video_id
stringlengths
8
11
video
stringlengths
22
25
conversations
listlengths
2
2
seed46_3118
videos/HRA_part2/3118.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red-tailed hawk soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rugged terrain below. It circles effortlessly, riding the thermals with grace, its sharp eyes scanning the ground for prey. The hawk's brown and white striped feathers shimmer in the sunlight, and its piercing yellow eyes and sharp curved beak are sharply defined. In the background, rolling hills and distant mountains provide a stunning natural landscape, all captured in stunning high-definition detail.]" }, { "from": "gpt", "value": "Bad. The red-tailed hawk's wings were generated deformed, the claws did not generate, and the body was generated twisted." } ]
seed46_2449
videos/HRA_part2/2449.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning male pheasant, adorned with vibrant plumage of iridescent greens and blues, struts proudly across a lush meadow filled with tall grasses and wildflowers. The sunlight filters through the canopy of towering trees, casting dappled shadows that accentuate the bird's magnificent feathers. The pheasant pauses, its sharp eyes scanning the surroundings, before letting out a distinctive call that echoes through the peaceful countryside, asserting its presence in the rich, natural habitat that surrounds it.]" }, { "from": "gpt", "value": "Normal. The pheasant's claws in the video are not fully generated, and the head is slightly distorted." } ]
seed42_254
videos/HRA_part0/254.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large construction crane dominates the skyline, its yellow and black body towering over a bustling cityscape at dusk. The crane's long arm stretches across the frame, adorned with industrial machinery and cables, as it stands on a partially constructed building amidst other tall structures. Workers in safety gear can be seen moving about the site, dwarfed by the massive crane, which looms against the orange and purple hues of the setting sun, casting long shadows over the urban landscape.]" }, { "from": "gpt", "value": "Bad. No workers were generated in the video." } ]
seed44_3147
videos/HRA_part1/3147.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising scene, a chimpanzee, wearing a small red apron, sits at a cash register typically found in a grocery store. The primate's eyes are closed as it receives a gentle caress from a human hand, which is softly petting its head, evoking a sense of calm and trust between the species. The chimpanzee's relaxed posture and closed eyes indicate a feeling of comfort and safety during this intimate interaction, set against the backdrop of a familiar checkout counter environment.]" }, { "from": "gpt", "value": "Bad. The person's hand shows deformities and mutations." } ]
seed46_2914
videos/HRA_part2/2914.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated nurse, wearing a classic white uniform and cap, checks a smoke detector in a hospital corridor, ensuring patient safety. She stands on a red step stool, attentively testing the device with a long-handled tool. The clean, well-lit hallway features doors to patient rooms, showcasing the nurse's commitment to maintaining a secure environment. Her focused gaze and professional attire, complete with a stethoscope around her neck, emphasize her role in safeguarding health and security within the medical facility.]" }, { "from": "gpt", "value": "Normal. The video only shows the camera moving while the nurse remains stationary." } ]
seed44_2191
videos/HRA_part1/2191.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A captivating scene unfolds, focusing solely on zebrafish within a clear, cylindrical fish tank. The vibrant striped patterns on the zebrafish stand out against the neutral background of the tank, which is devoid of any plants or decorations. The water is crystal clear, allowing every detail of the zebrafish, from their distinctive black and white stripes to their delicate fins, to be visible. The tank is illuminated by overhead lighting, casting a soft glow over the swimming zebrafish, highlighting their movement and the rippling effect they create in the water.]" }, { "from": "gpt", "value": "Normal. The fish swims basically normally in the video, but there is slight disharmony in the movements." } ]
seed42_2409
videos/HRA_part0/2409.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant coral reef ecosystem, a pair of butterfly fish, characterized by their distinctive black stripes and oval-shaped bodies, gracefully swim among the colorful corals and anemones. One fish displays a striking yellow hue with bold black markings, while the other exhibits a more subdued brown and white pattern. They navigate the intricate underwater landscape, their movements synchronized, as they explore the nooks and crannies of the reef in search of food. The scene is illuminated by the filtered sunlight that penetrates the clear blue water, casting dappled light on the fish and their surroundings.]" }, { "from": "gpt", "value": "Normal. The butterflyfish swims basically normally, but there is slight movement disharmony." } ]
seed44_134
videos/HRA_part1/134.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, identifiable by their beret and smock, kneels on a lush, alien landscape, sketching a capybara. The capybara, depicted in a relaxed posture, is the focal point, sitting amidst Martian flora. The scene is illuminated by the vibrant hues of a Martian sunset, casting an ethereal glow across the terrain. The artist's concentrated expression and the capybara's calm demeanor create a sense of tranquility, enhanced by the distant, rugged Martian mountains and the unique atmospheric conditions of the planet, which contribute to the vivid sunset colors. The artist's tools, including a palette and brushes, are scattered nearby, adding to the creative atmosphere of the scene.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_1144
videos/HRA_part0/1144.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, vibrant kitchen filled with the warm glow of overhead lights, a diverse group of four people, two women and two men, collaborate on preparing a feast. One woman, wearing a patterned apron over a floral dress, chops vegetables on a wooden cutting board placed on a granite countertop. Beside her, a man in a chef's jacket stirs a large pot on a professional stove, steam rising from the simmering contents. Another woman, donning a red bandana and denim jacket, carefully seasons a dish with herbs and spices, while the last man, clad in a checkered shirt, monitors the grill, flipping sizzling meats with tongs. The atmosphere is lively, with laughter and clinking utensils adding to the sense of camaraderie and shared purpose among the cooks.]" }, { "from": "gpt", "value": "Normal. The character's face is distorted, the arms are twisted, the hands are severely distorted, and the object in the man's hand is twisted." } ]
seed42_1851
videos/HRA_part0/1851.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic engineer, clad in a high-tech silver suit, is depicted running across a vast Galactic nebula, with swirling cosmic clouds and distant stars providing a dramatic backdrop. The engineer, wearing a sleek helmet that reflects the nebula's vibrant colors, is shown in various dynamic poses, conveying a sense of speed and determination. The scene is set against a massive, ethereal nebula, its colorful gas formations creating a stunning visual contrast with the engineer's metallic attire, emphasizing the thrilling combination of human endeavor and the awe-inspiring scale of the universe.]" }, { "from": "gpt", "value": "Normal. The engineer in the video runs basically normally, but there is some lack of coordination in the movements." } ]
seed42_1490
videos/HRA_part0/1490.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a helmet, leaps over debris inside a burning apartment complex, the intense flames and smoke creating a dramatic backdrop. The scene highlights the heroism and physical demands faced by firefighters in rescue operations. The exterior of the complex shows multiple stories engulfed in fire, emphasizing the scale of the emergency. The firefighter's decisive action, jumping over obstacles, symbolizes the urgent and dangerous nature of their mission to save lives and contain the blaze.]" }, { "from": "gpt", "value": "Normal. The character's movements are not smooth." } ]
seed46_1026
videos/HRA_part2/1026.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a beige jacket, black t-shirt, and khaki pants, stands thoughtfully at a hot springs site, contemplating a unique shot. Suddenly, a rhinoceros emerges from the mist, leaping gracefully over a small pond within the springs. The director watches intently, camera in hand, ready to capture the extraordinary moment as the sun sets behind, casting a golden hue over the scene. The rhinoceros, now the central figure, jumps with surprising agility amidst the steamy waters, creating an unforgettable juxtaposition of nature and wildlife against the backdrop of the director's vision.]" }, { "from": "gpt", "value": "Bad. The rhino's legs in the video are incomplete." } ]
seed46_1339
videos/HRA_part2/1339.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a muscular build, wearing a white sleeveless undershirt and dark gray jeans, stands on a wooden platform, intently applying paint to a large canvas with a brush. The focus is on his hands, which are covered in paint, as they skillfully create an abstract artwork. Behind him, a row of neatly arranged paint cans sits on a wooden floor, and the walls of the studio are painted white, creating a clean, professional environment. The artist's concentration is evident in his furrowed brow and the intensity of his gaze, while the vibrant colors on the canvas contrast with the neutral tones of his clothing and surroundings.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_1777
videos/HRA_part0/1777.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling city square, under the soft glow of streetlights and the clear night sky, a diverse group of individuals, including a man with a beard, a woman with glasses, and another woman with a ponytail, are all looking intently at something above them. Their postures and facial expressions convey a sense of awe and wonder, suggesting they are captivated by an extraordinary sight in the urban landscape. Among them, a man with a beard and a woman with glasses stand side by side, both gazing upwards with intense focus. Beside them, a woman with her hair in a ponytail also looks up, her face reflecting a mix of surprise and fascination. All around, the city continues its nightly activities, but these people remain transfixed, united in their shared attention to an unseen marvel overhead.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2054
videos/HRA_part0/2054.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and holding a fire hose, is seen wiping the nose of a meerkat standing on its hind legs, both against a backdrop of a controlled fire burning in a contained area. The firefighter wears a yellow fire-resistant suit, a black helmet, and gloves, while kneeling to gently wipe the meerkat's face with a cloth. The meerkat, curious and seemingly unbothered by the flames in the background, stands upright as the firefighter tends to it, creating an unusual yet touching interaction between the two.]" }, { "from": "gpt", "value": "Bad. No water hose or cloth was generated." } ]
seed42_3013
videos/HRA_part0/3013.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a white apron over a black shirt and gray pants, is seen scrubbing the bathroom floor with a green cleaning brush. The room is illuminated by overhead lights, and the chef's serious expression conveys the importance of cleanliness. In another angle, the chef, still in his chef's uniform, is shown on his knees, focused on scrubbing the bathroom tiles with determination. The video emphasizes the chef's commitment to hygiene, even in non-food-related areas, as he meticulously cleans the bathroom floor with a green cleaning brush under the bright lights.]" }, { "from": "gpt", "value": "Normal. The man's arm undergoes deformation." } ]
seed46_1235
videos/HRA_part2/1235.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a waiter in a crisp, white uniform gracefully carries a tray with a solar sail design etched onto it, reflecting the ambient light beautifully. The scene transitions to reveal a vast, serene pool where individuals swim leisurely, their movements creating ripples on the water's surface. The connection between these elements is seamless, as the solar sail motif continues to play a prominent role throughout the scene, symbolizing the merging of technology and tranquility. The waiter's elegant stride and the swimmers' peaceful strokes form a harmonious contrast, encapsulating the essence of a luxurious and innovative aquatic experience.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous, there are sudden changes." } ]
seed44_2338
videos/HRA_part1/2338.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an assortment of smaller fish. The grouper, distinguished by its size and spotted brown skin, explores its surroundings with a sense of ownership, occasionally pausing to inspect something of interest. Its powerful body and broad fins propel it through the crystal-clear waters, showcasing the serene beauty of life beneath the ocean's surface.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_2955
videos/HRA_part1/2955.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow fire-resistant jacket, is kneeling by a blocked drain on a rainy day, amidst urban surroundings. He wields a long, coiled hose and a specialized tool, methodically working to unclog the drain. His focused expression and the rain-soaked environment underscore the challenging task at hand. Moments later, he pulls the clog from the drain, revealing a mix of debris, while water begins to flow freely again, thanks to his diligent efforts. Throughout, the firefighter's protective gear and the wet cityscape provide context to the scene.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_2557
videos/HRA_part2/2557.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, two figures, a man and a woman, both wearing sophisticated, form-fitting silver spacesuits with intricate blue detailing, walk purposefully down a sleek corridor lit by soft, ambient blue light. They carry themselves with the poise and dignity of diplomats, their movements deliberate and confident. The man sports a neatly trimmed beard and short, dark hair, while the woman wears her long, curly hair in a high bun, adorned with small, sparkling silver clips. Both wear expressions of intense concentration, reflecting the gravity of their mission among the stars. Behind them, the corridor stretches into darkness, hinting at the vastness of space and the unknown adventures awaiting them.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_3133
videos/HRA_part2/3133.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature man with graying hair, dressed in a white T-shirt and black exercise pants, stretches his body against a gray studio wall. He leans forward with his right leg extended, foot against the wall, and his left leg bent, demonstrating flexibility. His hands rest on his right thigh and shin, while his head tilts down, showcasing a focused expression. Behind him, a large window reveals a blurred outdoor view, adding depth to the scene. The room is illuminated by soft, natural light, highlighting the man's dedication to maintaining his physical health.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_2887
videos/HRA_part1/2887.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cheerful nurse in a traditional white uniform and cap leaps playfully across the muddy terrain of a swampy forest, surrounded by tall, lush green ferns and moss-draped trees. The scene is vibrant and lively, with splashes of mud adding a dynamic element to her joyful activity. She bounds from one spongy moss-covered log to another, her movements fluid and energetic, a stark contrast to the typically serene and still environment of the swamp. The nurse's actions are filled with a sense of adventure and freedom, her figure standing out brightly against the dark, rich greens of the swamp vegetation.]" }, { "from": "gpt", "value": "Bad. The nurse's jumping action in the video is not smooth." } ]
seed42_1125
videos/HRA_part0/1125.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a dark suit, shirt, and tie, walks through a stunning geothermal field, surrounded by steaming geysers and colorful mineral deposits. The scene begins with the lawyer walking towards a large, erupting geyser, the water shooting high into the air against the dramatic landscape. Next, he pauses to observe another geyser, the steam rising from it creating a mystical atmosphere. Then, he continues walking, passing by a series of smaller geysers, their bubbling waters and vibrant colors contrasting sharply with his formal attire. Lastly, the lawyer is seen walking away from the camera, the vast geothermal field stretching out behind him, the geysers and steam adding an otherworldly touch to the professional setting.]" }, { "from": "gpt", "value": "Normal. The character's body is twisted, and the arms are distorted." } ]
seed42_1822
videos/HRA_part0/1822.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, complete with a stethoscope around his neck and wearing a white lab coat over a blue button-down shirt and khaki pants, sits by a serene lake, holding a fishing rod. The peaceful scene is set against a backdrop of lush greenery and a clear blue sky, with the doctor's attire and occupation contrasting with the tranquil activity of fishing. As he casts his line into the water, the camera captures the reflective surface of the lake and the doctor's focused yet relaxed demeanor, highlighting the juxtaposition between his professional life and his leisurely pursuit.]" }, { "from": "gpt", "value": "Normal. The doctor's actions of holding the fishing rod and fishing in the video are not very smooth and continuous." } ]
seed42_2216
videos/HRA_part0/2216.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer wearing a dark green jacket, blue jeans, and brown boots stands in a lush, green meadow dotted with dandelions. He looks down with a slight smile as he spots a small vole. The vole, with its distinctive round ears and brown fur, leaps from one dandelion tuft to another in the foreground, creating a playful contrast against the serene farm landscape. The farmer watches the vole's antics with amusement, his stance relaxed and his hands resting on his hips, as the rural setting provides a peaceful backdrop to this unexpected interaction.]" }, { "from": "gpt", "value": "Bad. The vole's body slightly deformed when it was moving." } ]
seed44_2431
videos/HRA_part1/2431.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a green uniform and safety vest, is seen intently wiping a large, realistic lizard statue with a cloth, ensuring its scales gleam under the bright sun. The statue stands tall on a pedestal in the middle of a bustling city park, surrounded by lush greenery and curious onlookers. The worker's focused expression and meticulous movements highlight the importance of maintaining public art, while the vibrant colors of the lizard statue contrast beautifully with the verdant foliage in the background.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_2577
videos/HRA_part2/2577.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a dark blue shirt and gray pants, walks purposefully through a modern art gallery, surrounded by large, abstract paintings and sculptures. He pauses to examine a piece closely, his posture attentive and engaged. Continuing his stroll, he passes by minimalist artworks, each occupying its own space within the spacious, well-lit gallery. Finally, he stops before a particularly striking sculpture, tilting his head to study it from different angles, his attire and demeanor contrasting with the avant-garde surroundings.]" }, { "from": "gpt", "value": "Bad. The man in the video walks very unsmoothly, and his movements are uncoordinated." } ]
seed46_2341
videos/HRA_part2/2341.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white hare, its fur thick and plush, crawls through a dense thicket of snow-laden pine trees, the texture of its coat contrasting starkly with the icy landscape. The hare's movements are cautious and deliberate, its eyes alert, as it navigates the snowy terrain in search of food. The scene is set against a backdrop of a serene winter forest, the hare's crawling motion emphasized by the slow, methodical pace, creating a sense of intimacy with the animal in its natural habitat.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_261
videos/HRA_part2/261.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, wearing a gray t-shirt and jeans, attentively waters lush green plants arranged in a neat row against a plain studio wall. He begins by pouring water from a green watering can onto the first plant, a potted ficus. Next, he moves to the second plant, a healthy monstera, continuing his task with care. Then, he focuses on the third plant, a vibrant snake plant, ensuring each receives adequate hydration. Lastly, he tends to the fourth plant, a thriving peace lily, completing the sequence with dedication, all within the simple yet functional confines of the studio space.]" }, { "from": "gpt", "value": "Normal. The director's action of watering the plant in the video is not smooth and continuous, with abrupt changes." } ]
seed42_1166
videos/HRA_part0/1166.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, donning avant-garde space fashion, sprints across a futuristic stage illuminated by neon lights. Dressed in a metallic silver bodysuit, complete with high-tech accessories and a helmet visor, they leap with dynamic energy. The scene is set in a grand, space-themed venue, filled with an audience captivated by the performance. Spotlights follow the actor as they navigate the runway, showcasing the innovative designs against a backdrop of cosmic visuals and ambient electronic music. The fusion of performance art, cutting-edge fashion, and sci-fi aesthetics creates a mesmerizing spectacle.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2065
videos/HRA_part2/2065.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy landscape under a clear blue sky, a woman wearing a flowing, cream-colored robe gently caresses a kneeling camel adorned with ornate saddles and blankets. The scene captures the tender bond between the woman and the camel, with her hand softly stroking its head. The woman's attire complements the desert environment, and her gentle touch conveys a sense of care and connection. Nearby, more camels stand, their presence adding to the serene atmosphere of the desert setting.]" }, { "from": "gpt", "value": "Bad. The arms, hands, face, camel's face, neck, and legs are distorted in the video." } ]
seed42_1852
videos/HRA_part0/1852.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier, with a casual hairstyle and wearing a dark green jacket over a gray t-shirt, leans against a white wall with a wooden panel. She holds a book titled \"The Great Gatsby\" by F. Scott Fitzgerald, reading it intently during a break. The scene is set in a grocery store aisle, with shelves stocked with products like canned goods and boxes of cereal visible in the background. The cashier's relaxed posture and focused gaze on the classic novel convey a sense of peace and personal time amidst her work environment.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed42_1375
videos/HRA_part0/1375.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning close-up of a rainbow trout fills the frame, its vibrant colors and intricate patterns captivating the viewer. The fish, partially submerged in crystal-clear water, showcases its beauty against a backdrop of smooth river stones and lush green vegetation. Its silver scales glisten in the sunlight, while its red and blue stripes stand out against the clear water. The trout's large, expressive eyes and delicate fins add to its charm, making it the undeniable star of the scene. The rippling water around it creates a sense of movement and life, immersing the viewer in the tranquil yet dynamic environment of a freshwater stream.]" }, { "from": "gpt", "value": "Normal. The video shows too many red marks on the trout's body." } ]
seed46_2826
videos/HRA_part2/2826.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a kangaroo, dressed in a chef's hat and apron, is shown playfully hopping around a vibrant, modern restaurant kitchen filled with gleaming stainless steel appliances and colorful, contemporary decor. The kangaroo then takes a break from its culinary duties to enjoy a refreshing swim in an outdoor pool, surrounded by lush greenery and bright, sunny skies, creating a surreal and delightful blend of dining and leisure. After its swim, the kangaroo returns to the restaurant, where it is greeted by patrons sitting at tables, enjoying their meals in the stylish dining area, complete with large windows offering views of the beautiful landscape outside. Finally, the kangaroo is seen back in the kitchen, preparing a dish with precision and care, as if it were a true master chef, all while maintaining its playful and endearing demeanor.]" }, { "from": "gpt", "value": "Bad. The kangaroo's movements in the video are not smooth." } ]
seed42_2758
videos/HRA_part0/2758.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a red plaid shirt, blue jeans, and a wide-brimmed straw hat, diligently sweeps his wooden porch with a long-handled broom, the early morning sun casting a warm glow over the rural scene. Beside him, a white dog rests lazily on the porch, enjoying the peaceful ambiance. The farmer pauses to wipe sweat from his brow, revealing a face lined with years of hard work and dedication to his land. He continues sweeping, the rhythmic sound of the broom against the wood providing a soothing soundtrack to the quiet countryside morning. Behind him, a lush green landscape stretches out, dotted with crops and farm buildings, a testament to his labor and connection to the earth.]" }, { "from": "gpt", "value": "Bad. The man's facial features in the video are generated blurry, his hands are deformed, and the white dog is abnormally generated. In the middle frame, the man's hand holding the broom suddenly distorts and deforms." } ]
seed42_2605
videos/HRA_part0/2605.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara runs energetically across a grassy plain, its wet nose and alert eyes highlighting its distinctive features. It bounds forward with determination, showcasing its muscular legs and agile movements. Moments later, the capybara leaps gracefully over an obstacle, demonstrating its impressive jumping ability. Then, it sprints with focused intensity, ears perked, and nostrils flared, against a backdrop of lush vegetation and distant hills. Finally, the capybara continues its swift run, its body language conveying strength and vitality as it navigates the open landscape.]" }, { "from": "gpt", "value": "Bad. The capybara's running in the video is very unsmooth, and the movements are uncoordinated." } ]
seed46_2300
videos/HRA_part2/2300.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-themed setting, a costumed performer dressed as a monkey is seen dancing against a backdrop of asteroid mining operations. The monkey wears a spacesuit with a helmet, moving energetically in zero gravity. Behind it, robots with mechanical arms mine valuable minerals from large asteroids, while spaceships shuttle between them. The scene combines elements of science fiction, entertainment, and industrial activity, all set against the backdrop of outer space. The monkey's playful antics contrast with the serious business of asteroid mining, creating a visually engaging and unexpected juxtaposition.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_2759
videos/HRA_part0/2759.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, a mustache, and glasses sits against a white wall, intently sewing a button onto a piece of fabric with a red thread. He wears a gray shirt, and the focus is on his hands, which hold the needle and thread with precision. His facial expression is concentrated, and he occasionally looks up, offering a slight smile. Throughout, he continues his task diligently, the red thread weaving in and out of the button holes, securing it firmly to the fabric. The simplicity of the setting allows the viewer to fully appreciate the man's skill and attention to detail in this everyday task.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_1605
videos/HRA_part2/1605.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric landscape under an overcast sky, a colossal mammoth, covered in thick, shaggy fur, is seen crawling on its knees, struggling through deep snow. Its large tusks and body are caked with ice and snow, emphasizing its immense size and the harsh conditions it endures. The creature's eyes, filled with determination and resilience, are set against the barren, icy wilderness, capturing the essence of survival in a frozen world.]" }, { "from": "gpt", "value": "Normal. The mammoth in the video is not on its knees." } ]
seed42_227
videos/HRA_part0/227.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged farmer with a short beard, dressed in a green flannel shirt, brown vest, brown trousers, and brown boots, hikes across a lush, green pasture. The vibrant colors of his clothing contrast beautifully with the verdant landscape. In the first scene, he pauses to look up at the sky, which is partly cloudy, indicating a pleasant day. Then, he continues hiking, walking uphill towards a dense forest in the distance, the rolling hills providing a stunning backdrop. Next, he stops to observe a group of sheep grazing nearby, his presence conveying a sense of peace and harmony with nature. Lastly, he is seen walking along a narrow path bordered by tall grass, his figure becoming smaller as he moves further away, encapsulating the spirit of adventure and connection to the land.]" }, { "from": "gpt", "value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements." } ]
seed46_2874
videos/HRA_part2/2874.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 experienced engineer, clad in a futuristic spacesuit with an illuminated helmet, embarks on a critical space rescue mission. Against the backdrop of a vast, starlit cosmos, he is seen swimming through the emptiness of space, propelled by bursts from his suit's thrusters. With a focused gaze and a determination to save lives, he maneuvers towards a damaged spacecraft, its hull breached and systems failing. The engineer's suit, equipped with advanced technology, allows him to navigate the zero-gravity environment with precision and grace, as he reaches the stricken vessel to begin emergency repairs.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_192
videos/HRA_part1/192.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, wearing a yellow helmet, a white tank top, blue jeans, and brown work boots, pauses from his labor to stand on a sandy beach, the serene ocean stretching behind him. He takes a moment to enjoy the view before energetically diving into the clear blue water, his clothes still on, embracing the refreshing swim. Underwater, he opens his eyes, revealing his blue goggles, as he swims with purpose, surrounded by the vivid marine life and the bright sunlight filtering through the surface. Afterward, he emerges from the sea, dripping wet, and walks back to his work site, leaving wet footprints on the sand, embodying a break well taken.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed42_1152
videos/HRA_part0/1152.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female cashier, dressed in a brown apron over a black top and gray pants, is fixing a mountain bike in a grocery store. The bike, with its wheels removed, rests on a repair stand, as she focuses intently on her task. Customers can be seen shopping in the background, adding an element of surprise to the setting. She works diligently, surrounded by store shelves stocked with various products, creating a juxtaposition between her usual role and the unusual activity of bike repair in a retail environment.]" }, { "from": "gpt", "value": "Bad. The character's face is distorted, the hands are severely distorted, and the arms are deformed." } ]
seed46_2518
videos/HRA_part2/2518.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil woodlands setting, characterized by lush vegetation and a serene atmosphere, a herd of majestic buffalo graze peacefully. The scene focuses on a single buffalo, its massive frame gently caressed by the soft branches of a weeping willow tree. The willow's slender leaves delicately brush against the buffalo's sturdy body, creating a tender and unexpected interaction between nature and wildlife. The buffalo's calm demeanor and the gentle sway of the willow branches in the breeze convey a sense of harmony and tranquility in the midst of the dense woodland.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_3128
videos/HRA_part0/3128.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bulletproof vest, climbs an arduous route up a steep, rocky cliff, demonstrating determination and skill. His equipment includes a helmet, harness, and climbing gear attached to his belt, while he uses a carabiner to secure his rope. The scene is set against a rugged landscape with lush greenery and distant mountains, highlighting the officer's physical prowess and commitment to overcoming challenges. The camera captures his focused face, the intricate details of his gear, and the breathtaking scenery, emphasizing the intensity and purpose of his climb.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_2842
videos/HRA_part1/2842.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space casino illuminated by neon lights, a golden retriever dog dons a stylish astronaut suit and a green swimming cap. The dog stands beside a luxurious, crystal-clear pool, surrounded by floating poker tables and slot machines, all set against the backdrop of a vast, star-studded universe. The dog appears happy and curious, ready to enjoy a refreshing swim among the celestial gambling atmosphere. Nearby, an alien bartender mixes a colorful cocktail, adding to the surreal and playful scene.]" }, { "from": "gpt", "value": "Normal. The dog's head is slightly distorted, the paws are slightly twisted, and the tail is twisted." } ]
seed46_175
videos/HRA_part2/175.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space medical facility, a man wearing a clean, white lab coat and blue surgical mask diligently wipes down advanced, high-tech equipment with precision and care. The room is illuminated by soft, ambient lighting, highlighting the sterile environment. The man's focused gaze and meticulous movements convey a sense of professionalism and dedication to maintaining the cleanliness of the facility. Around him, the walls are lined with monitors and medical devices, emphasizing the cutting-edge technology used in this extraterrestrial healthcare setting.]" }, { "from": "gpt", "value": "Bad. The man's movements in the video are not smooth and lack coordination." } ]
seed46_1373
videos/HRA_part2/1373.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, wearing a red plaid shirt and khaki pants, stands tall with his hands resting on a wooden fence, his gaze directed at a stunning sunset. Behind him, a lush green forest stretches into the distance, while the golden rays of the setting sun illuminate the landscape, casting a warm glow over everything. The man's posture suggests a sense of peace and tranquility as he takes in the breathtaking view before him.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2320
videos/HRA_part2/2320.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor wearing a yellow high-visibility vest and khaki pants walks purposefully down a dimly lit tunnel, holding a flashlight that illuminates the way ahead. The tunnel walls, painted a dull gray, are lined with pipes and electrical conduits, providing a gritty industrial backdrop. Shadows cast by the janitor's flashlight dance on the walls, adding a sense of depth and mystery to the scene. The janitor's steps echo in the confined space, punctuating the otherwise silent atmosphere of the tunnel system.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_3219
videos/HRA_part2/3219.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a classic gray suit with a blue tie, speaks earnestly into a microphone at a podium, set against a backdrop of a rich wood-paneled room. His hands gesticulate passionately as he addresses an unseen audience, conveying a sense of urgency and importance. The room is illuminated by soft, ambient lighting, highlighting the serious nature of the discussion. Close-ups capture the intensity in his eyes and the determination etched on his face, emphasizing the gravity of his words in this legal setting.]" }, { "from": "gpt", "value": "Bad. The lawyer's facial features in the video are not clearly generated, and the fingers are deformed." } ]
seed42_2405
videos/HRA_part0/2405.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a yellow long-sleeved shirt and gray pants, diligently cleans a large fish tank located in the corner of a classroom, filled with various colorful fish. The tank is illuminated by overhead lights, casting a warm glow on the aquatic environment. The student, with short brown hair and glasses, carefully removes algae from the glass walls using a scraper, ensuring a clear view of the vibrant underwater world. The scene captures the student's focused determination and the peaceful coexistence of education and nature within the classroom setting.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous and there are sudden changes." } ]
seed46_3058
videos/HRA_part2/3058.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious monkey, dressed in a red life jacket, sits on a wooden pier extending over a serene body of water, surrounded by lush greenery and tall trees. The monkey then playfully jumps into the clear blue water, creating ripples that spread outward. It swims energetically, its small arms paddling through the water, while a pair of sunglasses float nearby, adding a touch of whimsy to the scene. The monkey eventually climbs back onto the pier, shaking off droplets of water, with the sun casting a warm glow over the entire setting.]" }, { "from": "gpt", "value": "Normal. The monkey is not sitting on the dock." } ]
seed42_1043
videos/HRA_part0/1043.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chimpanzee dressed in a red vest acts as a cashier, sitting at a checkout counter filled with groceries. The chimp, wearing a name tag and a friendly smile, leans forward to scan items with a handheld barcode scanner. Suddenly, it drops the scanner and begins crawling on all fours, playfully moving across the wooden floor of the store. The camera follows the chimp as it crawls between the aisles, its red vest contrasting against the green apples and yellow bananas displayed on the shelves. Throughout the scene, the chimp's expressive face and curious behavior provide a lighthearted and engaging visual experience.]" }, { "from": "gpt", "value": "Normal. The chimpanzee's movements in the video are not smooth." } ]
seed42_1871
videos/HRA_part0/1871.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, distinguished by his chiseled features and casual attire of a blue shirt and jeans, gently caresses an antelope at a zoological park. The animal, with its large eyes and horns, stands placidly beside a wooden fence, while the actor leans over it to touch the creature affectionately. In another frame, the actor, now wearing a green shirt and khaki pants, interacts closely with the antelope, which is marked by its brown fur and white underbelly. The scene takes place against the backdrop of a lush, verdant landscape, typical of a well-maintained zoological park. Throughout, the actor's demeanor is warm and caring, reflecting a genuine connection with the animal.]" }, { "from": "gpt", "value": "Normal. No generation of the actor wearing a green shirt and khaki pants." } ]
seed44_2051
videos/HRA_part1/2051.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed anthropomorphic fox, wearing a doctor's white lab coat over a crisp blue shirt and a stethoscope around its neck, is seen swimming in a clear blue pool. The fox maintains a relaxed yet focused expression, showcasing its unique ability to swim effortlessly while fully clothed. The pool is surrounded by lush greenery, creating a serene atmosphere as the sunlight filters through the leaves, casting dappled shadows on the water's surface.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_1145
videos/HRA_part2/1145.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, donning a yellow shirt and dark glasses, vacuums the floor of a bright room filled with musical instruments. The scene opens with the musician, wearing a yellow t-shirt, dark glasses, and a smile, vacuuming the carpeted floor. The room is illuminated by sunlight streaming through a large window, casting a warm glow on the various instruments scattered about, including guitars, drums, and keyboards. As the musician moves the vacuum cleaner across the floor, they pause to adjust a guitar strap hanging from a nearby stand, revealing a passion for music even during mundane household tasks. The final shot captures the musician, still smiling, vacuuming near a drum set, highlighting the harmonious blend of daily chores and artistic pursuits within the vibrant space.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2172
videos/HRA_part0/2172.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a live clam lying half-open on a bed of damp sand, revealing its intricate interior textures and colors. The clam's exterior is rugged and brownish-black, while the interior showcases a lustrous, pearly surface. The sandy substrate is speckled with small stones and shells, adding to the natural coastal environment. Sunlight filters through the water, casting a soft glow on the scene, highlighting the clam's delicate features and the surrounding grains of sand.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_206
videos/HRA_part1/206.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 European badger, distinguished by its black and white striped face and brown fur, scurries through a network of intricately dug tunnels in a dimly lit sett. The animal, with its stocky build and sharp claws, moves swiftly and purposefully, navigating the narrow passages with ease. As it runs, the texture of the tunnel walls, composed of earth and roots, becomes apparent, providing a natural contrast to the badger's movement. Throughout the sequence, the focus remains on the badger's journey within the tunnel system, emphasizing its agility and familiarity with its subterranean habitat.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1121
videos/HRA_part0/1121.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a khaki safari outfit, is seen in a lush, green jungle environment, carefully cleaning a majestic tiger with a large cloth. The tiger, displaying distinctive orange stripes on a white underbelly, remains calm and cooperative during the process. The director, showing respect and gentleness, focuses intently on wiping the tiger, highlighting a unique bond between human and animal in a wild setting.]" }, { "from": "gpt", "value": "Bad. The character's action of wiping the tiger in the video is not smooth." } ]
seed44_1129
videos/HRA_part1/1129.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting, a waiter dressed in a crisp white shirt and black pants is seen sprinting energetically between charming houses with red-tiled roofs. The houses are adorned with lush green vines and windows framed by vibrant flowers. The waiter carries a silver tray aloft, maintaining perfect balance as he navigates the cobblestone streets. Each house has its own unique character, from wooden shutters to ornate door knockers, providing a picturesque backdrop for the waiter's urgent dash. The scene is imbued with a sense of community and lively activity, as the waiter's route weaves through the heart of the village, connecting the homes with his swift, professional service.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed46_1633
videos/HRA_part2/1633.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer kneels on a black rubber mat, meticulously repairing a vintage motorcycle in a cluttered garage. Wearing a gray t-shirt, navy blue cap, and tan cargo pants, he focuses intently on his work, surrounded by tools and parts. The garage walls are adorned with posters of classic cars and bikes, adding a nostalgic touch. A large, well-lit workbench is visible nearby, equipped with various tools and mechanical components. The engineer's hands move skillfully as he tightens bolts and adjusts the bike's engine, demonstrating his expertise and passion for restoring old motorcycles.]" }, { "from": "gpt", "value": "Normal. The character's face, hands, feet, and arms are distorted in the video." } ]
seed42_1074
videos/HRA_part0/1074.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned farmer, clad in a white shirt and brown trousers, stands in the middle of a lush green field under a clear blue sky. He is in mid-action, throwing hay bales with ease and precision. His weathered hands grip a bale tightly as he winds up for the toss, muscles straining beneath his shirt. The hay bales are scattered around him, some neatly stacked, others awaiting his expert throw. The farmer's face is set in determination, eyes focused on the target, embodying the hard work and strength synonymous with farming life.]" }, { "from": "gpt", "value": "Bad. The character's arm and head are deformed in the video." } ]
seed44_2453
videos/HRA_part1/2453.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 sunlit subtropical dry forest, a small, brownish-grey vole emerges from beneath the leaf litter, its fur blending seamlessly with the earthy tones of its surroundings. It pauses, nose twitching, before taking cautious steps forward, navigating the intricate network of twigs and leaves that carpet the forest floor. The vole's round ears and curious eyes are sharply focused, scanning the environment for both threats and opportunities as it walks through this arid woodland habitat, the sunlight filtering through the sparse canopy above.]" }, { "from": "gpt", "value": "Good. Basically no 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 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 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": "Bad. The leopard's head and neck are twisted in the video." } ]
seed44_1650
videos/HRA_part1/1650.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a gray jacket and dark pants, walks through a grassy campus area, holding a small, fluffy rabbit in their hands. They gently cradle the rabbit, which has white fur and black ears, as they stroll under a clear blue sky. The student occasionally looks down at the rabbit with a smile, while passersby glance curiously at the unusual sight. The scene is peaceful, with the student and rabbit seemingly enjoying each other's company in the outdoor setting.]" }, { "from": "gpt", "value": "Bad. The rabbit's face and limbs were not generated in the video, and the man's fingers were not fully generated, lacking facial features." } ]
seed42_1731
videos/HRA_part0/1731.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 swift, agile falcon soars majestically through the clear blue sky, its sharp eyes scanning the vast landscape below for any signs of prey. Its streamlined body, adorned in rich brown and white plumage, cuts through the air with effortless grace. With each powerful beat of its wings, it gains altitude, becoming a mere speck against the endless expanse of azure. Suddenly, spotting a small rodent in the fields below, the bird tucks its wings and dives, transforming into a blur of speed and precision. The falcon's silhouette against the bright sky is a testament to its namesake - swift and unyielding in its pursuit.]" }, { "from": "gpt", "value": "Bad. The falcon's soaring movements in the video are not smooth and continuous, and there are abrupt changes in the falcon's limbs." } ]
seed46_1308
videos/HRA_part2/1308.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patient teacher, wearing a brown jacket and khaki pants, stands in a rural classroom with wooden desks and a world map on the wall. She gently caresses a small deer that has wandered inside, creating a tender moment. The deer, with its large eyes and curious demeanor, stands calmly beside the teacher, who offers a comforting presence. Both the teacher and the deer are bathed in the warm, golden light filtering through the windows, adding to the serene atmosphere of the scene.]" }, { "from": "gpt", "value": "Normal. The teacher's action of petting the deer in the video is basically normal, with slight awkwardness." } ]
seed44_2514
videos/HRA_part1/2514.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space habitat designed to mimic Earth's savanna, a majestic rhinoceros, fitted with a specialized spacesuit, calmly walks on artificial grass under a simulated sky. Tourists, dressed in sleek, white spacesuits, observe from a safe distance behind transparent barriers, their expressions a mix of awe and curiosity. The rhino moves gracefully, its every step monitored by advanced technology to ensure its well-being in the zero-gravity environment. This unique scene captures the harmony between wildlife conservation and the boundless possibilities of space exploration, offering viewers a glimpse into a world where nature and technology coexist in the vastness of space.]" }, { "from": "gpt", "value": "Normal. The rhino's face and legs are distorted in the video." } ]
seed42_2835
videos/HRA_part0/2835.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet tender scene, a large brown bear gently caresses a smaller, lighter-brown bear against the backdrop of a vast savanna landscape. The two bears sit on the golden grass, under a clear blue sky dotted with a few white clouds. The big bear has its arm around the smaller one, while the other paw is softly stroking the smaller bear's head. Both bears wear collars, indicating they might be part of a conservation program. This heartwarming interaction unfolds in a protected area of the savanna, where wildlife coexists in harmony.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_3133
videos/HRA_part2/3133.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature man with graying hair, dressed in a white T-shirt and black exercise pants, stretches his body against a gray studio wall. He leans forward with his right leg extended, foot against the wall, and his left leg bent, demonstrating flexibility. His hands rest on his right thigh and shin, while his head tilts down, showcasing a focused expression. Behind him, a large window reveals a blurred outdoor view, adding depth to the scene. The room is illuminated by soft, natural light, highlighting the man's dedication to maintaining his physical health.]" }, { "from": "gpt", "value": "Bad. The video shows the man leaning forward, head hanging down, hands placed on his right thigh and shin, right leg extended with his foot against the wall, and left leg bent. The movements are not continuous and smooth, and there is a lack of coordination." } ]
seed44_2433
videos/HRA_part1/2433.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 director, distinguished by his brown hair and beard, along with round glasses, is seated in a director's chair on a set resembling a grassland heath. He interacts with a small gerbil, which scurries across the set's surface. The director is shown wiping his glasses with a cloth, revealing his blue eyes, while the gerbil continues its exploration nearby. The backdrop depicts a sunny day on the heath, complete with a blue sky and green vegetation, adding a natural element to the studio setting. Throughout, the director's focus alternates between the gerbil and wiping his glasses, capturing the unique dynamic between the two.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth, and the hamster's movements are also not smooth." } ]
seed44_2150
videos/HRA_part1/2150.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large Grouper fish, known for its speckled brown and white skin, swims serenely in clear, blue-green waters, surrounded by vibrant coral reefs teeming with life. Its powerful body, complete with a wide mouth and large eyes, glides effortlessly through the underwater environment. The Grouper pauses, hovering near a cluster of colorful corals and exotic marine life, showcasing its size and strength against the intricate patterns of the reef. The scene captures the fish's natural habitat, highlighting the contrast between its imposing presence and the delicate beauty of the coral ecosystem.]" }, { "from": "gpt", "value": "Bad. The generation of the mouth and fins of the grouper in the video has problems." } ]
seed46_1305
videos/HRA_part2/1305.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black panther leaps majestically across a moonlit savannah, its muscles rippling beneath dark fur that shimmers under the celestial glow. The powerful feline bounds over tall grasses, leaving a trail of disturbed foliage in its wake, as it propels itself forward with a burst of speed and grace. Upon landing, the panther crouches low, ready for its next spring, against the backdrop of a vast landscape, dotted with distant trees and illuminated by the silvery light of the full moon.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_1834
videos/HRA_part1/1834.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a futuristic spacesuit, leisurely walks through the pristine, metallic corridors of a bustling space station habitat, illuminated by soft, ambient lighting. He pauses to gaze intently at the vibrant Earth through a large observation window, perhaps seeking inspiration. Continuing his stroll, he passes various crew members engaged in their duties, highlighting the station's active community. The writer then stops at a console, where he interacts with advanced technology, possibly researching or gathering information for his work. Throughout the scene, the space station's interior is depicted in high detail, emphasizing its functional yet sophisticated design.]" }, { "from": "gpt", "value": "Normal. The crew in the background appears deformed and distorted." } ]
seed42_2736
videos/HRA_part0/2736.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit cave, a small brown bat, with leathery wings folded against its body, walks along the rocky ground with deliberate steps. Its face, framed by long, curved ears, is keenly observant. The bat pauses momentarily, revealing its tiny feet and claws as it navigates the stone surface. The focus then shifts to the bat's head, highlighting its intricate facial features and alert eyes. Finally, the bat is seen walking away, its silhouette set against the textured cave wall, creating a captivating scene of a bat navigating its environment on foot.]" }, { "from": "gpt", "value": "Bad. The bat's walking movements in the video are uncoordinated." } ]
seed42_2062
videos/HRA_part0/2062.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars majestically across a clear blue sky, its sharp eyes scanning the terrain below for any signs of movement. Its streamlined body, covered in a mottled brown and gray plumage, cuts through the air with effortless grace. The bird's hooked beak and powerful talons are on full display as it dives suddenly, plummeting towards the earth in pursuit of prey. In a burst of speed, it snatches a small rodent from the tall grass, its sharp claws closing around the struggling creature. The sparrowhawk then rises again into the heavens, carrying its prize back to its nest, a picture of strength and agility against the vastness of the sky.]" }, { "from": "gpt", "value": "Bad. The goshawk's movements in the video are not smooth." } ]
seed46_1471
videos/HRA_part2/1471.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm glow of sunrise, an antelope stands gracefully in the midst of a subtropical desert, its coat shimmering in hues of gold and brown, perfectly camouflaged against the sandy terrain. It is being gently caressed by the soft, early morning breeze, stirring the fine hairs on its body. The landscape is dotted with sparse vegetation and rocky outcrops, emphasizing the animal's resilience in this arid environment. The antelope's alert stance and curious gaze reflect its awareness of the surroundings, creating a serene yet dynamic scene in the vast, untouched wilderness.]" }, { "from": "gpt", "value": "Normal. The ears and horns of the antelope in the video are generated too high, and the ears suddenly become smaller and move lower during playback." } ]
seed42_2346
videos/HRA_part0/2346.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a plush koala toy, complete with realistic details and a charming face, comes to life against a green, leafy background reminiscent of eucalyptus. This adorable koala, clad in miniature jeans and a checkered shirt, begins to dance gracefully, its movements synchronized with an upbeat melody. Its paws sway side to side, and it gently bounces in place, capturing the essence of joy and playfulness. The dancing koala, set against the lush foliage, creates a delightful and enchanting moment, perfect for evoking smiles and happiness.]" }, { "from": "gpt", "value": "Normal. The koala's arms were slightly deformed while dancing." } ]
seed42_2670
videos/HRA_part0/2670.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, sits on a wooden crate under a bright blue sky, with scaffolding and building materials in the background. He gently pets a brown and white dog lying on its back, belly-up, on a pile of gravel, showing a tender moment of connection between the worker and the animal. The worker's hands, rough from labor, contrast with the softness of the dog's fur, creating a touching scene of companionship amidst a rugged worksite.]" }, { "from": "gpt", "value": "Bad. The worker's hand, the dog's head, and paws in the video have generation issues." } ]
seed46_1502
videos/HRA_part2/1502.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, subtropical woodland setting, a majestic tiger lies on the rich forest floor, its coat blending harmoniously with the dappled sunlight filtering through the dense foliage above. The camera captures the intimate moment as a gentle hand caresses the tiger's head, conveying an unexpected sense of trust and connection between the wild animal and the unseen human presence. The tiger's eyes are closed, its expression one of pure bliss, indicating a rare bond formed within the natural habitat of the subtropical woodlands.]" }, { "from": "gpt", "value": "Bad. The character's hands are distorted, the tiger's body is twisted, and the face is slightly distorted." } ]
seed42_1663
videos/HRA_part0/1663.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a yellow safety vest, kneels beside an urban street drain, diligently unclogging it with a specialized tool. His focused gaze and steady hands reveal his determination. In another scene, he stands with legs apart, continuing the task with a long, metal drain snake, his yellow fire department jacket and sturdy black boots standing out against the gray cityscape. His efforts are highlighted by the contrast between his vibrant attire and the dull surroundings, emphasizing his commitment to public service beyond firefighting. Throughout, the firefighter's steadfast posture and unwavering concentration underscore his dedication to maintaining community safety, even in mundane tasks.]" }, { "from": "gpt", "value": "Normal. The character's movements in the video are not smooth." } ]
seed42_1047
videos/HRA_part0/1047.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 seasoned farmer, wearing a white shirt, blue overalls, and a wide-brimmed hat, stands in a lush green field under a clear blue sky. He is in mid-throw, tossing hay bales with ease, his strong arms and focused expression showcasing his expertise. The hay bales are wrapped neatly in plastic, indicating a modern farming technique. The farmer's stance, with one leg forward for balance, adds dynamism to the scene, while the rolling hills and distant trees provide a picturesque rural backdrop.]" }, { "from": "gpt", "value": "Bad. The farmer's hand in the video disappears and reappears suddenly." } ]
seed46_2595
videos/HRA_part2/2595.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit living room filled with the warm glow of a fireplace, two young children sit closely together on a plush, brown couch. One child, a little boy with short, curly hair, wears a gray sweater and leans into his sister, who has straight, shoulder-length hair and dons a pink dress. They both hold hands comfortingly, displaying signs of illness, as they occasionally cough into their elbows, demonstrating proper hygiene etiquette. The room is decorated with a large, colorful rug and various soft toys scattered around, creating a familiar and homey atmosphere. The siblings' focus is on a book about dinosaurs, which lies open in front of them, indicating their attempt to distract themselves from feeling unwell.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous, there are sudden changes." } ]
seed46_1495
videos/HRA_part2/1495.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful buffalo, its body robust and muscular, leaps gracefully over a wooden fence in the midst of a lush, green prairie. The fence, made of weathered logs, stretches across the frame, adding texture and depth to the scene. The buffalo, its large horns curving outward, is captured mid-jump, showcasing its agility and strength. The background is filled with the vibrant hues of nature, from the deep greens of the grass to the soft blues of the sky, creating a stunning contrast against the dark brown of the buffalo. This majestic creature, defying expectations with its leap, embodies the spirit of the wild, free and untamed.]" }, { "from": "gpt", "value": "Normal. The water buffalo's jump in the video is uncoordinated." } ]
seed42_2973
videos/HRA_part0/2973.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet suburban neighborhood, two young boys stand side by side, wearing casual clothes; one in a gray t-shirt and denim shorts, the other in a red shirt and khaki shorts. They are positioned against a backdrop of a white-painted wooden fence, with lush green bushes visible beyond. The boy in gray has his left foot raised, while the other boy leans forward, both engaged in a playful interaction. Their stance and attire are typical of summertime leisure, capturing a candid moment of childhood camaraderie against a backdrop of a sunny day.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_3139
videos/HRA_part2/3139.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a blue shirt and apron, is seen in a well-lit kitchen, preparing an evening meal. The scene opens with a close-up of her face, framed by curly hair, as she smiles warmly while chopping vegetables on a wooden cutting board. She then proceeds to sauté the ingredients in a large pan on a gas stove, the flames casting a soft glow on her face. The camera captures her stirring the contents of the pan with a wooden spoon, her focus and passion for cooking evident in every movement. As the aroma of the sizzling food fills the room, she adds spices from a set of neatly arranged jars, her actions fluid and practiced, embodying the dual talents of writing and culinary artistry.]" }, { "from": "gpt", "value": "Normal. The woman's hand and the wooden spoon both deform when she is cooking." } ]
seed44_2328
videos/HRA_part1/2328.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly colored ibis, with its signature red curved bill and long legs, stands regally in a shallow body of water. Its plumage, a stunning mix of white, brown, and chestnut, catches the light beautifully. The bird's eye, sharp and observant, scans the surroundings for potential prey. The serene setting, featuring lush greenery and a calm water surface, enhances the serene atmosphere, making it a perfect habitat for this elegant creature.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1931
videos/HRA_part0/1931.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [On a sandy beach under clear blue skies, three young children, two boys and a girl, wearing colorful swimsuits and sunglasses, jump gleefully into the air in slow motion. Their silhouettes are highlighted by the sun, casting playful shadows on the sand. They leap again, this time with the vast ocean as their backdrop, their laughter echoing in the warm coastal breeze. Their final jump is captured mid-air, faces full of joy and wonder, the sea gently lapping at the shore behind them, encapsulating the essence of carefree childhood summers.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2096
videos/HRA_part0/2096.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green valley, two children, a boy and a girl, both wearing vibrant red raincoats and boots, playfully crawl on their hands and knees, exploring the rich foliage. Suddenly, they pause in awe as a majestic moose, adorned with a full rack of antlers, emerges from the mist, standing tall and still. The scene captures the magical moment when the children and the moose share a silent connection, surrounded by the beauty of nature. The children's wide-eyed wonder and the moose's calm presence create a captivating contrast, all set against the backdrop of the verdant valley.]" }, { "from": "gpt", "value": "Normal. The person's arm is twisted, the hand is distorted, the moose's face is distorted, and the legs are twisted." } ]
seed44_2883
videos/HRA_part1/2883.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant scene unfolds as a talented musician, clad in a red fox-themed costume, plays a golden saxophone under the neon lights of a bustling city street. The fox's expressive face, complete with whiskers and gleaming eyes, comes alive as it dances energetically, captivating the crowd with its infectious rhythm. Surrounded by urban graffiti and the glow of city lights, the fox's movements are fluid and dynamic, its tail swaying in time with the music. The atmosphere is electric, with onlookers swaying to the beat, all drawn into the enchanting performance of this unique fox-musician.]" }, { "from": "gpt", "value": "Normal. The musician wearing a fox costume in the video has a distorted face, twisted hands, and the object in their hands is also twisted." } ]
seed46_2004
videos/HRA_part2/2004.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male cashier, wearing a red apron with a name tag and a lanyard around his neck, is seen pulling a metal cart filled with various groceries, including a large water jug, milk, bread, and other items typically found in a supermarket. The cart is so full that it requires effort to pull, emphasizing the weight and volume of the goods. This scene takes place in a busy supermarket aisle, with shelves stocked with products and other customers shopping in the background.]" }, { "from": "gpt", "value": "Normal. The person's hand is distorted in the video." } ]
seed42_1652
videos/HRA_part0/1652.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A captivating scene unfolds where a talented violinist, dressed in a vibrant red cloak, plays a melodious tune while gracefully dancing on a vast, celestial stage illuminated by the ethereal glow of Saturn's rings in the distant cosmic horizon. In the foreground, a majestic white horse adorned with golden bridle and flowing mane leaps in perfect sync with the music, its hooves barely touching the stardust-covered stage, embodying a surreal fusion of artistry, nature, and the cosmos.]" }, { "from": "gpt", "value": "Bad. The faces and limbs of the characters in the video are distorted, as well as the face and legs of the white horse." } ]
seed42_2457
videos/HRA_part0/2457.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, smiling female musician, wearing a gray sweater, sits against a rustic wooden backdrop. She holds knitting needles and yarn in her hands, crafting a vibrant orange scarf. Her fingers, adorned with rings, skillfully manipulate the needles as she knits. Next, she wears a maroon beret and continues knitting, her eyes focused on her work. Then, she looks up from her knitting, her hazel eyes meeting the camera with a warm smile. Lastly, she proudly holds up the completed scarf, now a beautiful addition to her outfit, against the backdrop of wooden planks, showcasing her dual talents in music and knitting.]" }, { "from": "gpt", "value": "Normal. The action of the musician raising the scarf was not very smooth." } ]
seed46_1391
videos/HRA_part2/1391.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling a young Tom Hardy, wearing a futuristic space suit with a gorilla mascot emblem, embarks on an exhilarating lunar buggy ride across a desolate moon landscape, capturing the essence of adventure in outer space. Later, he is seen walking purposefully, leading the lunar buggy with ease, as if navigating through a challenging mission. The actor then pauses to admire the vast, starry expanse, evoking a sense of awe and wonder, before continuing his journey, showcasing determination and resilience. Throughout the scenes, the lunar buggy, with its distinctive design and rugged tires, remains a prominent feature, highlighting the vehicle's role in the astronaut's lunar exploration.]" }, { "from": "gpt", "value": "Normal. The character in the video walks unnaturally." } ]
seed44_1022
videos/HRA_part1/1022.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cheerful female nurse walks briskly down a hospital corridor, her blonde hair tied back in a neat bun. She wears a sky-blue uniform, gray tights, and white shoes. A stethoscope hangs around her neck, and she carries a clipboard in her right hand. The hallway is brightly lit, with a green floor and doors lining either side. The nurse's confident stride and professional attire convey a sense of purpose and dedication to her duties within the healthcare facility.]" }, { "from": "gpt", "value": "Good. The person in the video walks without any noticeable problems." } ]
seed44_2374
videos/HRA_part1/2374.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinctively attired in a crisp white shirt, black vest, and black trousers, diligently cleans the expansive windows of an upscale restaurant. Surrounded by lush greenery, he expertly maneuvers a squeegee across the glass, ensuring crystal-clear transparency. With focused determination, he tackles the task at hand, his movements methodical and efficient. The vibrant outdoor foliage contrasts sharply with the clean, modern lines of the building, highlighting the meticulous attention to detail in maintaining the restaurant's pristine appearance.]" }, { "from": "gpt", "value": "Bad. The actions are not continuous, there are sudden changes." } ]
seed44_2014
videos/HRA_part1/2014.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of a sea urchin reveals its intricate, symmetrical structure as it clings to a rocky surface underwater. Sunlight filters through the clear, blue water, casting a soft glow on the urchin's spines, which are a striking contrast to the dark rocks. The camera captures the water gently swaying the urchin, emphasizing its resilience in the marine environment. The scene is framed by the rocky crevices of the seabed, highlighting the creature's natural habitat, while the muted colors of the rocks and sand provide a serene backdrop for the brightly colored sea urchin.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_1503
videos/HRA_part2/1503.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate doctor, wearing a white lab coat, blue shirt, and khaki pants, gently caresses a small, brown squirrel nestled in her hands. The scene is set in a cozy, well-lit room with wooden floors, where the doctor, sporting a ponytail, glasses, and a warm smile, tenderly holds the squirrel. The focus is on the interaction between the caring medical professional and the tiny creature, emphasizing the nurturing bond formed in this peaceful environment.]" }, { "from": "gpt", "value": "Bad. The character's face is distorted, and the hands are twisted." } ]
seed44_1388
videos/HRA_part1/1388.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sunlit indoor environment, three young children sit on a large, comfortable sofa, each gently caressing a small rabbit. One child, dressed in a blue jacket, has short blond hair and a joyful smile, cradling a white rabbit with care. Another child, wearing a yellow shirt, has brown hair and a peaceful expression, softly petting a brown rabbit. The third child, clad in a red hoodie, has curly dark hair and a serene look, tenderly stroking a gray rabbit. The room is filled with a sense of calm and happiness, as the children enjoy the company of the adorable bunnies.]" }, { "from": "gpt", "value": "Normal. The character's face is slightly distorted, hands are twisted, arms are twisted, legs are twisted, the rabbit's body is twisted, and the head is twisted." } ]
seed44_2774
videos/HRA_part1/2774.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man with a bushy beard and wearing a brown jacket, blue jeans, and a black cap walks side by side with a coyote on a dirt path. They are set against a background of dense green forest and a sky filled with fluffy white clouds. The man, holding a wooden staff, and the coyote, with its distinctive bushy tail, navigate the wilderness together, their unlikely companionship highlighted by the peaceful, natural setting. Their journey unfolds on a trail marked by fallen leaves and tree roots, with the occasional glimpse of other wildlife in the surrounding woods.]" }, { "from": "gpt", "value": "Bad. The man's facial features in the video are generated blurry, hands and feet are deformed, the jackal's head and paws are abnormally generated, and the limbs of the jackal in the middle frames are twisted, deformed, or missing." } ]