video_id
stringlengths
8
11
video
stringlengths
22
25
conversations
listlengths
2
2
seed44_2884
videos/HRA_part1/2884.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a red flannel shirt, blue jeans, brown work boots, and a wide-brimmed straw hat, rakes a large pile of autumn leaves in the midst of a vast, open farmland. The scene is set during the golden hour, with the sun casting a warm glow across the landscape. The farmer pauses to wipe sweat from his brow, revealing a face lined with the wisdom of years spent working the land. He continues his task with a sense of purpose and pride, the leaves forming a vibrant mosaic of reds, oranges, and yellows around him. The video captures the essence of hard work and the beauty of seasonal change in the rural countryside.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_1632
videos/HRA_part0/1632.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with short brown hair, sits in a clean, organized office space filled with natural light. Dressed in a gray shirt, black vest, and jeans, he nods in agreement while conversing with someone off-camera. His demeanor is professional yet relaxed, and he gestures with his right hand during the discussion, emphasizing his points. The office environment is modern and minimalistic, featuring a wooden desk, a green plant, and a laptop, contributing to a focused and productive atmosphere.]" }, { "from": "gpt", "value": "Nomal. The movements are not smooth." } ]
seed42_3051
videos/HRA_part0/3051.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a white T-shirt and blue jeans, encounters a hare in the midst of vast farmlands, where the land stretches out under a wide, open sky. The scene then shifts to the student swimming in a serene, crystal-clear lake, surrounded by lush greenery, as the hare watches from the shore, curious and alert. The student's relaxed demeanor and the hare's attentive stance create a harmonious moment between nature and humanity, all set against the backdrop of expansive farmlands and a peaceful body of water.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed46_1999
videos/HRA_part2/1999.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Amid the bustling activity of a harbor filled with boats and people, two young boys perform a daring leap from a wooden dock into the shimmering water below, their joyful expressions and the spray of water capturing the thrill of their summer adventure. Dressed in casual shorts and t-shirts, they are silhouetted against the bright sky, their bodies mid-air in a moment frozen in time, encapsulating the essence of youthful freedom and the vibrant life of the harbor.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1082
videos/HRA_part0/1082.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal setting, a student, identifiable by their backpack and casual attire, is crawling through a crowded mall. This unusual behavior attracts the curious gaze of shoppers, who pause to watch. Unexpectedly, a hyena, also crawling and wearing a backpack, joins the student. Both crawl side by side, blending into the urban environment, creating a bizarre yet harmonious scene amidst the mall's vibrant storefronts and bustling pedestrian traffic.]" }, { "from": "gpt", "value": "Normal. Almost static." } ]
seed46_2606
videos/HRA_part2/2606.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, spotted jaguar leaps powerfully across a narrow stream in a lush, green rainforest, its muscles rippling beneath golden-brown fur, with water droplets splashing upwards. The big cat's intense gaze is fixed ahead, showcasing its agility and grace in motion against the vibrant jungle setting, complete with lush vegetation and the misty atmosphere of the rainforest environment.]" }, { "from": "gpt", "value": "Bad. The jaguar in the video has a twisted body, head, feet, and legs." } ]
seed44_1374
videos/HRA_part1/1374.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 softly lit room, two young siblings, a boy and a girl, are fast asleep in their cozy beds, surrounded by an assortment of toys. The boy, wearing a red superhero costume, lies sprawled across his bed, one arm hanging over the side, with a toy dinosaur resting on his chest. The girl, dressed in a pink nightgown adorned with stars, sleeps peacefully with her favorite teddy bear clutched tightly in her arms. A nightlight shaped like a moon casts a warm glow over the scene, highlighting the innocence and tranquility of childhood sleep.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_1659
videos/HRA_part0/1659.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and cap, walks through a bustling space casino, neon lights casting an otherworldly glow on the patrons. Among them, a meerkat stands upright, wearing a tiny tuxedo, its eyes wide with wonder as it navigates the futuristic gaming tables, slot machines, and alien creatures. The officer, maintaining a watchful eye, ensures order in this eclectic mix of species and activities, all set against the backdrop of a grand, space-themed casino.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2786
videos/HRA_part2/2786.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing a gray t-shirt and apron, stands in a small, dorm-like kitchen filled with natural light. They are preparing a meal, chopping vegetables on a cutting board placed on a countertop cluttered with cooking utensils and ingredients. The student, with a look of concentration, moves with practiced ease, flipping a pan on a stove top where steam rises from a pot. The atmosphere is casual and homely, with posters and notes adorning the walls, giving a glimpse into the student's daily life. Throughout, the student's enthusiasm for cooking is evident in their animated expressions and gestures, creating a vibrant and engaging scene.]" }, { "from": "gpt", "value": "Bad. The person's face, hands, and arms are distorted in the video." } ]
seed46_1870
videos/HRA_part2/1870.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor wearing a black t-shirt and dark jeans is seen running alongside a large, energetic yellow dog in an expansive park. The two are captured mid-stride, with the actor's focused gaze and the dog's joyful expression highlighting their shared activity. They run together in harmony, the actor's casual attire and the dog's bounding energy creating a dynamic and engaging scene against the lush greenery of the park.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_1006
videos/HRA_part0/1006.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a police officer, clad in a navy uniform with a badge, cap, and sunglasses, interacts with a large brown teddy bear outside a row of shops, which include a bakery, a bookstore, and a clothing store, each with colorful awnings and signs. The officer gently lifts the stuffed animal, which is nearly as big as him, into the air. Nearby, a group of children watch in awe, sitting cross-legged on the sidewalk, their faces alight with wonder and joy. The officer then crawls on his hands and knees next to the bear, playfully engaging with the delighted kids, creating a heartwarming moment of connection between law enforcement and the community, all against the backdrop of a bustling street lined with charming stores.]" }, { "from": "gpt", "value": "Bad. The character's hands are deformed." } ]
seed42_1700
videos/HRA_part0/1700.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a close-up view captures a stunning array of coral formations, teeming with life and color. Against a backdrop of clear blue water, the corals display a rich palette of oranges, pinks, purples, and greens. Delicate sea fans wave gently in the current, while intricate branching corals resemble undersea forests. Hard corals form complex structures, providing homes for countless marine creatures. Soft corals sway gracefully, their feathery polyps extending to catch passing nutrients. The scene is a testament to the beauty and biodiversity of coral reefs, a precious ecosystem thriving beneath the waves.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_1939
videos/HRA_part0/1939.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 smiling student, dressed in a green T-shirt and gray pants, joyfully jumps alongside a kangaroo in a lush, green field under a clear blue sky. The student, wearing brown shoes and a wristwatch, mimics the kangaroo's hopping motion, capturing a moment of playful interaction between human and nature. The kangaroo, with its distinctive features and powerful hind legs, bounds gracefully next to the enthusiastic student, both enjoying the freedom of movement against the serene backdrop of the outdoors.]" }, { "from": "gpt", "value": "Bad. The jumping actions of the student and the kangaroo in the video are not smooth and continuous, there are abrupt changes." } ]
seed46_1181
videos/HRA_part2/1181.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, showcasing its distinctive golden fur patterned with black rosettes, swims through a clear, sun-dappled body of water, its muscular body cutting through the liquid with surprising grace and strength. Its piercing eyes remain focused, and its ears are flattened against its head as it propels itself forward with powerful strokes, defying the typical terrestrial nature of its kind in this aquatic setting.]" }, { "from": "gpt", "value": "Normal. The leopard's swimming movements in the video are basically normal, but there is some lack of coordination." } ]
seed46_2539
videos/HRA_part2/2539.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, a young female cashier, dressed in a black apron over a white blouse, serves customers with a warm smile at an outdoor market stall. The background is filled with the vibrant energy of city life, complete with honking cars, pedestrians, and street vendors. Suddenly, the focus changes to a public pool where a group of diverse individuals, including a man in swimming trunks and a woman in a floral-print swimsuit, splash and play in the water. The atmosphere is lively and joyful, with the sounds of laughter and splashing filling the air, offering a stark contrast to the busy urban environment previously depicted.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_1234
videos/HRA_part1/1234.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic individual named Jay, donning a stylish gray jacket, a black turtleneck, and dark jeans, stands against a backdrop of city lights and a bridge, exuding confidence. He is captured in various poses, first looking directly at the viewer with a serious expression, then showing a side profile with a contemplative look. Jay then smiles warmly, showcasing his friendly demeanor, before striking a cool pose with his hands in his pockets, gazing into the distance. Throughout, the urban landscape behind him complements his modern style and enigmatic persona.]" }, { "from": "gpt", "value": "Normal. The facial generation in the video has defects." } ]
seed42_287
videos/HRA_part0/287.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a classic white uniform and a colorful headscarf, is seen energetically cleaning windows in a brightly lit hospital room. She moves with purpose, using a squeegee to clear away streaks, while patients rest peacefully in beds adorned with vibrant floral sheets. Sunlight filters through the partially cleaned panes, casting a warm glow over the serene space. In the background, a bustling city skyline is visible, contrasting the calm atmosphere within the room. The nurse's dedication to her task is evident in her focused expression and the gleaming glass that reflects her hard work.]" }, { "from": "gpt", "value": "Normal. The nurse's window cleaning movements in the video are basically normal, but there is some lack of coordination." } ]
seed46_1997
videos/HRA_part2/1997.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a tan vest, dark pants, and brown gloves, interacts with a realistic monkey puppet, crawling on all fours across a lush green landscape. The detailed puppet, featuring lifelike fur and expressive eyes, follows the worker's movements closely. The worker, with a serious yet focused demeanor, guides the monkey puppet through various natural terrains, including dense foliage and rocky terrain, highlighting the puppet's agility and realism. Throughout the scene, the worker's connection with the monkey puppet conveys a sense of companionship and shared purpose in their outdoor adventure.]" }, { "from": "gpt", "value": "Bad. The puppet monkey shows abnormal mutations and deformations. The man's hand also appears deformed." } ]
seed42_232
videos/HRA_part0/232.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his curly hair, beard, and glasses, is seen shoveling snow in a backyard during daylight. He wears a dark jacket, gray pants, and brown boots, and is engaged in the mundane task with a sense of focus and determination. Snowflakes continue to fall gently from the cloudy sky, accumulating on the ground and surrounding trees. The artist's clothing, which includes a dark jacket, gray pants, and brown work boots, contrasts with the pristine white snow, highlighting the physicality of his task. Despite the cold weather, he remains dedicated to clearing the snow, his breath visible in the crisp air, while a small dog watches him from a distance, adding a touch of companionship to the scene.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_1067
videos/HRA_part2/1067.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman, wearing a vibrant red dress and black high heels, gracefully dances in the center of a bustling restaurant. The place is filled with the warm glow of hanging lights and lively chatter from the patrons seated at their tables. She moves with confidence and joy, her dress swirling around her as she twirls to the rhythm of the live band playing in the corner. The camera captures her expressive face, full of happiness, and the admiring glances of those around her who pause to watch her performance.]" }, { "from": "gpt", "value": "Bad. The character's body movements are not smooth and uncoordinated." } ]
seed42_1459
videos/HRA_part0/1459.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional lawyer, dressed in a dark suit, sits at a modern glass desk in a well-lit office. The room features wooden floors, large windows, and contemporary art on the walls. The attorney is writing on a legal pad with a sleek fountain pen, his brows furrowed in concentration. The desk is adorned with an array of legal documents and a nameplate, while a laptop rests open nearby. The scene conveys a sense of seriousness and attention to detail as the lawyer diligently works on his case.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_1969
videos/HRA_part2/1969.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow Labrador dog, wearing a red collar and tags, happily swims in a natural hot spring pool, surrounded by lush green vegetation and a wooden dock. The water, clear and inviting, gently laps at the dog's fur as it paddles with ease. The dog's joyful expression and the serene environment of the hot springs create a peaceful and picturesque scene, enhanced by the vibrant greenery and the warm, bubbling water.]" }, { "from": "gpt", "value": "Normal. The dog's collar and mouth generation in the video have issues." } ]
seed46_2345
videos/HRA_part2/2345.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a doctor, clad in a crisp white lab coat, stands in a vibrant jungle setting, complete with lush green foliage and exotic flowers. Accompanied by a dingo, the duo begins to dance gracefully, the doctor's stethoscope swinging rhythmically as they move. The dingo, surprisingly elegant, prances alongside, its fur glistening under the golden sunlight filtering through the canopy above. The two continue their dance, the doctor's glasses catching the light and the dingo's tail swishing in time, creating a surreal and joyful spectacle in the heart of the jungle.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_2956
videos/HRA_part2/2956.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, clad in a white tank top, denim overalls, and brown work boots, stands in a modest kitchen with white cabinets and a checkered floor. He reaches into a modern, stainless steel dishwasher, his hands strong and calloused from farm labor. Carefully, he extracts a large, white plate, placing it onto a wooden drying rack set on the counter, where other plates and utensils already rest. The scene is intimate, highlighting the unexpected domestic task of unloading the dishwasher performed by this typically outdoorsy figure.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_2278
videos/HRA_part0/2278.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant musician, donning a yellow shirt, catches a flying drumstick during an energetic performance under the spotlight. The scene transitions to show the artist passionately singing into the microphone, the crowd's glow sticks illuminating the dark venue. Next, the musician is seen catching a guitar pick from another band member, their connection highlighted by the stage lights. Finally, the artist reaches out to catch a flower thrown from the audience, a gesture symbolizing the bond between performer and fans, all set against a backdrop of colorful stage lighting.]" }, { "from": "gpt", "value": "Normal. Missing the scene of the musician catching the guitar pick thrown by the band member, and the audience's glow sticks are not shown." } ]
seed46_2121
videos/HRA_part2/2121.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small hamster, characterized by its golden-brown fur and tiny ears, energetically jumps across wooden dock planks by a serene lake, surrounded by lush greenery. The hamster's miniature size contrasts with the vast, natural setting, creating a whimsical scene. Its movements are agile and lively, as it leaps from one dock plank to another, showcasing its playful spirit against the backdrop of a peaceful lakeside environment.]" }, { "from": "gpt", "value": "Bad. The hamster's limbs are missing in the video, and there are issues with the ears." } ]
seed46_2394
videos/HRA_part2/2394.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical, anthropomorphic setting, a weasel, dressed in a white doctor's coat over a blue shirt and tie, crawls on its belly across a cluttered desk filled with medical books and instruments, its eyes intently focused on a miniature stethoscope just out of reach. The desk is awash in a warm, golden light, casting long shadows and highlighting the weasel's determination. Behind the desk, a large window frames a bustling city skyline at sunset, adding a sense of urgency and drama to the scene.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed42_1457
videos/HRA_part0/1457.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical setting, a panda bear, donning a red apron and a name tag, stands behind a cash register in a grocery store decorated with red lanterns and Chinese New Year banners. The panda, with its distinctive black and white fur, is seen wiping the countertop meticulously, using a green cloth, while customers wait patiently in line. The scene captures the unique combination of a panda working as a cashier, diligently cleaning the service area, all within a vibrant and culturally-themed supermarket environment.]" }, { "from": "gpt", "value": "Normal. The panda's fingers in the video are not fully generated, and there are issues with the arms and eyes." } ]
seed42_1386
videos/HRA_part0/1386.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a black jacket, white shirt, and khaki pants, finds himself in an unexpected scenario where he is energetically dancing in a meadow. Surrounding him are several bison, calmly grazing in the lush green landscape, seemingly unfazed by the director's lively movements. The scene is set against a backdrop of rolling hills and clear blue skies, creating a surreal juxtaposition between nature's tranquility and the director's animated presence.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed46_1941
videos/HRA_part2/1941.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy white dog with a pink collar and a polka-dot harness walks down a suburban sidewalk, its ears perked and tail wagging. It pauses to sniff a green fire hydrant, then continues its leisurely stroll. The dog then trots across a quiet street, passing by a row of neatly trimmed hedges and a red mailbox. Finally, it stops to rest under the shade of a large tree, the sunlight filtering through the leaves and casting dappled shadows on the dog's fur.]" }, { "from": "gpt", "value": "Bad. The head and paws of the white fluffy dog in the video have generation issues." } ]
seed44_1909
videos/HRA_part1/1909.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a suit, tie, and leather briefcase, walks through lush wetlands filled with tall grasses and cattails, accompanied by a koala casually perched on their shoulder. The lawyer, with a determined look, strides forward on a narrow wooden boardwalk that winds through the wetland habitat. The koala, seemingly unfazed by its unusual companion, clings comfortably to the lawyer's shoulder, occasionally glancing around at the surrounding environment. The pair moves purposefully through the scenic wetlands, with the lawyer's polished shoes and professional attire contrasting sharply with the natural surroundings.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_2343
videos/HRA_part1/2343.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit prairie dotted with green shrubs and patches of tall grass, a large bison is rolling on its back in the dirt, surrounded by a cloud of dust. The bison, with its shaggy, brown fur and majestic horns, is enjoying a dust bath, rubbing vigorously against the ground. The camera captures the bison's content face as it lies on its side, legs kicking playfully in the air, creating a plume of dust that envelops its body. This behavior, known as 'dusting,' helps the bison remove parasites and excess oil from its coat, showcasing the creature's natural habits in a captivating scene.]" }, { "from": "gpt", "value": "Normal. The bison's movements in the video are basically normal, with slight coordination issues." } ]
seed46_1652
videos/HRA_part2/1652.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 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": "Good. Basically no problem." } ]
seed44_1233
videos/HRA_part1/1233.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin, distinguished by its black and white plumage, waddles comically on a snowy shore, pausing to preen its feathers with its sharp beak. Against a backdrop of icy mountains and a serene, cloud-dotted sky, it stands upright, displaying its characteristic tuxedo-like appearance. The bird then takes a leap into the frigid waters, where it swims gracefully, propelled by its flippers, before re-emerging onto the ice, shaking off droplets, and continuing its journey across the frosty landscape under the soft glow of the Antarctic sun.]" }, { "from": "gpt", "value": "Normal. The penguin's movements are not smooth." } ]
seed42_2850
videos/HRA_part0/2850.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a blue scrubs top and black pants, stands in a verdant garden filled with lush greenery and colorful flowers. She is engaged in digging a hole with a small spade, her face expressing determination and focus. The sunlight filters through the leaves above, casting dappled shadows on the rich soil beneath her feet. Despite her work, her demeanor conveys a sense of peace and purpose, as if tending to the earth is just another form of care she provides.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_2778
videos/HRA_part1/2778.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform with a badge and a hat, walks alongside a large, majestic rhinoceros. Both traverse a rugged terrain under a bright, sunny sky, creating an unusual yet compelling juxtaposition of authority and wildlife. The officer, equipped with a walkie-talkie on his belt, maintains a calm demeanor, while the rhinoceros, sporting a single horn and thick, wrinkled skin, ambles beside him. The scene unfolds in a spacious, natural environment, far from the urban settings typically associated with law enforcement.]" }, { "from": "gpt", "value": "Bad. The head of the rhino and the hand of the police officer in the video were generated abnormally." } ]
seed44_1411
videos/HRA_part1/1411.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal scene set in a vast, starlit cosmos, a renowned actor, dressed in a flowing white robe, participates in an otherworldly religious ceremony. The celestial setting features an enormous, ethereal bear standing on its hind legs, appearing majestic against the backdrop of distant galaxies. The actor, with a determined look, is seen running alongside the cosmic bear, both moving in unison within the sacred space ritual, their journey illuminated by the glow of nebulae and stars.]" }, { "from": "gpt", "value": "Bad. The video does not show the actor running alongside the cosmic bear to participate in the sacred space ritual." } ]
seed42_1584
videos/HRA_part0/1584.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, blue jeans, and a gray shirt, dances with uninhibited joy in the vastness of a desert canyon. The landscape features towering red rock formations, lush greenery, and a distant mountain range under a clear blue sky. The janitor, holding a broom as if it were a dance partner, spins and twirls with abandon, embodying a spirit of freedom and happiness amidst the stark beauty of nature. As the camera pans out, the scale of the canyons becomes apparent, contrasting the figure of the dancing janitor against the immense natural surroundings.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_1580
videos/HRA_part0/1580.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a yellow safety vest over a gray shirt, blue jeans, and brown shoes, climbs a tall, metal, industrial ladder in a large warehouse filled with boxes and equipment. He holds a tool in his right hand and reaches up with his left, the afternoon sun shining through the high windows, casting a warm glow over the dusty space. The ladder leans against a tall shelf stacked with supplies, and the man's focus is intense as he ascends, his brows furrowed in determination. Behind him, the vastness of the warehouse stretches out, with rows of shelves disappearing into the distance, emphasizing the scale of his task.]" }, { "from": "gpt", "value": "Bad. The movements are unsmooth." } ]
seed44_2644
videos/HRA_part1/2644.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with short, brown hair and a trimmed beard sits in a dimly lit room, wearing a casual gray t-shirt and black hoodie. He looks concerned as he holds his glasses in his right hand, resting on his knee. Suddenly, he coughs into his left hand, covering his mouth, with a worried expression on his face. The scene is set in an intimate space, capturing the man's discomfort and vulnerability during his unexpected coughing fit.]" }, { "from": "gpt", "value": "Bad. The man in the video has uncoordinated coughing movements." } ]
seed42_1222
videos/HRA_part0/1222.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone kangaroo is seen in a vast, arid landscape under a clear blue sky, performing a unique behavior - wiping its face with its paw in a human-like manner. The kangaroo, with its reddish-brown fur, stands on its hind legs, balancing its weight on its thick, muscular tail. As it wipes its face, the action is captured in slow motion, highlighting the texture of its fur and the intensity in its eyes. The gesture is repeated several times, each movement deliberate and almost meditative, offering a rare glimpse into the animal's world. The scene is set against the backdrop of the Australian outback, with distant mountains and sparse vegetation, emphasizing the kangaroo's natural habitat.]" }, { "from": "gpt", "value": "Bad. The kangaroo's front legs are severely deformed." } ]
seed42_1097
videos/HRA_part0/1097.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic great horned owl perches regally on a rugged branch, its piercing yellow eyes gazing intently into the distance. It's nestled among lush greenery, with sunlight filtering through the leaves, casting a warm glow on the owl's mottled brown and grey feathers. The owl's large, expressive eyes stand out against its feathered face, framed by tufts resembling horns. Its beak, curved and sharp, complements the fierce yet serene demeanor of this nocturnal hunter, set against a backdrop of dense forest vegetation.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2223
videos/HRA_part2/2223.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an unexpected scene, a mongoose, typically found in natural habitats, explores an industrial zone with caution, navigating through rusty pipes and concrete structures. Suddenly, it encounters a small pool of water, possibly from a recent rain, and surprisingly dips its paw in, showing curiosity about the liquid in this unusual environment. The mongoose then proceeds to swim gracefully, defying expectations of its usual terrestrial behavior, amidst the backdrop of industrial decay and urban grit. This juxtaposition highlights the animal's adaptability and resilience in an unorthodox setting.]" }, { "from": "gpt", "value": "Bad. The pangolin's legs show signs of deformity." } ]
seed46_1536
videos/HRA_part2/1536.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, clad in a blue medical scrub top and black pants, stands in a dramatic pose against a vivid, cloudy sky, with a buffalo charging in the background, creating a striking contrast. Moments later, she is shown running swiftly across a grassy field, the buffalo now galloping alongside her in the distance, both set against a backdrop of lush greenery and distant mountains. The nurse's attire remains consistent throughout, consisting of the blue scrub top, black pants, and white sneakers, while the buffalo's powerful form and the natural landscape provide a dynamic setting for this unique scene.]" }, { "from": "gpt", "value": "Bad. The nurse's running in the video is very unsmooth, and the movements are uncoordinated." } ]
seed42_185
videos/HRA_part0/185.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, clad in a casual black jacket and gray trousers, runs energetically across a large, open room within a space-themed educational facility. The room is adorned with detailed models of the Apollo spacecraft and other historical rockets, highlighting the center's focus on space exploration. As he moves, the director passes by a group of attentive students seated at tables, each engaged with interactive exhibits about space missions. The vibrant atmosphere reflects the excitement and educational value of the space center, emphasizing its commitment to inspiring the next generation of astronauts and scientists.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_1765
videos/HRA_part2/1765.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform and sporting sunglasses, stands with his arms crossed, observing the scene at a busy dock. Suddenly, a majestic deer emerges from the background, filled with lush greenery, and leaps gracefully over a small obstacle, drawing the attention of the officer and dock workers alike. The officer watches intently as the deer bounds across the wooden planks, its movements fluid and effortless, before disappearing into the foliage beyond the docks. Throughout the scene, the officer remains poised and watchful, his presence a testament to the unexpected encounters that can occur even in the midst of urban landscapes.]" }, { "from": "gpt", "value": "Bad. The deer's legs show deformities." } ]
seed42_2302
videos/HRA_part0/2302.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, clad in a brown leather jacket and blue jeans, traverses a desolate, rocky terrain reminiscent of Mars, accompanied by a robotic jackal. The landscape is barren and reddish, with distant mountains and a dim, orange-tinged sky. The writer, equipped with a backpack and walking stick, navigates the rough path, while the robotic companion, featuring sleek silver plating and glowing blue eyes, follows closely. The pair embarks on an adventure, exploring the rugged environment, with the writer occasionally stopping to jot down notes and the robot scanning the surroundings with its advanced sensors.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed44_1318
videos/HRA_part1/1318.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting illuminated by neon lights, a police officer, clad in a silver metallic uniform with a red sash, stands solemnly. Beside him, a robotic dog with glowing blue eyes sits attentively. The officer holds a ceremonial staff, participating in a galactic religious ceremony on a vast, holographic dance floor. Alien beings of various species gather around, some in traditional garb, others in futuristic attire, all engaged in a synchronized dance that combines elements of ancient rituals with modern electronic beats. The dance is a ritual to honor the cosmic connection between law enforcement, technology, and spirituality in this interstellar society.]" }, { "from": "gpt", "value": "Bad. The dance moves of the aliens in the video are not coordinated." } ]
seed46_2922
videos/HRA_part2/2922.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sea urchin reveals its intricate, spiny exterior, showcasing a variety of colors including green, purple, and brown. The spherical creature sits atop a rocky reef, surrounded by a vibrant marine environment teeming with life. Sunlight filters through the water, casting a warm glow on the sea urchin's textured surface, highlighting its natural beauty and resilience in the underwater world. Against the backdrop of the reef, the sea urchin appears both delicate and formidable, a testament to the diversity of oceanic fauna.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_2999
videos/HRA_part2/2999.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large grouper fish, with its distinct brown and white spotted pattern, swims serenely in a clear blue underwater environment. Its wide, flat head and protruding eyes are prominently featured as it navigates the aquatic space. Surrounding coral formations and gentle water currents add to the natural ambiance of the scene, providing a vivid portrayal of the grouper's habitat. The fish's powerful tail fin propels it effortlessly through the water, while smaller fish scatter in its presence, highlighting the grouper's dominant position in the marine ecosystem.]" }, { "from": "gpt", "value": "Normal. No smaller fish were generated." } ]
seed42_1390
videos/HRA_part0/1390.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cormorant, sleek and black, emerges from the water, its dripping feathers glistening in the sunlight. Perched on a low branch near the water's edge, it spreads its broad wings to dry, revealing a flash of orange throat beneath its hooked beak. The bird's intense eyes, set in a striking face, lock onto the camera, displaying its natural curiosity. Against a backdrop of rippling water and lush green foliage, the cormorant stands tall, a testament to its aquatic lifestyle, before diving back into the depths with a powerful flap of its wings.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed46_2929
videos/HRA_part2/2929.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a brown jacket over a striped shirt and khaki pants, performs a surprising leap over a row of yellow school lockers, demonstrating unexpected athleticism. In the next scene, he jumps again, this time over a green garbage can, showcasing his lively spirit. Then, he leaps over a red fire extinguisher mounted on a wall, his movements fluid and agile. Finally, the janitor, still clad in his brown jacket and khakis, clears a hurdle formed by a mop and bucket, his face expressing pure delight in these spontaneous acts of physicality, all within the confines of a school corridor.]" }, { "from": "gpt", "value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands." } ]
seed44_2880
videos/HRA_part1/2880.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 woman, dressed in a flowing white dress, interacts with a majestic lion in a surreal setting, emphasizing their connection. She crawls on a surface covered with lush green grass, facing the lion with a relaxed demeanor. The lion, also crawling, responds to her with curiosity, its golden eyes locked onto hers. Both the woman and the lion are framed by the vibrant greenery of their surroundings, highlighting the unusual yet peaceful encounter between human and beast.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed44_1963
videos/HRA_part1/1963.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, impeccably dressed in a black suit, white shirt, and black tie, stands against a blurred restaurant background. He holds a cocktail shaker in both hands, vigorously shaking it to mix a drink. His eyes are focused on the task, and beads of condensation form on the metal shaker. The action takes place in a dimly lit, upscale bar setting, with the shaker's metallic surface reflecting the ambient light. Throughout the scene, the waiter maintains his professional demeanor, his crisp attire contrasting with the dynamic motion of his hands as he expertly prepares a beverage.]" }, { "from": "gpt", "value": "Normal. The server in the video has uncoordinated movements." } ]
seed42_1107
videos/HRA_part0/1107.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal, dreamlike scene, a sleek, golden leopard with piercing green eyes gently caresses a miniature Mars rover replica with its paw, set against a cosmic, starry backdrop. The rover, adorned with intricate details mimicking real-life space exploration vehicles, sits motionless under the tender touch of the majestic feline. This juxtaposition of elements from different worlds - the wild, untamed beauty of the leopard and the marvels of human engineering represented by the rover - creates a captivating, otherworldly narrative.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_2467
videos/HRA_part0/2467.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret with a tan and black fur pattern leaps from a wooden platform in a spacious room, showing its agility and playfulness. The room is filled with natural light, highlighting the ferret's mid-air jump with a backdrop of a large window and potted plants. The ferret lands gracefully on another platform, part of a series of interconnected wooden structures designed for climbing and exploration. It pauses for a moment, looking curious and alert, before making another sudden leap, showcasing its lively spirit and acrobatic abilities against the serene indoor setting.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_1117
videos/HRA_part0/1117.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor, its curious nature evident as it explores its surroundings. It wears a tiny red harness, adding a pop of color against its natural brown and white fur. The room is spacious, with a large window letting in ample sunlight, casting warm light on the ferret as it moves about. In the background, a potted plant and a comfortable couch can be seen, providing context to the indoor environment where the ferret is freely walking.]" }, { "from": "gpt", "value": "Normal. During the middle frames when the ferret was moving, its paws would suddenly disappear or reappear." } ]
seed42_2274
videos/HRA_part0/2274.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal, Mars-like landscape painted in shades of orange and red, a woman wearing a futuristic silver suit gently caresses a majestic bison, while a second bison stands nearby. Behind them, a man clad in a matching silver suit rides a robust, armored horse, creating a striking contrast against the barren, rocky terrain and the distant, hazy horizon. The woman's tender touch on the bison's fur and the man's confident posture on the horse convey a sense of harmony and adventure in this otherworldly setting.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_2304
videos/HRA_part0/2304.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 chef, identifiable by his white uniform and toque, finds himself in an unexpected scenario, sharing a swimming pool with a large, brown bear. The pool, surrounded by lush greenery, offers a surreal setting as the chef, showing no fear, calmly floats on an inflatable raft, while the bear swims nearby, seemingly enjoying the water. Both characters coexist peacefully in this unusual scene, the chef maintaining his composure and the bear displaying a gentle demeanor, all under the clear blue sky.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed44_2180
videos/HRA_part1/2180.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast school of silver sardines elegantly maneuvers through the clear blue ocean, their synchronized movements creating mesmerizing patterns as they navigate around a large, rocky coral reef structure. Sunlight filters through the water, illuminating the fish and highlighting their metallic scales against the vibrant coral and lush underwater flora. The sardines' fluid dynamics and the contrast between their silvery bodies and the colorful marine environment create a stunning visual display in the depths of the sea.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_2310
videos/HRA_part2/2310.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, possibly a writer, wearing a brown jacket, blue shirt, and khaki pants, stands pensively on a rocky cliff overlooking a vast, stormy sea. He wipes his face with his right hand, perhaps reflecting a moment of emotional intensity or physical exertion, as he contemplates the dramatic landscape before him. The rugged terrain and turbulent waters provide a striking contrast to his thoughtful demeanor, emphasizing the solitude and grandeur of his surroundings.]" }, { "from": "gpt", "value": "Bad. The man in the video has uncoordinated movements." } ]
seed42_1506
videos/HRA_part0/1506.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent tiger, mid-leap, propels itself from a large rock into a lush, green forest, its body stretched out in a powerful arc. The tiger, with its distinctive orange coat patterned with black stripes, exhibits raw strength and grace as it jumps, surrounded by dense foliage and towering trees that provide a natural habitat. The action is captured in stunning detail, focusing on the tiger's muscular form, intense concentration, and the dynamic motion of its leap, encapsulating the essence of wild freedom.]" }, { "from": "gpt", "value": "Normal. The tiger's leap from the boulder to the forest in the video is not smooth and continuous." } ]
seed46_3025
videos/HRA_part2/3025.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray turtleneck, paints a large canvas featuring a moose in outer space, depicted in vibrant colors and abstract style. The scene shows the artist wiping paint from their hands while gazing thoughtfully at the artwork, which portrays the moose as a diplomat in a cosmic setting, surrounded by stars and planets. The artist's attire, including black pants and shoes, contrasts with the colorful painting, emphasizing the creative process and the unique concept of a moose on a space diplomatic mission.]" }, { "from": "gpt", "value": "Bad. The artist can be seen wiping the paint off their hands in the video, but the movements are very discontinuous and jerky." } ]
seed46_138
videos/HRA_part2/138.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant tropical dry forest, a talented female musician, dressed in a flowy yellow sundress, sits atop a fallen tree trunk, surrounded by lush greenery and vibrant wildflowers. She gently caresses her acoustic guitar, playing a soulful melody that resonates throughout the forest. Sunbeams filter through the canopy overhead, casting dappled light onto the forest floor, as birds chirp in the background, adding to the serene atmosphere. The musician's eyes are closed in concentration, her fingers gracefully moving across the strings, creating a harmonious symphony in the midst of nature's splendor.]" }, { "from": "gpt", "value": "Bad. Hands appear deformed, feet appear deformed." } ]
seed46_3067
videos/HRA_part2/3067.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white rabbit with black markings sits upright on a checkered cloth, using its right paw to wipe its face, as if cleaning or grooming itself, against a simple gray backdrop. The bunny pauses mid-wipe, its paw still touching its face, offering a candid glimpse of its self-care routine. This intimate moment is captured in high detail, highlighting the rabbit's endearing behavior and the textural contrast between its fur and the patterned fabric beneath it.]" }, { "from": "gpt", "value": "Bad. The generation of the white rabbit's paws in the video has issues." } ]
seed42_1005
videos/HRA_part0/1005.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a crisp white uniform and a colorful stethoscope, finds herself at the edge of a vast, shimmering ocean, where the sand meets the water. In her arms, she holds a small, fluffy rabbit, its ears perked up in curiosity. Together, they watch as a group of rabbits, similarly white and fluffy, leap and jump playfully across the sandy shore, the waves gently lapping at the background, creating a serene and whimsical scene.]" }, { "from": "gpt", "value": "Normal. The rabbit's jumping movements on the beach are not smooth and continuous." } ]
seed46_2024
videos/HRA_part2/2024.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled female student sits cross-legged on a clean, white surface, diligently hemming a pair of black pants with a focused expression. She wears a grey cardigan over a white collared shirt and blue jeans, her attire casual yet neat. The environment is bright and minimalistic, with ample natural light illuminating her task. Tools of her activity, such as scissors, thread, and a needle, are neatly arranged within reach, highlighting her attention to detail and organization. The scene captures her absorbed in the sewing process, her hands skillfully manipulating the fabric, demonstrating a blend of practical skill and academic studiousness.]" }, { "from": "gpt", "value": "Normal. The woman's movements in the video are basically normal, but there is some lack of coordination." } ]
seed46_1917
videos/HRA_part2/1917.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully cooked piece of salmon, expertly seared to achieve a perfect golden crust, sits center stage on a white ceramic plate. The salmon boasts a vibrant orange-pink interior, flaky yet moist, with a hint of dill sprinkled over it. Surrounding the fish are vibrant green asparagus spears, steamed to retain their crisp texture and natural color. Completing the dish is a drizzle of creamy sauce, likely a blend of lemon, butter, and capers, adding a touch of elegance and flavor. The plate is garnished with a sprig of parsley, enhancing the visual appeal of this exquisite salmon dish.]" }, { "from": "gpt", "value": "Bad. The video does not show butter and capers." } ]
seed46_1966
videos/HRA_part2/1966.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brightly lit, futuristic classroom filled with advanced technology, two young children, a boy and a girl, both wearing school uniforms, gently caress a small, friendly robot astronaut. The robot, designed with smooth, rounded edges for safety, features a smiling face on its metallic body, which is painted in shades of silver and blue. The room is decorated with educational posters and interactive screens, creating an engaging learning environment. The children, showing curiosity and affection, interact with the robot, which responds with gentle movements and playful sounds, fostering a connection between humans and artificial intelligence in a nurturing setting.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed46_2160
videos/HRA_part2/2160.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 park setting, two children engage in playful pushing, wearing vibrant, colorful clothing typical of a sunny day. One child, dressed in a yellow shirt and blue shorts, playfully pushes another child, who is wearing a red shirt and green shorts, against the backdrop of lush green grass and clear blue skies. The interaction is filled with laughter and joy, capturing the essence of innocent childhood fun. The children's faces are beaming with delight, their eyes sparkling with excitement, as they enjoy each other's company in the heart of nature's beauty.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed44_1071
videos/HRA_part1/1071.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark uniform with a badge and a radio, stands guard at a large, bustling sports stadium filled with cheering spectators, the sounds of excitement echoing throughout. Moments later, the focus is on the officer patrolling the perimeter of an Olympic-sized swimming pool, the water shimmering under the bright lights, capturing the intense competition of swimmers slicing through the water with powerful strokes. The officer's presence ensures safety and security, maintaining order amidst the thrilling aquatic events.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_3219
videos/HRA_part1/3219.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 hands appear deformed, and the face is somewhat blurry and distorted." } ]
seed44_1203
videos/HRA_part1/1203.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single kangaroo, identifiable by its reddish-brown fur, large muscular tail, and defined facial features, is seen jumping across a vast, arid landscape. The kangaroo bounds through the dry, sparsely vegetated terrain, its movements fluid and powerful. Its ears are alert, and its eyes are focused, conveying a sense of purpose and energy. The background is a vast, open space, punctuated by distant trees and a clear blue sky, emphasizing the kangaroo's natural habitat and the scale of its environment. The kangaroo's motion is captured in mid-air, showcasing the unique and iconic jumping ability that defines these marsupials.]" }, { "from": "gpt", "value": "Good. Basically no problem." } ]
seed42_216
videos/HRA_part0/216.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male lawyer, wearing a dark suit and a white shirt, attentively listens in a courtroom setting, his face expressing concern and focus. Seated at a wooden desk adorned with legal documents, he leans forward intently, his right hand resting on his chin in a gesture of deep consideration. The background features a traditional court setting with wood-paneled walls and a high ceiling, emphasizing the seriousness and formality of the legal proceedings. The judge and other participants are partially visible, adding context to the scene without detracting from the central figure of the engaged lawyer.]" }, { "from": "gpt", "value": "Normal. The person in the video does not move." } ]
seed44_110
videos/HRA_part1/110.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a gray beanie, black jacket, and khaki pants, meticulously organizes a cluttered garage. Surrounded by shelves filled with various items, including tools, bicycles, and storage bins, the writer methodically arranges the space. They handle each object with care, revealing a passion for order amidst creativity. As they work, the writer occasionally pauses to examine an item closely, perhaps reminiscing about its story, before placing it in its designated spot. The garage, bathed in warm, natural light filtering through the windows, transforms into a well-organized sanctuary, reflecting the writer's dual nature of imagination and practicality.]" }, { "from": "gpt", "value": "Bad. The movements are unsmooth." } ]
seed44_1967
videos/HRA_part1/1967.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 inventive scene unfolds where an engineer, clad in a gray jumpsuit and helmet, meticulously studies blueprints near a full-sized mechanical rhinoceros. Suddenly, the engineer leaps onto the rhino's back as it begins to jump, creating an unexpected yet thrilling spectacle. The mechanical rhinoceros, constructed with intricate metalwork and advanced engineering, bounds across the landscape, while the fearless engineer holds on, embodying a harmonious blend of human ingenuity and mechanical prowess.]" }, { "from": "gpt", "value": "Normal. Missing the scene of the engineer jumping onto the rhino." } ]
seed42_2089
videos/HRA_part0/2089.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative blend of scenes, two smiling children, a boy in a blue jacket and a girl in a pink jacket, walk alongside a life-sized zebra puppet, its distinctive black and white stripes vivid against a neutral background. The children hold hands, looking up in wonder, as the zebra puppet, operated by an unseen handler, walks alongside them. Behind them, a large, high-definition screen displays a captivating visualization of dark matter research, featuring swirling galaxies and complex data visualizations, seamlessly merging elements of nature, childhood innocence, and scientific exploration.]" }, { "from": "gpt", "value": "Bad. The faces and hands of the children and the head of the zebra puppet in the video have generation issues." } ]
seed42_2248
videos/HRA_part0/2248.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an urban park, a worker dressed in a green shirt and beige pants tends to the lush grass, unaware that a vibrant fox is watching from behind a tree. The fox, with its fiery red fur and piercing eyes, crouches low, ready to spring into action. Suddenly, it leaps into the air, jumping over a wooden bench in a graceful arc, capturing the essence of playfulness and freedom in the heart of the city. The worker, noticing the commotion, turns to see the fox mid-jump, a moment of surprise and delight shared between the two, set against a backdrop of tall buildings and green foliage.]" }, { "from": "gpt", "value": "Bad. The fox's legs appear deformed when jumping and running." } ]
seed42_2541
videos/HRA_part0/2541.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman, seemingly a teacher, sits at a sewing machine in a homey, cluttered room filled with natural light. She wears a simple white shirt and has short, neatly styled brown hair. The room is decorated with a large painting and a calendar on the wall, adding a personal touch. The teacher deftly operates the sewing machine, carefully hemming a pair of pants, demonstrating her skill and focus on the task at hand.]" }, { "from": "gpt", "value": "Normal. The woman's fingers in the video have generation issues, and her eyes are not open." } ]
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, 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." } ]
seed42_2309
videos/HRA_part0/2309.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, balding with glasses and a neatly trimmed beard, wearing a dark green collared shirt, focuses intently on fixing a leaky faucet in a public restroom. The faucet is positioned above a stainless steel sink with a mirror in the background. The janitor kneels on a yellow floor mat, using a wrench from his well-stocked tool belt to tighten the faucet's handle. The scene is illuminated by overhead fluorescent lights, casting a warm glow on the janitor's determined face as he works diligently to stop the dripping water.]" }, { "from": "gpt", "value": "Good. Basically no issues." } ]
seed44_2447
videos/HRA_part1/2447.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a gorilla wearing an astronaut suit stands before a massive spaceship, its textured surface reflecting the alien landscape. The gorilla looks up at the ship with curiosity and determination, ready to embark on a journey through interstellar space. Suddenly, the scene changes to show the gorilla swimming underwater, its powerful arms propelling it forward through crystal clear water, surrounded by colorful fish and vibrant coral reefs. The contrast between the futuristic space travel and the natural beauty of the underwater world highlights the versatility and adaptability of this extraordinary creature.]" }, { "from": "gpt", "value": "Good. No obvious issues." } ]
seed46_1221
videos/HRA_part2/1221.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a branch, its glossy black and white feathers shimmering under the sunlight, showcasing the bird's striking plumage against a lush green forest backdrop. The magpie turns its head, revealing its intelligent eyes and sharp beak, highlighting its curious nature. Moments later, it spreads its wings, displaying the full span of its black and white feathers, before taking flight, leaving behind a flurry of feathers and a sense of awe at its beauty and grace. Throughout the scene, the magpie remains the central focus, captivating the viewer with its natural elegance and charm.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed42_1056
videos/HRA_part0/1056.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature silverback gorilla sits in a lush, green environment, gently caressing a smaller gorilla with his large, expressive hands, showing tenderness and care. The silverback, with his powerful build and wise eyes, tenderly strokes the younger gorilla's back, creating a heartwarming scene of connection and affection within the primate family. This intimate moment is framed by the verdant foliage of their natural habitat, highlighting the emotional bond between these two creatures.]" }, { "from": "gpt", "value": "Normal. The fingers and ears of the gorilla in the video are missing." } ]
seed46_2734
videos/HRA_part2/2734.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic, silver-furred wolf stands on a platform at the base of a colossal space elevator, its massive structure stretching into the starlit sky. The wolf gently caresses the sleek, metallic surface of the elevator with its snout, as if acknowledging a familiar presence. Its piercing golden eyes reflect the surrounding ethereal lights, adding an otherworldly touch to the interaction between the creature and the futuristic architecture. The platform is surrounded by a vast, moonlit landscape, with distant mountains silhouetted against the night sky, creating a dramatic contrast to the looming space elevator.]" }, { "from": "gpt", "value": "Bad. The wolf's movements in the video are not smooth." } ]
seed46_1338
videos/HRA_part2/1338.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A diligent window cleaner, equipped with a squeegee and a bucket of soapy water, stands on a ladder propped against a tall, glass-paneled building. Dressed in a yellow high-visibility vest and dark pants, he methodically wipes the glass, leaving a streak-free shine. The bustling cityscape forms the backdrop, with pedestrians passing by and cars moving on the streets below. The sun casts a golden glow on the scene, highlighting the cleaner's hard work as he moves from pane to pane, ensuring crystal clarity for the occupants inside.]" }, { "from": "gpt", "value": "Bad. No ladder or pedestrians were generated." } ]
seed46_2676
videos/HRA_part2/2676.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dapper musician, clad in a black suit and red tie, strolls down a gravel path in the midst of a lush forest, accompanied by a friendly moose. The pair walk side by side, the musician holding his violin case, while the moose ambles along, its large antlers brushing against the tree branches. Sunlight filters through the dense canopy overhead, casting dappled shadows on the path as the duo continues their peaceful journey together.]" }, { "from": "gpt", "value": "Normal. The character's movements in the video are slightly unsmooth." } ]
seed44_1586
videos/HRA_part1/1586.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station habitat, illuminated by soft, ambient lighting, a caring teacher, wearing a navy blue jumpsuit with silver accents, gently caresses the head of a young student seated at a desk. The student, dressed in a matching uniform, looks up with wide eyes, feeling comfort and support. Behind them, a large window reveals the stunning view of Earth, while various educational tools and floating objects fill the zero-gravity environment, creating an immersive learning atmosphere. The teacher's compassionate touch and the unique setting emphasize the nurturing bond between educator and pupil in this extraordinary space classroom.]" }, { "from": "gpt", "value": "Normal. The teacher's actions of stroking the student's head in the video are basically normal, with only slight awkwardness." } ]
seed44_1626
videos/HRA_part1/1626.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic golden-brown lion leaps through the air against a vivid blue sky, its powerful muscles straining against the force of gravity. The lion, with piercing amber eyes and a thick mane, is suspended mid-jump, showcasing its agility and strength. Its leap is captured against a backdrop of lush green grass and scattered trees, highlighting the animal's natural habitat. The lion's claws are extended, ready to grip its prey, emphasizing the raw power and predatory nature of this iconic creature.]" }, { "from": "gpt", "value": "Normal. The lion's movements in the video are not smooth." } ]
seed46_198
videos/HRA_part2/198.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a classic white uniform with a red bandana around his neck, walks through a lush, green forest, his eyes fixed ahead with determination. Accompanied by a small, bushy-tailed squirrel perched on his shoulder, they navigate the woodland together. The chef carries a large basket, presumably filled with foraged ingredients, while the squirrel clutches an acorn in its paws, both on a mission in the vibrant, sun-dappled setting.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth." } ]
seed46_3212
videos/HRA_part2/3212.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 domestic chicken, speckled brown and white, is seen swimming in a clear mountain lake, surrounded by lush greenery and towering peaks. The bird paddles gracefully, its head held high, as it navigates the pristine waters. The landscape is breathtaking, with dense forests and majestic mountains framing the serene scene. The water shimmers under the sunlight, reflecting the vibrant scenery, while the chicken continues its unusual swim in the idyllic mountain setting.]" }, { "from": "gpt", "value": "Good. Basically correct." } ]
seed42_2965
videos/HRA_part0/2965.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a black turtleneck sweater and khaki pants, walks through a vast grassland with rolling hills under a clear blue sky. He pauses to observe a herd of deer grazing nearby, the animals' presence adding to the tranquility of the landscape. The writer continues his journey, a pen and notebook visible in his pocket, suggesting inspiration drawn from nature. As he moves further into the grassland, the distant silhouette of mountains can be seen, enhancing the sense of adventure and exploration. Throughout the scene, the focus remains on the writer's contemplative walk among the deer, with the vibrant green grass and expansive sky creating a serene and inspiring atmosphere.]" }, { "from": "gpt", "value": "Normal. The man's limbs are still somewhat uncoordinated while walking, and his hands and legs are deformed." } ]
seed44_2247
videos/HRA_part1/2247.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating scene, a janitor in a space museum is seen cleaning near a large, detailed model of the International Space Station, which is submerged in a serene indoor pool. Wearing a yellow vest, gray pants, and a white shirt, he carefully maneuvers around the underwater exhibit, highlighting his unique cleaning duties. The water around him is crystal clear, allowing viewers to appreciate the intricate details of the space station replica. As he works, the ambient lighting from above gently illuminates the water, creating a mesmerizing visual effect that blends the worlds of space exploration and aquatic tranquility.]" }, { "from": "gpt", "value": "Bad. The person's head, arms, and hands are distorted in the video." } ]
seed42_1247
videos/HRA_part0/1247.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear with a helmet, runs with focused determination across a dimly lit urban landscape, carrying a baseball bat. The scene is set at night, with the firefighter's outfit illuminated by the glow of city lights. His face is obscured by a breathing apparatus, adding to the sense of urgency and mystery. The baseball bat, an unexpected accessory, swings in his grip as he sprints with purpose, the background filled with the blurred shapes of buildings and streetlights, creating a dynamic and compelling image.]" }, { "from": "gpt", "value": "Normal. The baseball bat in hand deforms while running." } ]
seed42_2381
videos/HRA_part0/2381.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cormorant, distinguished by its sleek black body, yellow lower mandible, and piercing eyes, is captured mid-flight over a tranquil lake, showcasing its powerful wingspan against the serene waters below. It then perches on a branch, drying its wings, revealing its unique ability to spread its feathers. Next, the bird plunges into the water, its form streamlined as it hunts beneath the surface, demonstrating its aquatic prowess. Finally, it emerges victorious, a small fish clasped in its beak, highlighting its hunting skills in the wild. Throughout, the cormorant's natural habitat, from the calm lake to the surrounding foliage, is depicted in vivid detail.]" }, { "from": "gpt", "value": "Good. No obvious problems." } ]
seed44_2737
videos/HRA_part1/2737.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil, shallow pond surrounded by lush vegetation, a large moose with a wide, flat antler rack stands with its head submerged underwater. As it lifts its head, water droplets cascade down its face. The animal then proceeds to shake its head vigorously from side to side, flinging water off its fur and antlers. Its ears flap dynamically during the shaking motion, and its tongue can be seen hanging out playfully. Throughout the scene, the moose's eyes remain closed, indicating its enjoyment of the refreshing activity.]" }, { "from": "gpt", "value": "Normal. The moose's mouth and eyes generation in the video have problems." } ]
seed42_2915
videos/HRA_part0/2915.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah, embodying grace and power, rests on a dry, grassy savanna, its body curved in a relaxed position. It turns its head, using its paw to wipe its face, showcasing a natural, intimate grooming moment. The cheetah's distinctive black spots stand out against its tan fur, while its piercing eyes and pronounced facial features add depth to the scene. This close-up shot captures the animal's wild beauty and the serene environment surrounding it, with distant trees adding a sense of place to the composition.]" }, { "from": "gpt", "value": "Normal. The cheetah's head-turning movements are basically normal but there is some lack of coordination." } ]
seed44_3048
videos/HRA_part1/3048.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a traditional white uniform and cap, takes a break from her medical duties to paint a hospital room a soothing shade of light blue. Holding a paintbrush in her gloved hand, she carefully applies the paint to the wall, creating a fresh and welcoming environment for the patients. The room is brightly lit, with medical equipment neatly arranged on a side table, and a window letting in natural light, casting a warm glow on the freshly painted walls. The nurse's dedication to improving the space highlights her commitment to patient care beyond her regular responsibilities.]" }, { "from": "gpt", "value": "Bad. The woman's arm deforms while she is painting the wall. Her hands show signs of abnormal mutation. The brush in her hand also distorts." } ]
seed46_2059
videos/HRA_part2/2059.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor kneels in a lush green forest, attentively examining a small, injured deer lying on the mossy ground. The deer, with its distinctive brown coat and white underbelly, looks up at the doctor with trusting eyes. The scene is peaceful, with sunlight filtering through the trees, casting dappled shadows on the forest floor. The doctor, wearing a green field jacket and khaki pants, gently touches the deer's leg, showing care and concern. Nearby, other deer stand watch, their ears perked, observing the interaction from a safe distance.]" }, { "from": "gpt", "value": "Bad. The character's movements in the video are not smooth, and the deer's movements are also not smooth." } ]
seed46_1651
videos/HRA_part2/1651.mp4
[ { "from": "human", "value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a costume reminiscent of the 1920s, complete with a flapper dress and feather headband, dances gracefully amidst the lush greenery of a temperate rainforest. Sunlight filters through the dense canopy, casting dappled shadows on the forest floor. The actor performs a series of fluid movements, twirling and leaping with the elegance of a seasoned performer, while the vibrant flora and fauna of the rainforest provide a stunning natural backdrop. The atmosphere is one of enchantment and vitality, as the dancer's artistry harmonizes with the beauty of the ancient woodland.]" }, { "from": "gpt", "value": "Bad. The character in the video has a twisted body, face, arms, legs, and hands." } ]