video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_3184
|
videos/HRA_part2/3184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green savanna setting, a gentle giraffe is being affectionately caressed by a human, both standing under a vast, open sky. The giraffe, with its distinctive spotted coat and long neck, leans into the touch, expressing comfort and trust. The human, wearing a khaki safari outfit, reaches up to stroke the giraffe's face, creating a tender moment of interspecies connection. The scene is framed by the natural beauty of the savanna, with distant trees and a clear blue sky, emphasizing the harmony between the human and the majestic animal.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1037
|
videos/HRA_part2/1037.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, complete with a stethoscope around his neck, dons a brown jacket, dark trousers, and black boots as he shovels snow from a walkway. Snowflakes gently fall from a gray sky, settling on the green pine tree in the background. The doctor, wearing glasses and a wedding ring, pauses to wipe his brow, revealing his determination. He continues to clear the snow, demonstrating his commitment to his duties despite the weather. Throughout the scene, the doctor's attire remains unchanged, emphasizing his professional identity even in this domestic task.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2301
|
videos/HRA_part1/2301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful man with short brown hair and glasses, wearing a green striped shirt and apron, is baking a vanilla sponge cake in a home kitchen with white cabinets and countertops. He starts by pouring milk into a bowl containing flour, sugar, eggs, and butter, mixing the ingredients together with an electric mixer. The batter is then poured into a round cake pan and placed in a preheated oven. The camera captures the cake rising and turning golden brown. Once baked, the man removes the cake from the oven, lets it cool, and proceeds to frost it with whipped cream frosting using a spatula. The final shot shows the beautifully frosted cake on a white plate, ready to be served.]"
},
{
"from": "gpt",
"value": "Bad. No generation of a cheerful man with short brown hair and glasses wearing a green striped shirt and an apron; no generation of the process of mixing milk, flour, sugar, eggs, and butter in a bowl with an electric mixer; no generation of the cake rising and gradually turning golden yellow in the oven; no generation of the man taking the cake out of the oven."
}
] |
seed46_2414
|
videos/HRA_part2/2414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant orchard filled with apple trees heavy with ripe fruit, a large brown bear stands on its hind legs, its shaggy fur glistening in the dappled sunlight. It reaches up with a massive paw, gently swiping at the low-hanging branches laden with apples. The bear then lowers itself to all fours, picking up an apple it has dislodged, and wipes it carefully on its thick fur before taking a hearty bite, savoring the sweet, juicy flavor amidst the peaceful surroundings of the orchard.]"
},
{
"from": "gpt",
"value": "Normal. The brown bear's claws and mouth in the video have generation issues, and the eyes were not generated."
}
] |
seed44_3005
|
videos/HRA_part1/3005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a gray suit, red tie, and glasses, is kneeling in a whimsical scene beside a meerkat standing upright. The lawyer gently wipes the meerkat's face with a white cloth, both figures set against a vibrant green grassy background under a clear blue sky, creating an unusual yet captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's facial features are missing, fingers are deformed, and feet are problematic; the video does not realistically represent reality."
}
] |
seed42_1416
|
videos/HRA_part0/1416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a whole, raw cod fish, lying on a bed of ice, is showcased in stunning high-definition. The fish, with its distinctive greenish-grey skin and large, pearly eyes, is presented head-on, giving a clear view of its mouth and gills. The camera zooms in to reveal the intricate details of the cod's texture and scales, emphasizing its freshness. The background consists of a blurred array of seafood items, highlighting the cod as the central subject in a market or fishmonger's stall.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1886
|
videos/HRA_part2/1886.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, clad in rich brown fur, dashes across a lush, verdant forest floor, its bushy tail swaying energetically. The scene is captured in vibrant detail, with the beaver's small ears and alert eyes clearly visible as it navigates the underbrush. Its front paws, equipped with dexterous digits, grip the mossy ground, propelling it forward with a sense of urgency. The background features a dense thicket of trees and foliage, providing a natural habitat for the beaver's lively sprint.]"
},
{
"from": "gpt",
"value": "Bad. The beaver in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed46_2827
|
videos/HRA_part2/2827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, donning a white hazmat suit with a respirator mask, meticulously paints the walls of a spacious, well-lit room with vibrant orange strokes, capturing the essence of transformation. His attire, complete with protective goggles and gloves, underscores the precision and safety measures involved in the task. The room, initially a blank canvas, gradually comes alive with color, highlighting the engineer's skill and attention to detail as he revitalizes the space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1657
|
videos/HRA_part0/1657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious living room filled with natural light, a diligent woman wearing a yellow apron over a floral dress meticulously dusts an ornate wooden dresser, her movements methodical and thorough. Beside her, a man in a white shirt and brown trousers assists, carefully wiping down a matching side table. The room is elegantly decorated with antique furniture and Persian rugs, creating a warm and inviting atmosphere. On the walls, framed paintings and family photographs add personal touches to the space. The couple works in harmony, their actions demonstrating a shared commitment to maintaining their cherished home environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1330
|
videos/HRA_part1/1330.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, stands on a small green step stool. He is in the process of screwing in a light bulb into a fixture, which is attached to a pale yellow ceiling. The room is sparsely decorated, featuring a white table, a beige office chair, and a bookshelf filled with books and binders. The doctor, with short brown hair and glasses, focuses intently on the task at hand, his sleeves rolled up to his elbows. The scene is lit by other functional light fixtures in the room, casting a warm glow over the doctor and his makeshift ladder.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, and the face is deformed."
}
] |
seed46_1226
|
videos/HRA_part2/1226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a yellow high-visibility vest and gray trousers, crawls through a narrow tunnel within a vast, rocky quarry, his flashlight illuminating the rugged terrain. The dusty environment envelops him as he moves with determination, surrounded by towering walls of stone, showcasing the lesser-seen aspects of maintenance work in an expansive quarry setting.]"
},
{
"from": "gpt",
"value": "Normal. No flashlight was generated."
}
] |
seed46_1657
|
videos/HRA_part2/1657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious living room filled with natural light, a diligent woman wearing a yellow apron over a floral dress meticulously dusts an ornate wooden dresser, her movements methodical and thorough. Beside her, a man in a white shirt and brown trousers assists, carefully wiping down a matching side table. The room is elegantly decorated with antique furniture and Persian rugs, creating a warm and inviting atmosphere. On the walls, framed paintings and family photographs add personal touches to the space. The couple works in harmony, their actions demonstrating a shared commitment to maintaining their cherished home environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2102
|
videos/HRA_part0/2102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural village setting, two young boys wearing white shirts and blue shorts are seen wiping down a water buffalo with traditional woven baskets. The buffalo, with its distinctive curved horns, stands calmly under a thatched-roof shelter with wooden pillars. The boys work diligently, one focused on the buffalo's head and the other on its body, using the baskets as makeshift sponges. The scene is set against a backdrop of lush green vegetation and simple, rustic structures, capturing the essence of daily life in a rural community where buffalo play a significant role.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, and legs are distorted in the video, as well as the water buffalo's head and legs."
}
] |
seed44_1904
|
videos/HRA_part1/1904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed man in a white shirt and dark pants walks through a lush, green meadow dotted with vibrant wildflowers under a bright, clear blue sky. He strides purposefully, his hands clasped behind his back, exuding a sense of peace and connection with nature. The tall grass sways gently in the breeze around him, and in the distance, a range of rolling hills provides a picturesque backdrop, enhancing the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video has missing limbs and facial generation issues."
}
] |
seed46_2142
|
videos/HRA_part2/2142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, wearing a gray shirt and glasses, sits in a chair in a living room setting, gently caressing a small, fluffy white cat. The room is filled with natural light from a window behind him, illuminating the intimate interaction. The cat, appearing relaxed and content, lies on its back on the man's lap as he strokes its belly. The scene conveys a sense of warmth and affection between the man and the cat, with the soft focus on their faces capturing the tender moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2072
|
videos/HRA_part2/2072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, with short brown hair and a neatly trimmed beard, stands in a modern kitchen with white cabinets and countertops. He is wearing a casual outfit consisting of a gray t-shirt and dark blue jeans. The kitchen is well-lit, and natural light filters in from a nearby window. The man is focused on making coffee, pouring water into a sleek, stainless steel coffee maker. He then measures coffee grounds carefully, ensuring the perfect cup. As the coffee brews, steam rises gently, and the aroma fills the room, creating a warm and inviting atmosphere. The man waits patiently, his expression one of anticipation, as the coffee completes its cycle, ready to be enjoyed.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2175
|
videos/HRA_part1/2175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, golden hamster in swimwear, including water goggles and a miniature life jacket, floats on a raft in a clear, gently flowing river surrounded by lush greenery. It paddles with its tiny paws, navigating through the serene waters with determination. The hamster then jumps into the river, swimming energetically, its little body moving gracefully through the water. Finally, it rests on a rock near the riverbank, basking in the sunlight, wearing a happy expression, all set against the peaceful backdrop of a forest and a calm river.]"
},
{
"from": "gpt",
"value": "Bad. The dwarf hamster in the video has a distorted face."
}
] |
seed46_320
|
videos/HRA_part2/320.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a sleek gray suit, stands in a spacious room with large windows overlooking a space station's agricultural area, filled with vibrant green plants under artificial lights. He begins to dance gracefully, his movements a stark contrast to his professional attire, as he moves across the room with the space agriculture serving as a backdrop, highlighting the unique juxtaposition of law, agriculture, and dance in zero gravity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1199
|
videos/HRA_part2/1199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a brown wide-brimmed hat, green shirt, and khaki pants, tends to a lush garden, surrounded by vibrant flowers and verdant plants. She kneels on a green kneeling pad, carefully planting a sapling into the rich soil. Next, she waters the plants with a silver watering can, her actions gentle and nurturing. Then, she pauses to admire her work, a trowel in her hand, a satisfied smile on her face, with the garden in full bloom behind her. Lastly, she sits on a wooden bench, pen in hand, notebook open, capturing her thoughts inspired by the beauty of nature, the garden's colors and textures providing a stunning backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1766
|
videos/HRA_part0/1766.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a gray turtleneck sweater and brown corduroy pants, sits at a wooden desk in a rustic cabin, surrounded by nature. Suddenly, the scene changes to reveal a graceful gazelle leaping over a wooden fence in slow motion, its muscles straining against the force of the jump. The gazelle lands softly on the ground and continues to run, its movements fluid and effortless. The writer, inspired by the sight, begins to type furiously on a vintage typewriter, capturing the essence of the gazelle's leap in a beautifully written passage. The camera zooms in on the writer's face, showing the intense concentration and inspiration on their face as they bring the scene to life through their words. Throughout the video, the focus remains on the gazelle's powerful leap and the writer's artistic interpretation of it, with no additional distractions or scene transitions.]"
},
{
"from": "gpt",
"value": "Normal. The writer's hand in the video has issues."
}
] |
seed42_1661
|
videos/HRA_part0/1661.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh Atlantic cod fish, with clear eyes and shiny skin, rests on a bed of ice. Its mouth is slightly open, and it has a small silver ring through its lip. The fish is surrounded by green herbs and lemon slices, adding a pop of color against the icy background. The camera captures the cod from various angles, highlighting its texture and freshness, perfect for culinary preparations. Throughout the video, the fish remains stationary on the ice, the camera's movement providing dynamic visuals.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2495
|
videos/HRA_part2/2495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear including a yellow reflective jacket, black pants, and boots, meticulously irons his uniform in a room with a white wall and a table covered with a white cloth. The room is sparsely decorated, featuring a calendar and a portrait on the wall. The firefighter, sporting a well-groomed beard and a focused expression, demonstrates his attention to detail by carefully smoothing out the wrinkles in his uniform. The camera captures the steam from the iron as it glides over the fabric, highlighting the contrast between the firefighter's rugged appearance and the domestic task at hand.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_115
|
videos/HRA_part0/115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, with short, neatly styled brown hair and a neatly trimmed beard, sits at a wooden table under the glow of a vintage-style light bulb. He is sewing a button onto a garment with focused determination, his eyes intently fixed on the task. Dressed casually in a gray shirt, he works diligently, demonstrating unexpected domestic skills. The close-up shot captures his serious expression and the intricate details of his sewing technique, creating an intriguing contrast between his profession and this ordinary activity.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_2083
|
videos/HRA_part1/2083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter with neatly combed brown hair and a black uniform serves a couple seated at a beachside table, the ocean's horizon providing a romantic backdrop. He carefully places two plates of food on the table, his hands displaying a gentle, caressing motion, as if cherishing the art of serving. The couple looks on appreciatively, the man wearing a gray T-shirt and glasses, the woman adorned in a black dress with a plunging neckline. The scene is set during the golden hour, with the sun's rays casting a warm glow over the ocean and the couple, encapsulating a moment of intimate dining by the sea.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand appears deformed."
}
] |
seed42_2126
|
videos/HRA_part0/2126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, costumed in a shimmering silver outfit reminiscent of celestial bodies, performs an interpretive dance against a backdrop of the Uranus aurora. The aurora, with its vivid green and purple hues, illuminates the scene with an ethereal glow. The actor's movements are fluid and expressive, capturing the essence of cosmic energy and the mystical atmosphere of the distant planet. As the dance progresses, the auroral lights pulsate and swirl, creating a mesmerizing visual harmony between the performance and the celestial phenomenon. Throughout the video, the focus remains on the captivating dance, with the Uranus aurora serving as a breathtaking and dynamic canvas for the actor's artistry.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1865
|
videos/HRA_part2/1865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 savanna, two adult buffalo, with shaggy brown fur and impressive horns, engage in a tender moment. One buffalo affectionately caresses the other's face with its muzzle, displaying a rare display of gentleness and connection between these typically rugged creatures. The scene is set against a backdrop of lush grasslands and distant, rolling hills, capturing the essence of their wild habitat while highlighting the intimate bond shared by these majestic animals.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2418
|
videos/HRA_part1/2418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a focused doctor, dressed in a white lab coat, leans over a table, examining a specimen. On the floor below, a tiny mouse scurries across the wooden surface, navigating the shadows beneath the furniture. The scene alternates between the doctor's intense study and the mouse's cautious movements, highlighting the stark contrast between the clinical environment and the unexpected presence of the small creature.]"
},
{
"from": "gpt",
"value": "Bad. The mouse's running action in the video is not continuous and there are abrupt changes."
}
] |
seed44_1936
|
videos/HRA_part1/1936.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and a crisp white shirt, is spotted joyfully dancing in the middle of a highway during the golden hour. The unexpected scene unfolds as a small vole curiously watches from the roadside grass, adding a touch of whimsy. The officer's movements are lively, yet controlled, drawing the attention of passing motorists who slow down to witness this unusual spectacle. Despite the gravity of his profession, the officer's spontaneous dance embodies a lighthearted moment, offering a brief respite from the monotony of highway travel.]"
},
{
"from": "gpt",
"value": "Bad. The vole in the video did not show itself."
}
] |
seed46_2178
|
videos/HRA_part2/2178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with brown, shoulder-length hair unloads a stainless steel dishwasher in a modern kitchen with white cabinets and marble countertops. She wears a simple white T-shirt, blue jeans, and an apron, and her glasses rest on the tip of her nose as she intently organizes the dishes. The room is bright, with sunlight streaming in from a nearby window, illuminating the space and casting a warm glow on the polished floor. As she works, her movements are efficient and practiced, demonstrating her familiarity with the task.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1551
|
videos/HRA_part2/1551.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lustrous, cooked lobster is presented on a white plate, its vivid red shell contrasting beautifully against the pristine background. The lobster's body is split open to reveal tender, succulent meat, artfully garnished with fresh herbs and lemon wedges, enhancing the dish's visual appeal. Accompanied by a side of drawn butter and a sprinkle of parsley, the dish exudes elegance and promises a rich, indulgent dining experience, perfect for a gourmet feast. The steam gently rising from the plate adds a touch of warmth and freshness, inviting the viewer to savor every detail of this exquisite culinary creation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1454
|
videos/HRA_part0/1454.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a khaki safari outfit, complete with a wide-brimmed hat, kneels in a lush, green environment, closely observing a large hippopotamus. The director's intense focus and proximity to the wild animal emphasize the unique and potentially dangerous nature of the scene. The hippopotamus, with its massive body and distinctive features, slowly crawls through the tall grass, creating a sense of movement and life in the otherwise still landscape. The director's presence adds a narrative element, suggesting a story unfolding between human curiosity and the untamed wilderness.]"
},
{
"from": "gpt",
"value": "Bad. Hippo's head is twisted, body is twisted."
}
] |
seed46_1566
|
videos/HRA_part2/1566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, with a ferret perched on his shoulder, floats weightlessly in a vast cosmic pool that mirrors Jupiter's Great Red Spot. Dressed in a dark wetsuit and goggles, he somersaults gracefully through the water, the ferret securely nestled and seemingly unfazed. The swirling red and white clouds of Jupiter envelop the scene, creating a surreal and captivating contrast to the serene swimming motion. Throughout, the ferret remains a constant presence, its curious gaze following the actor's every move in this otherworldly aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1029
|
videos/HRA_part0/1029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown rat, with patches of white fur, walks methodically across a weathered wooden surface. It pauses momentarily, its whiskers twitching, before continuing its journey. The rat's movements are deliberate, each step calculated, as it navigates the worn planks. Its tail, long and pink, sways gently behind it, adding to the creature's curious demeanor. Throughout the scene, the rat remains the sole focus, walking with purpose on the textured wood, creating a compelling narrative of survival and exploration.]"
},
{
"from": "gpt",
"value": "Bad. The tail of the mouse in the video has missing parts, and the paws also have missing parts."
}
] |
seed44_1624
|
videos/HRA_part1/1624.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged nurse with graying hair and a face marked by worry stands in a dimly lit hospital room, her shoulders quivering as she experiences an intense emotional reaction. Dressed in a blue scrub top and black pants, she holds a clipboard against a background cluttered with medical equipment. She is depicted in close-up, her eyes closed in a moment of vulnerability, her body language conveying her internal struggle. The scene captures her in a raw, unguarded moment, her uniform rumpled and her stance unsteady, reflecting the stress and strain of her profession.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2512
|
videos/HRA_part0/2512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter wearing a black suit and white shirt, complete with a bow tie and name tag, holds a silver serving tray with a glass of red wine as he runs swiftly through a vast, meticulously maintained cemetery. The grass is neatly trimmed, and the tombstones are lined up in perfect rows, extending into the horizon under a clear blue sky. Suddenly, a cheetah appears, running alongside the waiter, matching his pace effortlessly. Both the waiter and the cheetah continue their run through the peaceful graveyard, the cheetah's spots contrasting against the greenery, while the waiter remains composed, maintaining a professional demeanor despite the unusual circumstances.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, and legs are twisted in the video, and the cheetah's body, head, legs, and paws are also twisted."
}
] |
seed44_1887
|
videos/HRA_part1/1887.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic male chef, wearing a classic white chef's jacket and black pants, is filmed in a bustling, modern restaurant kitchen. He begins by seasoning a dish with a sprinkle of herbs, his hands moving with practiced ease. Next, he deftly flips a piece of seared salmon in a sizzling pan, the steam rising around him adding to the atmosphere. Then, he carefully arranges the cooked salmon on a plate, garnishing it with fresh greens and a drizzle of sauce. Lastly, he gives a satisfied nod, presenting the beautifully plated meal to the camera, the vibrant colors of the food contrasting with the stainless steel appliances in the background.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and there is a sudden change, and the chef's spatula disappears suddenly. Also, the plate of salmon suddenly appears."
}
] |
seed46_2839
|
videos/HRA_part2/2839.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair and glasses, wearing a gray T-shirt, stands in a modern laundry room with gray walls and white cabinets, meticulously ironing a white shirt. He pauses to adjust the garment, showcasing his attention to detail. The room is well-lit, highlighting his focused expression and the neat arrangement of laundry supplies in the background. Throughout the scene, he continues to press the iron over the fabric, demonstrating his expertise in maintaining a sharp appearance, all set against the backdrop of a contemporary, organized laundry space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_3006
|
videos/HRA_part0/3006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green environment, a small brown mouse stands on the edge of a natural pool, surrounded by dense shrubbery and tall grass, creating an intricate network of thickets. The mouse looks intently at the water, its ears perked and body alert. Suddenly, it bravely leaps into the clear, shimmering pool, swimming with surprising agility, its tiny paws propelling it through the water. As it swims, the camera captures the ripples created by its movement, highlighting the contrast between the busy activity of the mouse and the stillness of the thickets surrounding the pool.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1636
|
videos/HRA_part0/1636.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom, a devoted teacher wearing a VR headset and haptic gloves guides students through an immersive virtual reality space training simulation. The teacher demonstrates a caressing gesture, using the VR equipment to teach sensitive and precise movements in zero-gravity conditions. The environment is depicted with advanced graphics, showing the teacher floating among stars and planets, while the students observe from their own VR stations, mimicking the instructor's actions to learn essential space exploration skills.]"
},
{
"from": "gpt",
"value": "Normal. The movements of the students in the video are basically normal, with slight lack of coordination."
}
] |
seed42_1314
|
videos/HRA_part0/1314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-dusted wilderness, two majestic bison stand side by side, their large, sturdy bodies nearly touching. One bison gently nudges the other with its snout in a tender caress, their breath visible in the crisp air. Their shaggy coats ripple slightly in the wind, and their eyes meet, conveying a deep bond. The scene is peaceful and intimate, set against a backdrop of distant mountains and a clear blue sky, highlighting the gentle nature of these powerful creatures.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1640
|
videos/HRA_part1/1640.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 passionate chef, donning a classic white chef's jacket and black pants, is filmed in high definition as he masterfully prepares an exquisite dinner in a bustling restaurant kitchen. The scene opens with him seasoning a sizzling steak with precision, the flames from the grill casting dramatic shadows. Next, he's shown tossing vibrant vegetables in a pan with a practiced flick of his wrist, the steam rising and enhancing the aroma. Then, he carefully plates the finished dish, garnishing it with fresh herbs, each movement demonstrating his culinary expertise. Lastly, the chef adds a final touch, drizzling a rich sauce over the dish, the colors and textures popping against the pristine white plate, ready to delight the senses.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1182
|
videos/HRA_part1/1182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 herd of African buffalo, distinguished by their massive curved horns and sturdy builds, gallop across a sunlit savanna, stirring up clouds of dust in their wake. The lead buffalo, a dominant male, charges ahead with determination, followed closely by the rest of the herd. They run through tall grass, which sways in the breeze, creating a dramatic contrast against the clear blue sky. The action is captured in high definition, focusing on the power and grace of these magnificent animals as they thunder across the landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1243
|
videos/HRA_part1/1243.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman wearing a brown jacket and brown pants is crawling on a wooden floor inside a rustic cabin. She is moving towards a large, curious moose that has its head inside the cabin through an open window. The moose, with its distinctively large antlers, is also partially inside the cabin, seemingly intrigued by the woman's presence, creating an unusual and captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The person's legs and hands are deformed. The cow's head is also deformed."
}
] |
seed42_3179
|
videos/HRA_part0/3179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 salaryman strides purposefully down a bustling Tokyo street, his black business attire contrasting sharply with the neon signs and billboards towering overhead. The urban landscape is alive with the energy of the city, as the pedestrian moves through crowds of similarly dressed workers. The architecture reflects a blend of traditional and modern styles, with historic buildings standing alongside sleek skyscrapers. Throughout the scene, the salaryman maintains his steady pace, his journey punctuated by the vibrant colors and dynamic movements of the city around him.]"
},
{
"from": "gpt",
"value": "Bad. The man's arms are slightly deformed while walking, and the faces of people in the background are blurry, with characters distorted."
}
] |
seed44_2497
|
videos/HRA_part1/2497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sandy desert under a wide, cloudless blue sky, a single brown camel moves slowly across the dunes, its large, padded feet carefully placing one in front of the other in a crawling motion. The desert stretches out behind and ahead of the camel, unbroken except for the undulating lines of sand. The sun, high and bright, casts the camel's long, distinct shadow on the dune it has just crossed, emphasizing the creature's solitary journey through this immense, arid landscape.]"
},
{
"from": "gpt",
"value": "Normal. The camel's walking in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed44_1218
|
videos/HRA_part1/1218.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 diligent male artist applies paint to a large, colorful abstract artwork on a vertical easel, positioned outdoors against a sunny, clear blue sky. Dressed in a simple white tank top and khaki cargo shorts, he works intently, surrounded by various tools of his trade including brushes, a palette, and a small table holding additional supplies. His focused expression and the vibrant colors of the painting contrast sharply with the natural greenery and clear sky in the background, creating a dynamic scene of creative energy and artistic passion.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, and the hands are twisted."
}
] |
seed46_3138
|
videos/HRA_part2/3138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek black panther walks with measured steps through a dense, shadowy forest, its eyes gleaming with an almost otherworldly green hue. The majestic feline's coat shimmers under the dappled sunlight filtering through the thick canopy above. With each confident stride, the panther's muscles ripple beneath its inky fur, exuding raw power and grace. The underbrush parts gently as the panther moves, revealing the intricate play of light and shadow on the forest floor, punctuated by the occasional flash of vibrant foliage.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1356
|
videos/HRA_part1/1356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, vibrant green and iridescent, hovers in a close-up shot against a blurred background of lush vegetation. Its wings, a blur of motion, propel it as it feeds from a red salvia flower, the curved beak piercing the bloom. The bird's small size, quick movements, and the detailed feathers are highlighted, set against the rich greenery and soft, natural lighting. The scene captures the hummingbird's agility and the delicate interaction between the bird and the flower, encapsulating the beauty of nature in high definition.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's eyes in the video were not generated."
}
] |
seed46_2446
|
videos/HRA_part2/2446.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the hazy, ethereal atmosphere of Neptune, a space-suited firefighter, equipped with a specialized breathing apparatus and protective gear, is seen wiping the visor of his helmet. A neon bat, adapted to the planet's unique environment, hangs upside-down from a rocky outcropping nearby, its vibrant wings contrasting against the dimly lit, gaseous landscape. The firefighter's actions are deliberate and methodical, emphasizing the importance of maintaining clear visibility in the challenging conditions of Neptune's alien skies.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3198
|
videos/HRA_part2/3198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone firefighter, clad in a specialized Neptune atmospheric suit, complete with a helmet and breathing apparatus, runs across a rugged, alien landscape bathed in eerie, ethereal light. The environment is dominated by hues of blue and green, evoking the mysterious atmosphere of Neptune. Wisps of cloud-like formations swirl in the distance, adding to the otherworldly ambiance. The firefighter's suit, equipped with advanced technology to withstand the harsh conditions, glimmers under the faint illumination, highlighting the bravery and determination required to perform such a daunting task in an extraterrestrial setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1515
|
videos/HRA_part2/1515.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a red t-shirt and black cap, meticulously cleans his silver car with a sponge in a residential driveway, set against a sunny day. His attire includes a red t-shirt with a white logo, black pants, and white sneakers, while his accessories consist of a black baseball cap and a wristwatch. As he works, his right leg occasionally bounces to an invisible beat, revealing his musical nature. Throughout the scene, he uses various cleaning tools, such as a bucket of soapy water, a hose, and a microfiber towel, all while maintaining a joyful demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the face is distorted, and the legs are twisted."
}
] |
seed46_1938
|
videos/HRA_part2/1938.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated nurse, wearing a clean, white uniform and a green apron, is diligently scrubbing the bathroom floor in a hospital setting, her focused gaze and determined posture highlighting her commitment to hygiene. She uses a green scrub brush and a bucket of soapy water, her actions methodical and thorough. The bathroom is modern and well-lit, featuring stainless steel fixtures and a clean, white toilet, sink, and shower stall. The nurse's attention to detail and her professional demeanor underscore the importance of maintaining a sterile environment in the healthcare facility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2539
|
videos/HRA_part1/2539.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city 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": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2925
|
videos/HRA_part2/2925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, dressed in a black leather jacket, dark jeans, and sunglasses, walks purposefully down a busy city street, the iconic Flatiron Building visible in the background. Suddenly, the scene shifts to depict him walking at an extraordinary pace, a visual effect suggesting the concept of light-speed travel. He continues his brisk walk, now surrounded by blurs of color and light, evoking the sensation of moving at incredible velocities. Throughout this dynamic sequence, he maintains his cool demeanor, his outfit unchanged, embodying the fusion of urban style and science fiction themes.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2709
|
videos/HRA_part1/2709.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male musician, donning a red bandana, black sleeveless shirt, and black jeans, skillfully stir-fries ingredients in a wok over a high flame. The kitchen features a large stainless steel hood vent and several pots hanging above, giving it a professional look. The artist, known for his energetic stage presence, exhibits precision and focus as he deftly flips vegetables and proteins in the pan. The vibrant colors of the food contrast beautifully with the dark metal utensils and the flames beneath the wok, creating a visually engaging scene. Throughout the process, he maintains his cool demeanor, occasionally checking the seasoning and adjusting the heat, demonstrating his culinary prowess alongside his musical talent.]"
},
{
"from": "gpt",
"value": "Bad. The male musician's facial features and hands in the video are distorted, and the hanging pots are generated abnormally."
}
] |
seed42_1963
|
videos/HRA_part0/1963.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 waiter in the video has uncoordinated movements."
}
] |
seed46_310
|
videos/HRA_part2/310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a black jacket and khaki pants, confidently walks alongside a zebra in the middle of a desert landscape, both seemingly unfazed by the arid environment. The director holds a megaphone in one hand and a script in the other, while the zebra, a symbol of the untamed, ambles beside him, the two forming an unlikely duo in this surreal scene. The sun casts long shadows, highlighting the stark beauty of the desert, as the director and the zebra continue their journey together, a testament to the unexpected alliances that can occur in the pursuit of art.]"
},
{
"from": "gpt",
"value": "Bad. No script was generated."
}
] |
seed46_2449
|
videos/HRA_part2/2449.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 stunning male pheasant, adorned with vibrant plumage of iridescent greens and blues, struts proudly across a lush meadow filled with tall grasses and wildflowers. The sunlight filters through the canopy of towering trees, casting dappled shadows that accentuate the bird's magnificent feathers. The pheasant pauses, its sharp eyes scanning the surroundings, before letting out a distinctive call that echoes through the peaceful countryside, asserting its presence in the rich, natural habitat that surrounds it.]"
},
{
"from": "gpt",
"value": "Normal. The wild chicken's movements in the video are slightly uncoordinated."
}
] |
seed44_2005
|
videos/HRA_part1/2005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man dressed as a waiter, wearing a black vest, white shirt, black tie, and apron, is playfully dancing with a horse in the middle of a grassy field under a clear blue sky. The horse, adorned with a golden bridle and red and gold saddle blanket, seems to be enjoying the unexpected dance, moving gracefully in sync with the waiter's steps. Both the waiter and the horse exhibit expressions of pure joy and abandon, creating a surreal yet delightful spectacle. The vibrant colors of their attire contrast beautifully with the natural greenery and blue sky, adding to the dreamlike quality of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The horse's ears and mouth, as well as the bridle, were generated incorrectly; the hand beside it was abnormally generated, and there was a sudden distortion and deformation in the middle frame."
}
] |
seed42_2719
|
videos/HRA_part0/2719.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 adorned with lavish decorations for an extravagant wedding, a neatly-dressed cashier, wearing a classic black vest and bow tie, diligently wipes the immaculate glass counter with a small cloth. The backdrop features elegant table settings, floral arrangements, and a large, illuminated dance floor, all indicative of an upscale celebration. The cashier's meticulous attention to detail ensures the space station's cash register area remains spotless amidst the grand festivities.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2535
|
videos/HRA_part2/2535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, temperate shrubland landscape, a chef wearing a classic white uniform and toque walks alongside a majestic, dark-furred wolf. Both figures are set against a backdrop of dense, lush vegetation, with the chef holding a large, brown paper bag presumably filled with ingredients. The pair continues their journey, moving purposefully through the shrubland, the chef's attire standing out against the rich greenery and the wolf's fur blending seamlessly into the natural surroundings. The scene conveys a sense of adventure and companionship between the chef and the wolf as they explore the wild terrain together.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1534
|
videos/HRA_part1/1534.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings with keen eyesight. Suddenly, it springs into action, jumping high into the air from the sandy ground of its desert habitat. The meerkat's body is arched gracefully mid-leap, showcasing its agility and strength. Its fur, a blend of tans and browns, contrasts beautifully against the clear blue sky, capturing the essence of life in the wild. As it lands, the meerkat's alert ears and expressive face reveal its readiness for any challenge in its environment.]"
},
{
"from": "gpt",
"value": "Bad. The meerkat's limbs in the video are not fully generated, and the tail is missing."
}
] |
seed42_1070
|
videos/HRA_part0/1070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural, grassy setting under a partly cloudy sky, two boys wearing a red shirt and a gray shirt work together to mend a broken wooden fence, using tools and materials at their disposal. They are focused on the task, with one boy hammering a nail into the wood while the other steadies the fence post. The atmosphere is cooperative and industrious, with the boys' clothes and hands getting dirty from the work. Nearby, a small barn and additional fencing can be seen, adding to the pastoral scene. The boys' dedication to fixing the fence is evident in their determined expressions and the progress they've made so far.]"
},
{
"from": "gpt",
"value": "Bad. The boy's movements in the video are not smooth and coordinated."
}
] |
seed46_1226
|
videos/HRA_part2/1226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a yellow high-visibility vest and gray trousers, crawls through a narrow tunnel within a vast, rocky quarry, his flashlight illuminating the rugged terrain. The dusty environment envelops him as he moves with determination, surrounded by towering walls of stone, showcasing the lesser-seen aspects of maintenance work in an expansive quarry setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, the hand is deformed, the head is distorted, and the legs are twisted."
}
] |
seed42_2574
|
videos/HRA_part0/2574.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 worker, clad in a yellow safety vest and black trousers, stands amidst the towering structures of an oil refinery under the vast sky. He is seen wiping down the massive pipes, his actions emphasizing the scale of the mammoth industrial landscape around him. The refinery, with its intricate network of pipes and tanks, looms large in the background, highlighting the solitary figure of the worker engaged in his task. The setting is dominated by the industrial aesthetics of the oil refinery, with the worker's presence adding a human element to the otherwise imposing scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_3022
|
videos/HRA_part0/3022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing swimming trunks and a cap, playfully interacts with a live rabbit at a backyard pool party. Surrounded by friends, he gently holds the rabbit, which remains calm, near the water's edge. The scene transitions to show the student swimming in the pool, while the rabbit sits safely on a towel nearby, being petted by another person. Throughout, the atmosphere is one of carefree enjoyment, with the student and his friends laughing and splashing in the water, and the rabbit seeming content in its temporary role as a poolside companion.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the student holding the rabbit as mentioned in the caption."
}
] |
seed42_3154
|
videos/HRA_part0/3154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female teacher, wearing a green shirt and black pants, is seen in a classroom with a high ceiling, assembling a wooden table. The room is filled with natural light from large windows, illuminating the space. She is kneeling on the floor, carefully screwing in a leg of the table with a screwdriver, demonstrating a practical skill to her attentive students, who watch from a distance. The teacher's patience and focus are evident as she meticulously puts together the piece of furniture, providing a valuable learning experience in a bright and welcoming environment.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher's fingers and feet are deformed, there are issues with the facial generation, limbs are missing, and the screwdriver is deformed."
}
] |
seed44_3181
|
videos/HRA_part1/3181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 underwater scene illuminated by natural light filtering through the water's surface, a school of vibrant, multicolored fish swim together in unison. The fish display a range of hues, including orange, yellow, and blue, with intricate patterns adorning their scales. They gracefully navigate the aquatic environment, surrounded by lush green seaweed gently swaying in the current. The detailed textures of the fish's bodies and the vivid colors of their surroundings create a captivating and serene underwater world.]"
},
{
"from": "gpt",
"value": "Bad. The fish's eyes in the video have generation issues, with some parts penetrating the model."
}
] |
seed46_1968
|
videos/HRA_part2/1968.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone coyote, characterized by its brown and gray fur, alert ears, and a bushy tail, traverses the lush rainforest floor. It walks purposefully among the vibrant green foliage, moss-covered logs, and fallen branches, creating a path through the dense undergrowth. The scene is set in a temperate rainforest, where the air is misty and moist, enhancing the rich greens and browns of the environment. The coyote's journey is filled with the sounds of dripping water and rustling leaves, as it explores this verdant, wet habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1744
|
videos/HRA_part2/1744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly contrasting scene, a lone hyena stands in the foreground, its silhouette framed against a golden sunset, while in the distance, meticulously aligned rows of lush green vines stretch across the landscape, indicating a vast vineyard. As the camera pans, a luxurious swimming pool comes into view, nestled amidst the vineyard, shimmering under the fading sunlight, offering a surreal juxtaposition of wild and cultivated beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3216
|
videos/HRA_part2/3216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray jacket and blue jeans, runs with a determined look across a desolate industrial landscape dominated by oil refineries. The scene opens with him striding purposefully, his gaze fixed ahead. Next, he's seen mid-stride, his right arm extended forward, the refineries' towering structures and billowing smokestacks looming behind him. Then, he's captured in motion, his left foot lifting from the ground, the industrial backdrop providing a stark contrast to his vibrant attire. Finally, the artist continues his run, his silhouette framed against the imposing oil refinery complex, embodying resilience and movement in an urban-industrial setting.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hands, arms, feet, and legs are twisted in the video."
}
] |
seed46_1494
|
videos/HRA_part2/1494.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 thoughtful young student, dressed in casual attire, gently caresses a chimpanzee seated beside her, both looking straight ahead. The scene is set against the backdrop of a busy industrial area, with large oil refineries visible in the background, emitting plumes of smoke into the hazy sky. Despite the industrial setting, the focus remains on the tender interaction between the student and the chimpanzee, conveying a sense of connection and empathy amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change, and a hand inexplicably appears on the gorilla's head."
}
] |
seed42_2318
|
videos/HRA_part0/2318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman stands tall and poised, her blonde hair in a sleek bun, wearing a fitted black blazer over a white collared shirt, black trousers, and black heels. She is positioned in front of a large window with a city skyline visible in the background, her gaze directed towards the urban landscape. The scene is bathed in the warm glow of the setting sun, casting a golden hue over the woman and the cityscape, highlighting her silhouette and the texture of her attire. The contrast between the structured clothing and the fluidity of her stance conveys a sense of power and elegance.]"
},
{
"from": "gpt",
"value": "Normal. The video only shows the camera moving while the person remains stationary."
}
] |
seed46_2038
|
videos/HRA_part2/2038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars gracefully over a vast, shimmering ocean, its expansive wingspan casting a shadow on the water below. The bird's plumage, a stunning blend of white and dark feathers, contrasts beautifully against the blue sky. As it glides through the air, its sharp eyes scan the sea for signs of prey. In the background, the silhouette of an island can be seen, adding depth and scale to the scene. The albatross, a symbol of freedom and endurance, continues its flight, the wind gently ruffling its feathers, embodying the spirit of the open sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1474
|
videos/HRA_part2/1474.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, vibrant forest setting, a mother beaver tenderly caresses her kit with her large, front paw, both sitting cozily within their wooden lodge. The mother, with her brown fur and attentive gaze, gently strokes the smaller beaver, who looks up at her with wide eyes, creating a heartwarming scene of maternal love. The wooden lodge, intricately built from branches and mud, provides a safe and nurturing environment for the family, with green leaves and trees visible in the background, highlighting the beauty of their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1694
|
videos/HRA_part1/1694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, rustic coffee shop filled with warm, golden light and the aroma of freshly brewed coffee, a young female cashier, wearing a green apron over a striped shirt, knits a vibrant red scarf during a lull in business. She sits behind the counter, surrounded by pastries, a cash register, and an espresso machine. Her focused expression and nimble fingers working the knitting needles capture the essence of making something beautiful by hand in a quaint, welcoming environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers in the video are not fully generated, and the yarn is unrealistic."
}
] |
seed44_1171
|
videos/HRA_part1/1171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wildlife sanctuary, a compassionate veterinarian, wearing a khaki shirt and cargo pants, gently wipes the face of a majestic cheetah lying on a checkered cloth, its gaze fixed on the vet. The scene is set outdoors, with lush greenery and wooden fences framing the backdrop, highlighting the unique bond between the medical professional and the wild animal. The vet's careful action, using a soft, white cloth, conveys a sense of tenderness and care, while the cheetah's calm demeanor suggests trust and familiarity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2103
|
videos/HRA_part2/2103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, clad in a spacesuit with a NASA logo, stands against the striking backdrop of a Martian sunset, characterized by its pinkish-blue hue. The director is captured mid-jump, with one arm raised in triumph, against the dramatic landscape of Mars. The sandy terrain stretches into the distance, dotted with rocks and craters, providing a stark contrast to the vibrant colors of the sunset. The director's silhouette is outlined by the warm glow of the setting sun, creating a powerful visual representation of human exploration and the beauty of the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1213
|
videos/HRA_part0/1213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic, casually dressed woman walks down a city street, passing by various urban elements such as a fire hydrant, a streetlight, and a parked car, all while maintaining a confident stride. She wears a brown jacket, blue jeans, and black shoes, with her hair tied back in a bun, showcasing her energetic yet relaxed demeanor. The cityscape includes a yellow taxi in the background, adding to the bustling atmosphere. As she continues her journey, the urban environment unfolds around her, capturing the essence of city life.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2341
|
videos/HRA_part0/2341.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 white hare, its fur thick and plush, crawls through a dense thicket of snow-laden pine trees, the texture of its coat contrasting starkly with the icy landscape. The hare's movements are cautious and deliberate, its eyes alert, as it navigates the snowy terrain in search of food. The scene is set against a backdrop of a serene winter forest, the hare's crawling motion emphasized by the slow, methodical pace, creating a sense of intimacy with the animal in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's movements in the video are slightly unsmooth."
}
] |
seed42_321
|
videos/HRA_part0/321.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white rabbit sits quietly by a serene pond, the first light of sunrise on Mercury casting a pale, ethereal glow over the still waters. The sky is a deep shade of indigo, dotted with fading stars, while the distant horizon glimmers with the soft, alien light of the emerging sun. The rabbit, with its soft fur glistening with dew, prepares to take a unique plunge, as it gently enters the calm waters, creating ripples that expand across the glassy surface, under the enchanting, otherworldly beauty of a Mercury dawn.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the sun's rays."
}
] |
seed42_2221
|
videos/HRA_part0/2221.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a medium-large raptor with a brown back and contrasting white underparts, soars gracefully over a serene lake at sunset. Its piercing yellow eyes are fixed on the water below, searching for prey. The bird's distinctive head, marked with a dark eye-stripe and a white throat, contrasts strikingly with its dark cap. Its underwings show a mix of white and brown streaks, while its legs dangle beneath it, ready to grasp a fish. The osprey's silhouette is framed by the warm glow of the setting sun, casting a golden hue over the tranquil waters.]"
},
{
"from": "gpt",
"value": "Normal. The claws show deformities and abnormalities."
}
] |
seed42_1011
|
videos/HRA_part0/1011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a film director, clad in a beige jacket, navy-blue shirt, and brown trousers, kneels on the floor of an art gallery, observing a taxidermied beaver. The setting is an exhibition space filled with various artworks, including paintings and sculptures. The director's intent gaze and body language suggest deep engagement with the beaver specimen, which is placed on a pedestal among other natural history exhibits. The camera captures this curious interaction from multiple angles, highlighting the director's fascination and the eclectic atmosphere of the gallery.]"
},
{
"from": "gpt",
"value": "Normal. The director's movements while kneeling on the floor to observe the beaver exhibit in the video are not smooth and coordinated, and there are sudden changes."
}
] |
seed46_1123
|
videos/HRA_part2/1123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge, sits attentively on a stone bench in a small, enclosed garden. He rests his hands on his thighs, wearing black gloves, and looks directly at the camera with a serious expression. Behind him, lush greenery and blooming flowers frame the serene setting, offering a peaceful contrast to his authoritative presence. The officer's attire includes a navy cap, and he holds a black baton in his right hand, symbolizing his role in maintaining law and order. Despite the tranquility of the garden, his alert posture and watchful gaze convey readiness and vigilance.]"
},
{
"from": "gpt",
"value": "Normal. The officer's hand in the video is generated incorrectly."
}
] |
seed46_2767
|
videos/HRA_part2/2767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a black uniform with a red vest and a bow tie, walks across a vast, icy landscape, surrounded by towering glaciers and rugged terrain. He carries a silver tray with a glass of champagne, balancing it gracefully as he strides forward. The scene is set against a backdrop of dramatic, icy mountains, with the waiter's polished shoes and formal attire contrasting starkly with the rugged, snow-covered ground. Despite the harsh environment, he moves with poise and determination, the luxurious glass of champagne glistening under the pale arctic sun.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2741
|
videos/HRA_part2/2741.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male musician, clad in a brown leather jacket, blue shirt, and black pants, gently caresses his acoustic guitar while sitting on a wooden bench. Surrounded by lush, green ferns and towering trees in a dense forest, he looks down at his instrument with a serene smile. The scene is illuminated by the soft glow of sunlight filtering through the foliage, casting dappled shadows on the mossy ground. The musician's tender touch and loving gaze convey a deep connection with his guitar, set against the serene backdrop of nature's splendor.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2483
|
videos/HRA_part0/2483.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spotted hyena, mid-jump, leaps across a grassy savanna landscape, its powerful hind legs fully extended beneath it, capturing the essence of its agility and strength. The hyena's spotted coat is vivid against the green vegetation, and its mouth is open, revealing sharp teeth, as it focuses on an unseen target ahead. The scene is set during the golden hour, with warm sunlight casting a glow over the hyena and the surrounding environment, highlighting the texture of the grass and the depth of the landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1976
|
videos/HRA_part1/1976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, spotted leopard leaps across a mossy log in a dense, lush forest, its powerful muscles rippling under golden fur flecked with black rosettes. Towering trees with emerald canopies surround the scene, dappled sunlight filtering through the leaves, casting an ethereal glow. The big cat lands gracefully on the forest floor, strewn with ferns and fallen leaves, before bounding away into the undergrowth, demonstrating the apex predator's agility and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's crawling movements are discontinuous and undergo sudden changes."
}
] |
seed46_1867
|
videos/HRA_part2/1867.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, wearing a khaki safari outfit complete with a vest, pants, and hat, walks alongside a capybara on a leash. They are strolling on a concrete path that winds through a lush, green landscape filled with trees and shrubs. The capybara, the world's largest rodent, is shown in profile, moving at a relaxed pace beside the human. The setting is a serene, outdoor environment, possibly within a zoo or wildlife sanctuary, where the two amble together in a scene that highlights the unique bond between the caretaker and the animal.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1312
|
videos/HRA_part2/1312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white swan floats regally on a tranquil lake, its reflection shimmering in the water. The swan, with its long, curved neck and proud demeanor, glides effortlessly, surrounded by lush green vegetation on the banks. Its wings, partially extended, display the exquisite feather patterns, while its webbed feet gently propel it forward. The serene atmosphere is enhanced by the soft, natural lighting that illuminates the scene, capturing the swan's every graceful movement on the mirror-like surface of the lake.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2025
|
videos/HRA_part0/2025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, donning a green jacket, blue jeans, and a gray cap, stands on a ladder propped against the side of a barn, which features a vibrant red exterior and white trim. He is engaged in cleaning the gutters, using a gloved hand to remove debris. The scene is set against a backdrop of lush greenery and a clear blue sky. Moments later, he pauses to survey his work, a pitchfork leaning against the barn wall beside him. The farmer then continues his task diligently, his attire and the pastoral setting creating a vivid image of rural life.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_207
|
videos/HRA_part0/207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zero gravity, a whimsical scene unfolds where a small, brown porcupine floats, performing a delightful dance. It gracefully pirouettes against a backdrop of stars and the vast cosmos, its quills gently swaying in the absence of gravity. The porcupine then leaps playfully, executing mid-air flips and twists with an infectious joy, its quills shimmering under celestial lights. Throughout the dance, the porcupine's movements are fluid and weightless, embodying the freedom and fun of dancing in space, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2209
|
videos/HRA_part0/2209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a well-dressed doctor, wearing a white coat and a stethoscope around his neck, finds himself in a vibrant restaurant filled with lively music. Surprisingly, he is accompanied by a monkey dressed in miniature clothing, sitting on a chair beside him. As the captivating beat takes over, the doctor and the monkey begin to dance together, their movements synchronized in a comical yet endearing manner. The other patrons, seemingly unfazed, continue dining, providing a backdrop of casual elegance to this unusual dance spectacle.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_3159
|
videos/HRA_part0/3159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 casually dressed man, wearing a dark gray t-shirt, sits at a wooden table in a dimly lit room with yellow walls and a red ceiling. He lifts a glass of water to his lips, pausing to drink. His gaze is directed away from the camera, towards another person sitting across from him. The atmosphere is relaxed and intimate, with the man's simple attire and the warm, homey setting creating a sense of comfort and familiarity.]"
},
{
"from": "gpt",
"value": "Good. Basically no problems."
}
] |
seed44_2110
|
videos/HRA_part1/2110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, wearing a gray jacket and khaki pants, sits cross-legged on a lush green meadow, gently caressing a docile water buffalo. The buffalo, with its large frame and distinctive horns, stands calmly beside a small body of water, accepting the student's affectionate touch. The student's serene facial expression and the peaceful surroundings, including trees and distant mountains, create a harmonious atmosphere. The scene is bathed in warm sunlight, casting a golden hue over the student and the buffalo, highlighting the tender connection between human and animal in a rural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1837
|
videos/HRA_part2/1837.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a blue jacket and jeans, walks alongside a graceful gazelle through the spacious interior of a futuristic space hotel. The hotel's design features large windows showcasing the vastness of space, with Earth visible in the distance. The student and the gazelle navigate the corridors, passing by otherworldly landscapes displayed on interactive walls. At one point, they pause near a recreational area, where guests can observe cosmic phenomena through a panoramic observatory dome. Throughout their walk, the unique bond between the student and the gazelle is evident, highlighting the extraordinary nature of this extraterrestrial encounter.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1376
|
videos/HRA_part0/1376.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark uniform with a badge and a radio attached to his belt, stands with a serious expression in the middle of an urban street, partially illuminated by the glow of a streetlight. In the background, a large, gray wolf leaps over a chain-link fence in a single, powerful bound, its eyes locked onto something unseen beyond the frame. The scene captures the juxtaposition of law enforcement and untamed nature, with the officer's authoritative presence contrasted by the wolf's wild, instinctive leap.]"
},
{
"from": "gpt",
"value": "Bad. The gray wolf's limbs appear deformed, and it directly crossing the fence is unrealistic."
}
] |
seed42_2114
|
videos/HRA_part0/2114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a branch, its distinctive black-and-white plumage gleaming under the sunlight filtering through the leaves of a large tree. The bird's eyes are sharp and alert, its beak curved and ready to snatch any unsuspecting prey. Behind it, the lush green foliage of the forest provides a stark contrast to its striking feathers, while the soft chirping of other birds creates a peaceful atmosphere. Suddenly, the magpie takes flight, its wings beating gracefully as it soars through the air, leaving a trail of black and white behind it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1303
|
videos/HRA_part0/1303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 North American porcupine, distinguished by its brown and white quills, runs through a dense forest environment, navigating between moss-covered trees. The porcupine, with its quills standing out prominently, dashes across the screen from right to left, showcasing its agility. Its facial features, including small eyes and a pointed nose, are clearly visible as it moves quickly, demonstrating the animal's unexpected speed and grace in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The porcupine in the video has a clipping issue when passing through the trees."
}
] |
seed46_2733
|
videos/HRA_part2/2733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cozy, well-lit room, two individuals sit side by side on wooden stools, engrossed in the meticulous task of hemming pants. One person, wearing a plaid shirt, focuses intently on the fabric spread across their lap, while the other, donning a gray sweater, holds a pair of scissors, ready to trim the excess material. Both use a sewing machine placed on a rustic wooden table, the sound of the needle punctuating the air as they work diligently. The scene is filled with tools of the trade, including spools of thread, a tape measure, and pins, all set against the backdrop of a warm, welcoming space adorned with shelves of craft supplies.]"
},
{
"from": "gpt",
"value": "Normal. The sewing machine in the video is not on the wooden table."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.