an astronaut wearing a gray spacesuit walks on an asteroid's surface, which is rich in minerals, while in the background, an unexpected sight unfolds: a full-grown moose, also wearing a spacesuit, roams freely, seemingly adapted to zero gravity. The astronaut, equipped with a helmet and backpack, explores the rocky terrain, while the moose, with its large antlers and hefty frame, adds an element of surrealism to the scene. Both figures are set against the backdrop of space, with distant stars and galaxies visible in the vast emptiness.]" }, { "from": "gpt", "value": "Normal. The moose's head is twisted, and its legs are twisted." } ]
seed42_2537
videos/HRA_part0/2537.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over casual attire, walks through a lush deciduous forest during autumn. Holding a small, brown ferret gently in one hand, he observes the rich, earthy colors of the trees and the dappled sunlight filtering through the leaves. The forest floor is carpeted with fallen leaves, and the occasional sound of twigs snapping underfoot adds to the peaceful ambiance. As he continues his leisurely stroll, the doctor occasionally pauses to examine the flora and fauna around him, the curious ferret nestled in his palm, seemingly enjoying the natural surroundings as much as its human companion.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed44_2311
videos/HRA_part1/2311.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, with striking golden eyes and a distinctive pattern of rosettes on its tawny fur, is captured in high definition as it lies on a branch. It begins by looking straight ahead, showcasing its majestic presence. Then, it turns its head to the right, revealing its sharp features and powerful muscles rippling beneath its coat. Next, the leopard proceeds to clean itself, licking its paw and wiping it across its face, a display of natural behavior in its untamed habitat. Throughout the sequence, the leopard remains perched on the branch, its gaze occasionally flicking towards the viewer, offering a rare glimpse into its private grooming routine.]" }, { "from": "gpt", "value": "Normal. The leopard's movements in the video are basically normal, but there is slight disharmony." } ]
seed46_256
videos/HRA_part2/256.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of an ibis's head, featuring its distinct red facial skin and long, curved bill, contrasted against a dark background. The bird's textured feathers, detailed facial features, and piercing eyes are captured in high definition. The ibis is shown from various angles, highlighting its unique physical attributes, including its sharp, curved beak and distinctive eye markings. Throughout the footage, the ibis's head remains the central focus, with the dark backdrop emphasizing its striking appearance.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_3127
videos/HRA_part0/3127.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An African elephant, distinguished by its large ears and gray skin, stands against a backdrop of geysers erupting in the distance, creating a misty atmosphere. The majestic animal uses its trunk to spray water onto itself, seemingly wiping or cleaning, as it enjoys a refreshing moment in the wild. This scene is set against the dramatic natural landscape, featuring geothermal activity, highlighting the unique interaction between wildlife and environment.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_2415
videos/HRA_part2/2415.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, exhibiting a rare display of gentleness, is seen affectionately caressing another leopard in a lush, verdant environment. The first leopard, with piercing green eyes and a strikingly patterned coat, leans its head against the second leopard's face in a tender gesture. Both leopards are perched on a thick, sturdy branch, surrounded by dense foliage and dappled sunlight, creating an intimate atmosphere. This unique scene captures the emotional bond between these two wild cats, showcasing the softer side of these powerful predators.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed42_132
videos/HRA_part0/132.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, clad in a black turtleneck and jeans, sits on a stage, intently playing a marimba with mallets. Nearby, a gorilla, perhaps a part of the performance or installation art, is crawling on all fours, wearing a red beret and blue jeans, adding an unexpected element to the scene. The contrast between the focused human artist and the ape in casual attire creates a surreal and captivating visual narrative.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed44_2655
videos/HRA_part1/2655.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, wearing a casual button-down shirt and khaki pants, is seen sketching mall blueprints on a large, clear desk, surrounded by architectural models and technical drawings. Moments later, the scene shifts to a vibrant mall interior, where the same engineer is seen interacting with a diverse group of shoppers, pointing out design features and technological advancements. Finally, the video captures the engineer enjoying a well-deserved break by swimming leisurely in a modern, glass-enclosed pool, located on the mall's rooftop, showcasing a harmonious blend of work and relaxation.]" }, { "from": "gpt", "value": "Bad. The character's face, hands, and arms are distorted in the video." } ]
seed44_3031
videos/HRA_part1/3031.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man with a full beard, dressed in a green shirt and brown pants, is kneeling in a forest clearing. He gently wipes a small, injured porcupine with a white cloth, his face expressing deep concern and care. The porcupine, quills visible, lies quietly on a bed of moss and leaves, seemingly aware of the man's protective presence. The forest surroundings, with tall trees and dappled sunlight, provide a natural and peaceful setting for this tender interaction between man and wildlife.]" }, { "from": "gpt", "value": "Normal. The man in the video wiping the porcupine is basically normal, but there is slight clumsiness in his movements." } ]
seed46_1042
videos/HRA_part2/1042.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature woman with graying hair tied in a ponytail engages in a fall activity, raking leaves in her spacious backyard. Dressed in a blue shirt, denim jacket, and brown gloves, she meticulously gathers the autumn foliage. The scene is set in late afternoon, as indicated by the soft, golden light filtering through the trees. She pauses to look up, her expression one of determination mixed with a sense of accomplishment, surrounded by piles of leaves and a red wheelbarrow nearby, emblematic of the season's chores and the beauty of nature's transition.]" }, { "from": "gpt", "value": "Bad. The arm is twisted and deformed." } ]
seed46_2536
videos/HRA_part2/2536.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, otherworldly landscape under a night sky, a group of six individuals dressed in futuristic silver spacesuits, equipped with jetpacks, are leaping dynamically across a comet's icy surface. The comet is depicted with a diffuse, gaseous tail stretching into the cosmos. Each person exhibits a different pose mid-jump, capturing the essence of weightlessness and adventure. The background showcases distant galaxies and stars, emphasizing the grandeur of space exploration. The scene conveys a sense of exhilaration and the spirit of human curiosity pushing boundaries beyond Earth.]" }, { "from": "gpt", "value": "Bad. The comet did not generate a diffuse gaseous tail." } ]
seed42_1706
videos/HRA_part0/1706.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the surreal landscape of Neptune's gaseous atmosphere, rendered in vivid purples and blues, a meerkat stands alert amidst floating islands of icy material. The meerkat, wearing a small spacesuit with a clear helmet, wipes its face with a tiny cloth, perhaps to clean away condensation or space dust. The contrast between the meerkat's terrestrial behavior and the alien environment creates a whimsical and unexpected scene. Behind the meerkat, the swirling clouds of Neptune provide a dramatic backdrop, emphasizing the creature's isolation and the vastness of its surroundings.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous, and there are sudden changes." } ]
seed42_19
videos/HRA_part0/19.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 underwater scene, a stunning coral reef thrives, illuminated by the dappled sunlight filtering through the clear blue water. A variety of corals in different shapes and sizes, ranging from brain coral to staghorn coral, create a textured landscape. The colors are rich and saturated, featuring shades of orange, red, purple, and green. The reef is teeming with life, as schools of colorful fish, such as angelfish and clownfish, swim gracefully among the corals. In the foreground, a curious sea turtle glides by, adding to the dynamic beauty of this marine ecosystem.]" }, { "from": "gpt", "value": "Normal. The fish's body is twisted in the video." } ]
seed44_3089
videos/HRA_part1/3089.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, colorful scene unfolds where a person dressed in a black cape and white shirt, reminiscent of a bat, engages in an energetic dance. Their movements are fluid and dynamic, capturing the essence of nocturnal flight against a dark, starry sky. As they spin and leap, the cape billows dramatically, creating dramatic silhouettes against the twinkling celestial backdrop. The dancer's face is painted in black and white, accentuating the bat-like features, adding to the theatricality of the performance. Throughout the dance, the focus remains on the captivating interplay between the dancer's bat-inspired costume and the enchanting night sky.]" }, { "from": "gpt", "value": "Bad. The person's head, arms, and hands are distorted in the video." } ]
seed46_3106
videos/HRA_part2/3106.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded male musician, clad in a brown jacket, blue jeans, and a gray hat, walks through a dense forest filled with tall, lush green trees. He carries a guitar case over his shoulder, suggesting a journey to or from a performance. The woodland environment is rich with ferns and moss, creating a vibrant, natural setting. Sunlight filters through the canopy, casting dappled light on the forest floor as the musician strides purposefully along the path, his attire and equipment blending harmoniously with the woodlands.]" }, { "from": "gpt", "value": "Normal. The male musician's hands and feet in the video are generated deformed." } ]
seed44_2141
videos/HRA_part1/2141.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view captures a raw oyster, nestled on a bed of ice, its textured shell half-open to reveal a plump, glistening body. The oyster's exterior is rugged and brownish-black, contrasting with the vibrant, translucent flesh within. Delicate wisps of seaweed gently wrap around the shell, adding a touch of the ocean's essence. The scene is illuminated by natural light, highlighting the intricate patterns on the shell and the shimmering droplets of moisture on the oyster's surface.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_2549
videos/HRA_part1/2549.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, wearing a beige jacket and dark trousers, sits on a wooden dock by the water's edge. He gently caresses a small, curious otter that has climbed onto his lap, looking into its eyes with a warm smile. The otter, with its sleek brown fur and bright, inquisitive gaze, seems comfortable and at ease in the actor's presence. The scene is set against a serene backdrop of gently lapping waves and lush greenery, capturing a tender moment between human and animal in a peaceful natural setting.]" }, { "from": "gpt", "value": "Bad. The otter's movements in the video are not smooth." } ]
seed46_3096
videos/HRA_part2/3096.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, tropical dry forest, a distinguished film director, clad in a beige safari jacket, beige pants, and a wide-brimmed hat, meticulously orchestrates a captivating scene. Surrounded by the rich tapestry of nature, featuring tall, sun-bleached trees and vibrant green foliage, the director focuses intently on the action unfolding before him. The scene transitions to a stunning natural pool, where an athletic swimmer, wearing a black swimming cap and goggles, slices through the crystal-clear water with powerful strokes, showcasing grace and strength. The director watches from the edge, his expression a blend of concentration and appreciation for the beauty of both the forest and the swimmer's fluid movements.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1952
videos/HRA_part0/1952.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a young female cashier with a name tag, wearing a yellow shirt and black pants, is playfully jumping over a small, live hamster on the floor of a convenience store, capturing a lighthearted moment during her shift. The hamster, seen from above, scurries across the checkered floor, adding to the unexpected and amusing interaction. The cashier, still mid-jump, is framed by shelves of beverages and snacks, creating a surreal yet charming atmosphere in the store aisle. The scene is set under the bright lights of the shop, highlighting the unusual encounter between the employee and the tiny rodent.]" }, { "from": "gpt", "value": "Bad. The character in the video is distorted, with twisted facial expressions, twisted arms, twisted legs, and even the hamster's paws and face are distorted, along with the legs." } ]
seed44_194
videos/HRA_part1/194.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully in a clear blue sky, its sharp eyes scanning the grassy meadows below for prey. Its body is a sleek silhouette against the brightness, with a prominent head and compact wings. It then swoops down with remarkable agility, talons extended, targeting a small rodent in the tall grass. The bird's plumage is a striking mix of brown and gray, with a white underbelly marked by dark bands, as it lands on a branch, alert and ready to strike again. Finally, it takes flight once more, its powerful beats and aerodynamic form cutting through the air with precision, embodying the essence of a skilled avian predator.]" }, { "from": "gpt", "value": "Bad. The goshawk's face is distorted, the claws are twisted, and the wings are deformed." } ]
seed46_2478
videos/HRA_part2/2478.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, wearing a black t-shirt, showcases a ferret jumping from his right shoulder onto his left arm. Set against a dark grey background, the scene highlights the ferret's agility and the actor's engagement with the small animal. The actor's facial expression conveys amusement and surprise, emphasizing the playful interaction between man and pet. Throughout the sequence, the ferret performs several jumps, each time landing gracefully on different parts of the actor's body, while he remains fully engaged and attentive, his black t-shirt providing a stark contrast against the neutral backdrop.]" }, { "from": "gpt", "value": "Bad. The man's facial features are deformed, there is a missing part in the arm generation, and the ferret's body, limbs, and facial features are deformed." } ]
seed46_2945
videos/HRA_part2/2945.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great horned owl perches regally on a rugged tree branch, its piercing yellow eyes gazing intently into the distance under the cover of night. The owl's feathers are a stunning mix of brown, gray, and black, intricately patterned to provide perfect camouflage against the bark of the tree. Its large, feathered body appears robust, and its sharp talons grip the branch firmly. The owl's face is framed by a distinctive set of ear tufts, giving it a fierce and formidable appearance. In the background, the moonlight filters softly through the canopy of the forest, casting an ethereal glow on the owl and its surroundings. The atmosphere is tranquil, with only the sounds of nature breaking the silence, as the owl remains vigilant, ready to swoop down at any moment to catch its prey.]" }, { "from": "gpt", "value": "Normal. The owl's claws are twisted, and its head is slightly twisted." } ]
seed46_16
videos/HRA_part2/16.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ferret, wearing a red bow tie and small glasses, jumps joyfully on a miniature roller coaster car at a whimsical animal-sized amusement park. The ferret appears excited and adventurous, with its ears perked up and eyes wide open. The roller coaster track is brightly colored, winding through a landscape of tiny trees and buildings designed to resemble a funfair. Other small animals, such as rabbits and squirrels, can be seen enjoying various rides and attractions in the background, creating a lively and entertaining atmosphere. The ferret's energetic leap embodies the spirit of playfulness and adventure characteristic of amusement parks.]" }, { "from": "gpt", "value": "Normal. The ferret's movements in the video are not smooth." } ]
seed44_266
videos/HRA_part1/266.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by his black-framed glasses and neat appearance, stands in a modern kitchen with a clean, white countertop and stainless steel appliances. He wears a white chef's coat over a blue shirt and dark pants, and sports a neatly trimmed beard. He focuses intently on his cooking task, holding a whisk in his right hand and stirring a mixture in a bowl with precision and care. Behind him, a window allows natural light to illuminate the space, adding to the clean and professional atmosphere of the scene.]" }, { "from": "gpt", "value": "Normal. The engineer's movements in the video are basically normal, but there is some lack of coordination." } ]
seed46_1452
videos/HRA_part2/1452.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant, imaginative scene, a woman with a pixie haircut, dressed in a NASA astronaut suit, interacts playfully with a capuchin monkey wearing a matching miniature spacesuit, both standing inside a futuristic space education center. The room is filled with interactive displays and holographic projections, creating an immersive learning environment. Moments later, they are seen together in an indoor pool, designed to simulate zero-gravity conditions, where the woman and the monkey float effortlessly in their spacesuits, highlighting the unique experience of swimming in a space-themed educational facility.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous, there is a sudden change." } ]
seed42_132
videos/HRA_part0/132.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, clad in a black turtleneck and jeans, sits on a stage, intently playing a marimba with mallets. Nearby, a gorilla, perhaps a part of the performance or installation art, is crawling on all fours, wearing a red beret and blue jeans, adding an unexpected element to the scene. The contrast between the focused human artist and the ape in casual attire creates a surreal and captivating visual narrative.]" }, { "from": "gpt", "value": "Normal. The character's movements are not smooth." } ]
seed44_1664
videos/HRA_part1/1664.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling market filled with vibrant stalls and the sounds of commerce, a young male cashier, dressed in a blue button-down shirt and khaki pants, walks purposefully across the busy floor. He carries a green plastic bag, possibly containing produce or goods, adding a touch of realism to the scene. The market is alive with activity, from the colorful array of fruits and vegetables on display to the lively chatter of customers and vendors. The cashier navigates this energetic environment, his journey through the market captured in a series of dynamic shots that convey the lively atmosphere.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed46_258
videos/HRA_part2/258.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate female veterinarian, wearing a white lab coat and blue scrubs, gently feeds a small dog from a spoon, her caring nature evident in her warm smile. The clinic room is clean and modern, with stainless steel equipment and a large window providing natural light. Behind her, a poster about pet nutrition hangs on the pale green wall. On a nearby table, various pet food samples are neatly arranged, emphasizing the importance of proper animal care. Throughout the scene, the vet's loving interaction with the dog highlights her dedication to animal welfare.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_2417
videos/HRA_part0/2417.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, golden cheetah crawls under a low-hanging, silver photon sail, its eyes fixated ahead, muscles rippling beneath its spotted coat, set against a backdrop of a futuristic, metallic landscape. The sail, towering above, reflects beams of sunlight, creating an ethereal glow around the big cat. The cheetah, with its distinctive black tear markings and piercing green eyes, moves gracefully, its body positioned low to the ground, as if stalking prey, while the sail's advanced technology hints at a world beyond nature.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed44_1362
videos/HRA_part1/1362.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum after hours, a diligent worker in a blue uniform shirt crawls under an exhibit, focusing on maintenance tasks. The exhibit features ancient Egyptian artifacts, including a sarcophagus and hieroglyphic panels, with spotlights illuminating the space. The worker's attire includes safety gear, like gloves and a helmet, emphasizing the cautious approach required for handling historical items. The dimly lit museum hall, filled with glass display cases and statues, provides a dramatic setting for the solitary figure working beneath the exhibition platform.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_1578
videos/HRA_part1/1578.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, adorned in a cozy gray sweater and glasses, stands in a modern kitchen with sleek appliances, ready to craft stories. They pour water into a high-tech coffee machine, its illuminated screen displaying the brewing process, setting the scene for a productive day of writing. The individual then adds coffee grounds to the machine, preparing a perfect cup of coffee to fuel their creative endeavors. Dressed in a comfortable outfit and with a laptop nearby, they embody the ideal image of a writer ready to tackle the day, all while the aroma of freshly brewed coffee fills the air.]" }, { "from": "gpt", "value": "Bad. The character's arm is twisted, and the hand is distorted." } ]