video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2069
|
videos/HRA_part2/2069.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer wearing a red shirt and brown overalls strolls through a vast, lush green field, holding a walking stick as he leisurely promenades. Suddenly, he leaps into the air, his hat flying off, with a wide smile on his face, revealing sheer joy and freedom. The farmer continues his playful jumping spree amidst the vibrant scenery, surrounded by endless rows of corn stalks swaying gently in the breeze. As he lands, he resumes his peaceful walk, stick in hand, with the sun casting a warm glow over the fertile land, creating a sense of harmony and contentment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1427
|
videos/HRA_part0/1427.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded musician wearing a brown cap, gray jacket, and blue jeans ascends a rocky cliff face, demonstrating his adventurous spirit. He skillfully plays a small drum-like instrument called a tambourine, attached to his harness, merging his passion for music with his love for climbing. The scene captures his fearless determination, with the tambourine adding a unique touch to his climbing gear, as he conquers the steep rock formation against a dramatic, cloudy sky.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2665
|
videos/HRA_part2/2665.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a futuristic spacesuit, gently caresses a small, feathered chicken on a Mars base camp, surrounded by high-tech equipment and monitors displaying scientific data. The young woman, with her hair tied back in a bun, looks down at the bird with a warm smile, providing a moment of tenderness in the stark, utilitarian environment. The base camp is illuminated by artificial lights, casting a soft glow on the scene, with the red Martian landscape visible through the transparent dome. The student's affectionate gesture towards the chicken offers a sense of comfort and connection in the otherwise alien setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's action of petting the chicken in the video is basically normal, with slight awkwardness."
}
] |
seed44_2799
|
videos/HRA_part1/2799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a dark green jacket, beige shirt, and brown trousers, is seen on set with a weasel perched on his shoulder. The weasel, with its sleek body and curious eyes, suddenly leaps off the director's shoulder, mid-air, creating a moment of unexpected levity. The director, maintaining his composure, watches the weasel's acrobatic jump with a mix of amusement and surprise, all captured against the backdrop of a bustling movie set.]"
},
{
"from": "gpt",
"value": "Normal. The weasel's movements in the video are not smooth."
}
] |
seed46_2917
|
videos/HRA_part2/2917.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy hamster sits upright on its hind legs, engaging in a grooming session within its cozy cage. The hamster meticulously wipes its face with its front paws, demonstrating a natural behavior typical of these animals. Its movements are deliberate and focused, highlighting the creature's self-care routine in a habitat filled with soft bedding and a water bottle visible in the background. The hamster's fur is a mix of brown and white, adding to the visual appeal of the scene as it diligently cleans itself.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2223
|
videos/HRA_part0/2223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 an unexpected scene, a mongoose, typically found in natural habitats, explores an industrial zone with caution, navigating through rusty pipes and concrete structures. Suddenly, it encounters a small pool of water, possibly from a recent rain, and surprisingly dips its paw in, showing curiosity about the liquid in this unusual environment. The mongoose then proceeds to swim gracefully, defying expectations of its usual terrestrial behavior, amidst the backdrop of industrial decay and urban grit. This juxtaposition highlights the animal's adaptability and resilience in an unorthodox setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2721
|
videos/HRA_part2/2721.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and a yellow firefighting jacket, gently wipes soot off a small, brown hedgehog that's been rescued from a fire. The hedgehog, nestled in the firefighter's protective glove, looks up with curious eyes as it's being cleaned. The scene takes place against the backdrop of a fire-damaged building, with smoke still lingering in the air, emphasizing the tender moment between the rescuer and the rescued animal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1715
|
videos/HRA_part1/1715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful woman stands tall, embracing the sunlight that cascades upon her, highlighting her radiant smile and the vibrant colors of her floral maxi dress. She is positioned on a wooden deck, overlooking a serene lake surrounded by lush greenery, with the distant silhouette of majestic mountains providing a breathtaking backdrop. Her curly brown hair, adorned with a delicate headband, gently sways in the breeze, while her closed eyes suggest a moment of peaceful contemplation. She holds a small bunch of wildflowers in her right hand, adding a touch of nature's beauty to the scene. The warm glow of the sun, combined with the natural splendor of her surroundings, creates a harmonious atmosphere that encapsulates the essence of tranquility and connection with the outdoors.]"
},
{
"from": "gpt",
"value": "Normal. The woman's face, headband, and hand in the video are basically normal, with slight inconsistencies."
}
] |
seed42_2455
|
videos/HRA_part0/2455.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, wearing a black cap, glasses, and a gray shirt, sits at a wooden table under a dimly lit lamp, intently sketching with a pencil in his right hand on a large sheet of paper. Musical instruments, including a guitar, a violin, and a trumpet, are visible in the background, indicating his passion for music. The focus is on the musician's face and hands as he draws, capturing his creative process in a room filled with musical equipment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1200
|
videos/HRA_part1/1200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vividly contrasting scene, two young boys, one wearing a red life jacket and the other in swimming trunks, are seen engaging with a camel on a sandy shore near shallow water, under a clear blue sky. The camel, adorned with a colorful saddle, dips its head into the turquoise water, while the children look on with delight. One boy, in the red life jacket, reaches out to touch the camel, capturing a moment of unexpected interaction between land and sea creatures. The setting sun illuminates the scene, casting warm hues across the water and highlighting the unique connection between the children and the camel in this coastal environment.]"
},
{
"from": "gpt",
"value": "Bad. The child in the red clothes in the video moves awkwardly, and the camel's drinking action is also not smooth."
}
] |
seed44_1117
|
videos/HRA_part1/1117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor, its curious nature evident as it explores its surroundings. It wears a tiny red harness, adding a pop of color against its natural brown and white fur. The room is spacious, with a large window letting in ample sunlight, casting warm light on the ferret as it moves about. In the background, a potted plant and a comfortable couch can be seen, providing context to the indoor environment where the ferret is freely walking.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1386
|
videos/HRA_part1/1386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a black jacket, white shirt, and khaki pants, finds himself in an unexpected scenario where he is energetically dancing in a meadow. Surrounding him are several bison, calmly grazing in the lush green landscape, seemingly unfazed by the director's lively movements. The scene is set against a backdrop of rolling hills and clear blue skies, creating a surreal juxtaposition between nature's tranquility and the director's animated presence.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the person show signs of deformity and mutation, and the face is also distorted. The cow in the background is deformed."
}
] |
seed46_1025
|
videos/HRA_part2/1025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull perches regally atop a wooden post on a deserted, windswept beach, its pristine white feathers ruffled by the salty breeze. The gull, with its sharp yellow beak and piercing eyes, surveys the vast expanse of sea and sky, seemingly contemplating the horizon. Suddenly, it spreads its wings, launching into flight, the camera capturing the intricate detail of its feathered anatomy as it glides effortlessly over the undulating waves. The seagull then returns to its perch, standing tall against the dramatic backdrop of an overcast sky, embodying the spirit of the coast.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1270
|
videos/HRA_part2/1270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A ruggedly handsome firefighter, wearing a red and yellow vest, blue jeans, and brown shoes, gently caresses a curious gazelle on a vast, sandy beach. The gazelle, with its striking, wide eyes and alert posture, stands on the shore, the waves lapping at its feet. The scene shifts to show the firefighter's strong, comforting hands petting the animal's face, as they both stand against a backdrop of clear blue skies and the endless ocean horizon. The firefighter's caring demeanor and the gazelle's trusting stance on the picturesque beach create a poignant, contrasting image.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2322
|
videos/HRA_part0/2322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a backdrop of lush greenery and blue skies, two young boys, one wearing a yellow shirt and the other in red, are intently engaged in fixing a wooden fence. They work diligently, using a variety of tools spread out before them, their faces concentrated and serious as they tackle the task at hand. One boy, dressed in a yellow shirt, blue shorts, and brown shoes, leans against the fence, his hands busy with repair work, while the other, in a red shirt, khaki shorts, and blue sneakers, stands with a tool in hand, ready to assist. The scene captures the industrious spirit of childhood play, with the boys' clothes and tools adding vibrant details to the image.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, face, head, and legs of the character in the video are distorted."
}
] |
seed44_1511
|
videos/HRA_part1/1511.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, standing in a lush green meadow under a vast blue sky, begins by shaking its bushy tail, sending droplets flying in a slow-motion spray. It then proceeds to wipe its face with a paw, leaving water droplets clinging to the fur around its eyes and nose. The fox's alert ears and curious gaze are highlighted as it pauses mid-wipe, showcasing the intimate grooming moment in stunning detail against the serene natural backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The red fox's face is slightly distorted."
}
] |
seed44_2344
|
videos/HRA_part1/2344.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, wearing a gray suit, white shirt, and patterned tie, stands in a dark room illuminated by a single spotlight, giving a speech about the concept of traveling at light speed. He passionately caresses an abstract sculpture representing the fabric of spacetime, emphasizing his points about the theoretical possibilities of superluminal travel. His gestures are expressive, conveying the emotional weight of discussing such a groundbreaking topic, all while maintaining eye contact with his unseen audience, inviting them to share in the wonder and complexity of his subject matter.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2933
|
videos/HRA_part1/2933.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a green shirt and khaki pants, walks alongside a realistic hare in an urban alley setting, both seemingly coexisting in the gritty environment. The janitor, holding a broom, looks down at the rabbit with a curious expression. In another moment, the janitor, still in his green uniform, leans against a brick wall while the hare sits calmly beside him, the cityscape in the background adding to the unusual pairing. Lastly, the janitor and the hare are seen walking together, the man in his green work attire and the rabbit hopping leisurely, both navigating the textured, urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's face is distorted, hands and feet are deformed, the rabbit is generated inconsistently, and the broom in the cleaner's hand suddenly disappears in the middle frame."
}
] |
seed46_3183
|
videos/HRA_part2/3183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, hardworking nurse, identifiable by her scrubs—light blue top and dark blue pants—devotes her day off to organizing her garage. She sorts through items, deciding what to keep, with sunlight streaming in from the open garage door. The nurse, now in a different set of scrubs, green top and dark blue pants, methodically arranges tools and equipment on shelves. She pauses to admire her progress, standing amid her organized belongings, which include a bicycle and various household items. Finally, she wipes her brow, pleased with her efforts, as she surveys the tidy space, now a reflection of her meticulous nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2559
|
videos/HRA_part1/2559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, upscale restaurant, a waiter with a mustache and wearing a black vest, white shirt, and black tie attentively wipes a round table with a white cloth. Behind him, a dingo stands on its hind legs, wearing a chef's hat and apron, attempting to mimic the waiter's actions with a smaller, comically proportioned cloth. The scene is set in an elegant dining room with wooden floors, high ceilings, and large windows, creating a surreal juxtaposition of sophistication and whimsy.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted, the object in hand is distorted, the Australian dingo's body and head are distorted."
}
] |
seed42_1935
|
videos/HRA_part0/1935.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of a large, sleek bass fish fills the screen, its body glistening with vibrant green and brown hues, accented by striking black spots. The fish's powerful form is emphasized as it swims within its natural freshwater habitat, surrounded by lush aquatic plants and a rocky bottom. The water's rippling surface occasionally comes into view, hinting at the bass's movements just beneath. The scene is captured in high definition, highlighting the intricate details of the fish's scales, fins, and eyes, offering a captivating glimpse into the underwater world of this formidable predator.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1509
|
videos/HRA_part1/1509.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense forest setting, a majestic stag with an impressive set of antlers leads a herd of deer through a narrow path, their movements graceful and unhurried. The camera captures their journey from a low angle, emphasizing the size and strength of the animals. The lush greenery surrounds them, providing a natural backdrop that complements their brown coats. As they walk, the sound of their hooves softly hitting the ground echoes through the woods, creating a serene atmosphere. The herd moves with purpose, navigating the terrain with ease, highlighting the beauty and resilience of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2433
|
videos/HRA_part0/2433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 director, distinguished by his brown hair and beard, along with round glasses, is seated in a director's chair on a set resembling a grassland heath. He interacts with a small gerbil, which scurries across the set's surface. The director is shown wiping his glasses with a cloth, revealing his blue eyes, while the gerbil continues its exploration nearby. The backdrop depicts a sunny day on the heath, complete with a blue sky and green vegetation, adding a natural element to the studio setting. Throughout, the director's focus alternates between the gerbil and wiping his glasses, capturing the unique dynamic between the two.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_309
|
videos/HRA_part1/309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kneels on a hardwood floor, wearing a grey turtleneck sweater, dark jeans, and brown boots, painting a vivid abstract artwork on a large canvas. A friendly dog, possibly a Golden Retriever, crawls playfully toward the artist, who gently pets it with a loving smile, both surrounded by the warm glow of a studio space filled with art supplies and natural light. The scene captures a tender moment between the artist and their canine companion, with the unfinished artwork providing a glimpse into the creative process.]"
},
{
"from": "gpt",
"value": "Bad. The artist's fingers and feet are deformed in the video, the eyes are not open, there is a missing part of the arm, and there are issues with the dog's limbs and face."
}
] |
seed44_1716
|
videos/HRA_part1/1716.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush temperate deciduous forest during autumn, two people, a woman in a green jacket and a man in a brown vest, are observed sitting on a blanket, engaged in a relaxed conversation. Beside them, a capybara crawls slowly across the blanket, its large size and docile nature evident. The forest floor is covered in a mosaic of fallen leaves, while the trees stand tall with their branches partially denuded, creating a dappled sunlight effect. The overall atmosphere is one of peaceful coexistence between humans and wildlife in the natural habitat of the capybara.]"
},
{
"from": "gpt",
"value": "Bad. The video generated an additional woman wearing a green jacket."
}
] |
seed44_1467
|
videos/HRA_part1/1467.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking beaver, clad in a miniature construction hat and suspenders, jumps enthusiastically over a series of logs arranged like hurdles, against a backdrop of lush greenery. The logs, positioned in a line, serve as obstacles for the beaver to leap over. The scene is set in a vibrant, verdant environment, with the beaver's energetic movements highlighting its industrious nature. As it clears each log, the beaver's determination and agility are evident, showcasing its ability to navigate challenges with agility and grace.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's paws and overalls in the video have issues."
}
] |
seed42_1743
|
videos/HRA_part0/1743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant green parrot with yellow facial feathers and red tail feathers perches on a branch, set against a blurred green background. The bird turns its head to look over its shoulder, displaying its detailed plumage. It then faces forward, revealing its sharp beak and curious expression. Next, it preens itself, using its beak to adjust its feathers, highlighting its self-care behavior. Finally, the parrot opens its wings slightly, showing off more of its stunning colors, all against a consistent blurred green backdrop that keeps the focus on the bird.]"
},
{
"from": "gpt",
"value": "Normal. The parrot's movements in the video are basically normal, with slight disharmony."
}
] |
seed46_2760
|
videos/HRA_part2/2760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a neatly trimmed beard and a muscular build rearranges furniture in a modern living room. He lifts a heavy wooden coffee table with ease, his biceps flexing under a tight-fitting gray T-shirt. Wearing dark blue jeans and white sneakers, he positions the table in the center of the room, then pauses to consider the layout. Satisfied, he proceeds to adjust the placement of two large, plush armchairs, ensuring they are perfectly aligned with the table. The room features minimalist decor, with white walls, a large window letting in ample natural light, and a sleek flat-screen TV mounted above a low-profile entertainment unit. Throughout the scene, the man's confident demeanor and attention to detail are evident as he meticulously arranges the furniture to achieve a balanced and inviting space.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are severely distorted in the video."
}
] |
seed44_1793
|
videos/HRA_part1/1793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dimly lit, futuristic setting, a skilled musician, dressed in a black leather jacket, plays a gleaming silver electric guitar. Nearby, an enormous, friendly bear, adorned with a red bow tie, listens intently, its paw gently resting on the musician's shoulder in a gesture of companionship. Suddenly, a shimmering wormhole opens behind them, revealing a kaleidoscope of colors and swirling galaxies. The musician and the bear look into the wormhole, their expressions a mix of awe and curiosity, as they contemplate the mysteries of the universe together.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_210
|
videos/HRA_part1/210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, solitary rhinoceros is seen swimming in a natural body of water, surrounded by lush green vegetation. Its body is partially submerged, showing off its powerful swimming capabilities as it moves through the water. The rhino's head remains above the surface, its eyes focused ahead, and its mouth occasionally opening to breathe. The water gently laps at its thick skin, creating ripples that extend outward. In the background, tall trees and dense foliage provide a contrast to the open water where the rhinoceros swims.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2290
|
videos/HRA_part0/2290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 college student, dressed in a maroon hoodie and gray sweatpants, diligently wipes down a large, brown bison statue with a white cloth, showing care and attention to detail. The scene takes place on a grassy campus, with trees in the background, highlighting the unique connection between the student and the symbolic animal figure. The student's focused expression and the careful motion of wiping the bison's surface convey a sense of respect and tradition associated with university life.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2744
|
videos/HRA_part0/2744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene unfolds as a sleek, black king cobra emerges from tall, dense grass, its hood partially spread. It races forward, muscles rippling under its shiny scales, demonstrating the surprising speed of these normally slow-moving serpents. The snake's eyes are intently focused ahead, suggesting a purposeful journey or a response to a nearby threat, all captured against a backdrop of lush, green foliage.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_220
|
videos/HRA_part2/220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sun-drenched subtropical shrubland, a striking red fox gently caresses the foliage with its bushy tail as it moves gracefully through the sparse landscape. The fox, with its vibrant fur and alert demeanor, interacts tenderly with the arid environment, highlighting the delicate balance between predator and habitat. Against the backdrop of scrub vegetation and scattered trees, the fox's movements convey a sense of care and connection to the natural world.]"
},
{
"from": "gpt",
"value": "Normal. The red fox's movements in the video are not smooth."
}
] |
seed42_2506
|
videos/HRA_part0/2506.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an imaginative scene, a lone camel, adorned with vibrant red and yellow fabrics, stands gracefully at the edge of a bustling highway under a vivid orange sunset. Vehicles whiz by in the background, forming streaks of light against the twilight sky. The camel begins to sway and dance, moving its body to an unheard rhythm, creating a surreal contrast between the wild and the urban landscape. Its movements are fluid and expressive, drawing attention despite the chaos of the surrounding traffic. The highway lights and car headlights illuminate the scene, casting dramatic shadows as the camel continues its dance, a captivating spectacle where nature meets the modern world.]"
},
{
"from": "gpt",
"value": "Normal. The camel's movements in the video are not smooth."
}
] |
seed44_1872
|
videos/HRA_part1/1872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant nudibranch, adorned with striking orange and white hues, gracefully glides across a coral reef teeming with life. Its intricate body showcases an array of colors and textures, including bold orange patches and delicate white spots. The marine environment is rich with various shades of blue, green, and brown, providing a stunning contrast to the nudibranch's vivid appearance. Surrounding the scene are schools of tropical fish, their scales shimmering in the underwater light, while the reef's complex structure offers a mesmerizing backdrop to the creature's serene movement.]"
},
{
"from": "gpt",
"value": "Normal. The eye generation of the sea slug in the video is problematic."
}
] |
seed44_1015
|
videos/HRA_part1/1015.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional nurse, clad in a light blue scrubs top and dark blue scrubs pants, sits at a desk with a name badge visible on her chest. She types diligently on a desktop computer keyboard, her focus unwavering. Behind her, a hospital room is visible, featuring a bed with crisp white sheets and a patient resting peacefully under a blanket. Medical equipment lines the walls, including an IV stand and a monitor displaying vital signs, while a window allows natural light to illuminate the space. The nurse's posture and concentration convey her dedication to her work in this healthcare setting.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2560
|
videos/HRA_part0/2560.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor wearing a yellow high-visibility vest, khaki cargo shorts, and a green t-shirt is crawling on a sandy beach, possibly searching for lost items or performing an unusual cleaning task. The beach is wide and sandy, with shallow water and a calm sea stretching into the distance. Palm trees dot the landscape, and the beach is relatively empty except for a few people walking in the background. The janitor's actions are focused and deliberate, contrasting with the serene coastal scenery.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2569
|
videos/HRA_part2/2569.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of fresh mackerel, glistening under bright lights, is presented on a bed of ice. The fish has distinctive vertical stripes, a sign of its freshness, and its eyes are clear and shiny. The camera then zooms out to reveal the fishmonger's stall, bustling with activity, where various species of fish are displayed on ice. The mackerel takes center stage, surrounded by other seafood, emphasizing its appeal among the array of options. Throughout, the high-definition footage captures the vibrant colors and textures of the fish market, focusing on the mackerel as the star attraction.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2086
|
videos/HRA_part0/2086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric engineer, clad in a green jumpsuit and safety helmet, finds himself in an unexpected scenario amidst the industrial backdrop of a power plant. Surrounded by towering turbines and complex machinery, he encounters a curious lizard, its vibrant scales contrasting starkly with the metallic environment. Inspired by this unusual meeting, the engineer begins to dance, his movements fluid and joyful, as if the rhythms of the machinery have become his own. The lizard watches, almost as if entranced, as the engineer twirls and leaps, creating a surreal scene where the boundaries between human, nature, and industry blur harmoniously.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, twisted hands, twisted legs, and a twisted lizard's body."
}
] |
seed42_1166
|
videos/HRA_part0/1166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning avant-garde space fashion, sprints across a futuristic stage illuminated by neon lights. Dressed in a metallic silver bodysuit, complete with high-tech accessories and a helmet visor, they leap with dynamic energy. The scene is set in a grand, space-themed venue, filled with an audience captivated by the performance. Spotlights follow the actor as they navigate the runway, showcasing the innovative designs against a backdrop of cosmic visuals and ambient electronic music. The fusion of performance art, cutting-edge fashion, and sci-fi aesthetics creates a mesmerizing spectacle.]"
},
{
"from": "gpt",
"value": "Normal. The actor in the video has missing limbs and is not fully generated."
}
] |
seed42_2076
|
videos/HRA_part0/2076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 young, cheerful nurse, wearing a white uniform and a badge, is seen running through a lush, green landscape dotted with tall trees and vibrant vegetation. In the distance, a serene hot springs oasis comes into view, its steam gently rising against the backdrop of a clear blue sky. The nurse, with a backpack and running shoes, continues her jog towards this peaceful destination, her movements fluid and energetic. Upon arrival, she pauses to enjoy the tranquil atmosphere, the steam from the hot springs swirling around her, before continuing her run along the scenic path that meanders through the verdant scenery.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's limbs were not fully generated, and the face was not generated."
}
] |
seed46_1032
|
videos/HRA_part2/1032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge, cap, and sunglasses, stands at the edge of a zoo's flamingo enclosure, where vibrant pink birds congregate. The scene shifts slightly to reveal a clear blue pool within the zoological park, where the officer now interacts with the public, demonstrating water safety techniques. Nearby, children and families watch, some seated on benches under the shade of lush trees, while others lean on the railing, observing the swimming demonstration with interest. Throughout, the police officer remains engaged and attentive, fostering a sense of community and safety among the zoo visitors.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are not smooth."
}
] |
seed44_1553
|
videos/HRA_part1/1553.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male bassist passionately plays a sleek, black upright bass, his eyes closed in concentration, against a dark stage background. He wears a black turtleneck sweater and jeans, exuding confidence and skill. His right hand expertly plucks the strings while his left hand positions the notes on the fingerboard. The bass, adorned with white fret markers, resonates with each stroke, creating deep, rich tones. The musician's dedication and the instrument's elegance are highlighted under the dim stage lights, captivating the audience with the bass's powerful sound.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers were not generated, the hand was generated blurry, and the man's head was not generated."
}
] |
seed46_1640
|
videos/HRA_part2/1640.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate chef, donning a classic white chef's jacket and black pants, is filmed in high definition as he masterfully prepares an exquisite dinner in a bustling restaurant kitchen. The scene opens with him seasoning a sizzling steak with precision, the flames from the grill casting dramatic shadows. Next, he's shown tossing vibrant vegetables in a pan with a practiced flick of his wrist, the steam rising and enhancing the aroma. Then, he carefully plates the finished dish, garnishing it with fresh herbs, each movement demonstrating his culinary expertise. Lastly, the chef adds a final touch, drizzling a rich sauce over the dish, the colors and textures popping against the pristine white plate, ready to delight the senses.]"
},
{
"from": "gpt",
"value": "Bad. The chef's fingers and fork in the video are not fully generated, and the pot is deformed."
}
] |
seed42_2003
|
videos/HRA_part0/2003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man wearing a casual jacket and jeans walks through a futuristic cityscape, where the architecture blends elements from different eras, creating a sense of time distortion. He moves with purpose, passing by a mix of old-world cobblestone streets and modern glass skyscrapers. The sky above is tinted with a slight orange hue, suggesting a world where the laws of physics have been altered. As he continues his journey, the background subtly shifts, revealing glimpses of historical landmarks juxtaposed with advanced technology, alluding to the concept of time dilation affecting his walk.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand in the video has issues."
}
] |
seed46_1652
|
videos/HRA_part2/1652.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A captivating scene unfolds where a talented violinist, dressed in a vibrant red cloak, plays a melodious tune while gracefully dancing on a vast, celestial stage illuminated by the ethereal glow of Saturn's rings in the distant cosmic horizon. In the foreground, a majestic white horse adorned with golden bridle and flowing mane leaps in perfect sync with the music, its hooves barely touching the stardust-covered stage, embodying a surreal fusion of artistry, nature, and the cosmos.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, face, arms, legs, and hands, and the white horse also has a twisted face and legs."
}
] |
seed42_1675
|
videos/HRA_part0/1675.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, spiky European hedgehog leaps into the air, defying expectations as it jumps over a miniature hurdle, showcasing its unexpected agility. The hedgehog, with its typical brown and white quills, lands softly on a lush green surface, demonstrating its natural ability to navigate obstacles. The scene is set against a simple, uncluttered outdoor backdrop, allowing the hedgehog's unique action to be the focal point of the video.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_20
|
videos/HRA_part1/20.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female cashier with a headband, working at a checkout counter filled with various snacks and beverages, gently caresses a stuffed cheetah. The stuffed animal is placed on the counter next to a cash register, amidst a selection of candy bars. The woman looks lovingly at the toy, her hands tenderly stroking its soft fur, as if sharing a moment of affection with an imaginary companion in the midst of her daily routine.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1946
|
videos/HRA_part2/1946.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 is seen grooming itself meticulously, its paws lifting to wipe across its face and whiskers. Positioned against a neutral grey backdrop, the rat's actions are the focal point, as it carefully tends to its cleanliness, showcasing the natural behavior of self-care in rodents. The scene is intimate, with the rat's fur and whiskers detailed in high definition, emphasizing the texture and vibrancy of its coat against the monochromatic setting.]"
},
{
"from": "gpt",
"value": "Normal. The fingers and mouth of the brown rat in the video are poorly generated, and one ear is missing."
}
] |
seed46_1463
|
videos/HRA_part2/1463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush subtropical dry forest, a group of five individuals, three women and two men, engage in a cleaning ritual. The women, dressed in green shirts and beige shorts, wipe leaves from a wooden table under the shade of a large tree. One of the men, wearing a yellow shirt and brown shorts, wipes the surface of a fallen log nearby. The other man, in a white shirt and blue shorts, wipes his brow, likely from the physical exertion of the task. The scene is filled with vibrant green foliage, and a sense of camaraderie and purpose is evident among the group members as they work together in the serene forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the face is distorted, and the leaf is distorted."
}
] |
seed44_3150
|
videos/HRA_part1/3150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, possibly his cub, against the backdrop of a lush, green savanna during golden hour. The adult lion, with its voluminous tawny mane, displays affection, while the cub, sporting a lighter coat and smaller stature, responds with innocent playfulness. The heartwarming interaction unfolds under a vast, cloud-dappled sky, with scattered acacia trees and distant mountains completing the serene African landscape. This intimate moment captures the rare display of tenderness and bonding within the lion family, far from the typical fierce and powerful image associated with these animals.]"
},
{
"from": "gpt",
"value": "Normal. The adult male lion's movements in the video are basically normal, with the cub's movements being a bit uncoordinated."
}
] |
seed44_1235
|
videos/HRA_part1/1235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a waiter in a crisp, white uniform gracefully carries a tray with a solar sail design etched onto it, reflecting the ambient light beautifully. The scene transitions to reveal a vast, serene pool where individuals swim leisurely, their movements creating ripples on the water's surface. The connection between these elements is seamless, as the solar sail motif continues to play a prominent role throughout the scene, symbolizing the merging of technology and tranquility. The waiter's elegant stride and the swimmers' peaceful strokes form a harmonious contrast, encapsulating the essence of a luxurious and innovative aquatic experience.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's body is missing a part, and the hand proportions are generated abnormally."
}
] |
seed44_1542
|
videos/HRA_part1/1542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature, bespectacled man, presumably a writer, stands on a ladder, cleaning the rain gutters of a charming, old house. He wears a brown jacket over a checked shirt, blue jeans, and a cap, while holding a long-handled gutter scoop. The scene is set against a backdrop of lush greenery, indicating a peaceful, suburban environment. The writer's focused expression and the tools of his current task, including the ladder, scoop, and a bucket placed on the grass, suggest a dedicated approach to home maintenance. Despite the mundane activity, his attire hints at his dual identity as a creative professional and a homeowner managing everyday chores.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and legs are deformed."
}
] |
seed42_2931
|
videos/HRA_part0/2931.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction site bustling with activity, filled with hard hats and heavy machinery, serves as the backdrop for a massive crane towering overhead. The crane, painted in bold yellow and black stripes, extends its long arm skyward, with a hook dangling below. Sunlight glints off the metal, highlighting the intricate framework and gears that enable the crane's powerful movements. At the top, a small cabin shelters the operator, who skillfully maneuvers the crane to lift and place heavy steel beams, essential for building the city's skyline. Dust and debris swirl around the base, where workers guide the crane's actions with precise hand signals, contributing to the urban landscape's ongoing transformation.]"
},
{
"from": "gpt",
"value": "Normal. The worker in the video is not shown."
}
] |
seed44_3082
|
videos/HRA_part1/3082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 art gallery illuminated by soft purple lighting, a distinguished doctor, wearing a crisp white lab coat over a button-down shirt and slacks, meticulously wipes an ancient relic. The artifact, seemingly made of obsidian, is displayed on a sleek, metallic pedestal amidst avant-garde artworks floating in zero gravity. The doctor's focused gaze and careful handling emphasize the significance of the object, while the surrounding art pieces, including abstract sculptures and vibrant paintings, add a touch of cultural richness to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's movements in the video are slightly unsmooth."
}
] |
seed44_2145
|
videos/HRA_part1/2145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a green swimsuit, sits on a sandy beach near a turquoise body of water, typing away on a laptop, while a small hedgehog perches on the writer's shoulder. The hedgehog has a tiny life jacket on, matching the writer's swimwear. In another scene, the writer is shown swimming in the clear waters, with the hedgehog floating alongside in its miniature life vest, both enjoying a peaceful day at the seaside under a bright, sunny sky.]"
},
{
"from": "gpt",
"value": "Bad. The writer's hand, hedgehog, and life jacket in the video have generation issues."
}
] |
seed42_1055
|
videos/HRA_part0/1055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative musician, adorned in a casual outfit featuring a gray turtleneck sweater and dark pants, sits on a wooden chair in a cozy, dimly lit room. Surrounded by musical instruments, the artist focuses intently on knitting a vibrant red scarf, demonstrating a surprising talent beyond music. The scene captures the individual's dual passions, highlighting their artistic versatility as they skillfully knit while sitting amongst guitars and sheet music, basking in the warm glow of a single lamp.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1793
|
videos/HRA_part2/1793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, futuristic setting, a skilled musician, dressed in a black leather jacket, plays a gleaming silver electric guitar. Nearby, an enormous, friendly bear, adorned with a red bow tie, listens intently, its paw gently resting on the musician's shoulder in a gesture of companionship. Suddenly, a shimmering wormhole opens behind them, revealing a kaleidoscope of colors and swirling galaxies. The musician and the bear look into the wormhole, their expressions a mix of awe and curiosity, as they contemplate the mysteries of the universe together.]"
},
{
"from": "gpt",
"value": "Normal. The bear's movements in the video are not smooth."
}
] |
seed46_2524
|
videos/HRA_part2/2524.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a young, cheerful cashier, wearing a green apron over a striped shirt, is seen enjoying a swim in a clear, tranquil body of water surrounded by scrublands. The cashier, with short, wavy hair and a nose ring, alternates between swimming and floating on the water's surface, showcasing a sense of freedom and relaxation. The scrublands, with their sparse vegetation and sandy soil, provide a stark contrast to the refreshing water, creating a unique and captivating scene. Throughout, the cashier's attire remains consistent, featuring the green apron and striped shirt, as they immerse themselves in the peaceful environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2216
|
videos/HRA_part0/2216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 farmer wearing a dark green jacket, blue jeans, and brown boots stands in a lush, green meadow dotted with dandelions. He looks down with a slight smile as he spots a small vole. The vole, with its distinctive round ears and brown fur, leaps from one dandelion tuft to another in the foreground, creating a playful contrast against the serene farm landscape. The farmer watches the vole's antics with amusement, his stance relaxed and his hands resting on his hips, as the rural setting provides a peaceful backdrop to this unexpected interaction.]"
},
{
"from": "gpt",
"value": "Normal. The middle-aged farmer was not fully generated."
}
] |
seed44_1531
|
videos/HRA_part1/1531.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tan, agile dingo leaps over a low branch in a sparse woodland setting, its muscles taut and ears flattened against its head, showcasing its wild nature. The canine's body is mid-air, suspended in a moment of action, with its hind legs propelling it forward. Its piercing eyes are focused ahead, and its tongue hangs out slightly, revealing its determination and vitality. The surroundings consist of scattered trees and brush, highlighting the dingo's natural habitat as it performs this energetic jump.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2051
|
videos/HRA_part2/2051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 anthropomorphic fox, wearing a doctor's white lab coat over a crisp blue shirt and a stethoscope around its neck, is seen swimming in a clear blue pool. The fox maintains a relaxed yet focused expression, showcasing its unique ability to swim effortlessly while fully clothed. The pool is surrounded by lush greenery, creating a serene atmosphere as the sunlight filters through the leaves, casting dappled shadows on the water's surface.]"
},
{
"from": "gpt",
"value": "Bad. The fox's face is distorted in the video."
}
] |
seed46_2513
|
videos/HRA_part2/2513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a distinguished lawyer, clad in a classic black suit and white shirt, gently caresses the metallic surface of a Mars rover model placed on a wooden table. The room is dimly lit, casting dramatic shadows across the scene. The lawyer's face reflects a mix of fascination and professional poise, while the rover, adorned with intricate details and wheels designed for extraterrestrial terrain, stands as a symbol of human innovation and exploration. This intimate interaction between the legal world and space technology creates a thought-provoking narrative about the convergence of seemingly unrelated fields.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1912
|
videos/HRA_part1/1912.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, bald musician, donning a black turtleneck, focuses intently on fixing a leaky faucet in an upscale bathroom with marble countertops. Initially, he looks thoughtful, holding a wrench and examining the faucet. Moments later, he is seen tightening the faucet with the tool, his sleeves rolled up, revealing a tattoo on his arm. He then tests the faucet, turning it on and off, ensuring no leaks remain. Finally, he wipes his hands on a towel, looking satisfied with his handiwork, all set against the backdrop of a luxurious bathroom with a marble sink and countertop.]"
},
{
"from": "gpt",
"value": "Bad. The musician's movements to repair the faucet in the video are very disjointed and jerky."
}
] |
seed42_2774
|
videos/HRA_part0/2774.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man with a bushy beard and wearing a brown jacket, blue jeans, and a black cap walks side by side with a coyote on a dirt path. They are set against a background of dense green forest and a sky filled with fluffy white clouds. The man, holding a wooden staff, and the coyote, with its distinctive bushy tail, navigate the wilderness together, their unlikely companionship highlighted by the peaceful, natural setting. Their journey unfolds on a trail marked by fallen leaves and tree roots, with the occasional glimpse of other wildlife in the surrounding woods.]"
},
{
"from": "gpt",
"value": "Normal. The man and the wolf's walking movements are not smooth, and there is a lack of coordination between them."
}
] |
seed42_1347
|
videos/HRA_part0/1347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged doctor with short, neatly styled brown hair, wearing a white lab coat over a blue button-up shirt and khaki pants, is comforting a crying young patient. The child, dressed in a yellow T-shirt and blue shorts, sits on a medical examination table, clutching a stuffed animal, while the doctor gently places a reassuring hand on the child's shoulder. The scene takes place in a brightly lit clinic room, with medical posters on the walls and a computer screen visible in the background. The doctor's empathetic expression and the child's teary face convey a moment of vulnerability and care in a clinical setting.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's actions of placing his hand on the child's shoulder in the video are basically normal, with only slight awkwardness."
}
] |
seed46_1610
|
videos/HRA_part2/1610.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A giant panda, identifiable by its black ears and eye patches, crawls through a lush, green bamboo grove within the expansive botanical gardens. The panda's methodical movements are highlighted against the vibrant backdrop of the garden, filled with diverse plant life. It crawls on all fours, showcasing its distinctive gait, with the botanical gardens' rich vegetation and meticulously maintained pathways framing the scene. The panda's actions are set against this verdant setting, emphasizing its natural habitat within the carefully curated environment of the botanical gardens.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the panda missing one leg, the ears are not close to the head, and the body is twisted."
}
] |
seed46_2564
|
videos/HRA_part2/2564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, dressed in a dark blue shirt and wearing glasses, sits at a desk cluttered with books and papers, engrossed in typing on a laptop. Suddenly, a dazzling, intense white hole explosion occurs behind him, wiping out everything in its path except for the writer and his desk, which remain untouched. The force of the explosion is so powerful that it erases the background, leaving only a blinding white light. Despite the chaos unfolding behind him, the writer remains undisturbed, continuing to type away, seemingly oblivious to the cosmic event taking place just feet away.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1289
|
videos/HRA_part1/1289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine, high-quality close-up of a fresh cod fillet takes center stage, its surface glistening under bright lights. The fish boasts a clean, white flesh with a hint of natural oils visible, presenting a perfect texture for culinary delights. Set against a simple, dark background, the cod fillet's purity and freshness are accentuated, making it visually appealing for seafood connoisseurs and chefs alike.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2452
|
videos/HRA_part1/2452.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, clad in a yellow jacket and black trousers, stands on a glacier, performing maintenance on a piece of equipment. The scene opens with a close-up of his hands, wearing black gloves, carefully wiping ice from a sophisticated device. The vast, icy landscape stretches behind him, with the sun casting a warm glow on the cold environment. As he continues to wipe away the frost, the camera pans out to reveal the enormity of the glacier and the solitude of his task. The engineer's focused expression and the stark beauty of the icy terrain provide a captivating contrast in this high-definition shot.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_271
|
videos/HRA_part0/271.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest, blue jeans, and a brown shirt, interacts with a moose in a serene lake, both swimming together in the cool, clear water. The scene opens with the worker paddling gently, the moose swimming nearby, and lush greenery framing the tranquil waterscape. Next, the worker and the moose are seen swimming side by side, the man's safety vest and the moose's large antlers clearly visible above water. Then, the worker, still in his yellow safety vest, blue jeans, and brown shirt, floats on his back, the moose swimming peacefully beside him. Finally, the two unlikely companions, the worker in his distinctive attire and the majestic moose, continue to swim together in harmony, the peaceful lake and verdant surroundings creating a picturesque setting.]"
},
{
"from": "gpt",
"value": "Bad. The worker's face, eyes, and mouth in the video are generated inconsistently, the legs are generated distorted, and the moose's antlers are generated somewhat inconsistently."
}
] |
seed44_2616
|
videos/HRA_part1/2616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, muscular man, shirtless and wearing only swimming trunks, stands on a vast Martian landscape, gazing up at the star-studded night sky. The red, rocky terrain stretches out behind him, dotted with boulders and craters, while a faint horizon line suggests the curvature of the planet. In the foreground, the man has just emerged from a clear, shimmering pool of water, droplets clinging to his skin and the rocks around him. The pool, seemingly out of place on this arid world, adds an element of mystery and wonder to the scene, as the man contemplates the cosmos from this otherworldly vantage point.]"
},
{
"from": "gpt",
"value": "Normal. The video only shows the camera moving while the person remains stationary."
}
] |
seed46_2684
|
videos/HRA_part2/2684.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heroic firefighter, clad in full gear and a yellow helmet, stands in a lush, green forest near a majestic waterfall, holding a gerbil gently in his hands. He carefully wipes water from the small animal's face, ensuring its safety, as the waterfall cascades powerfully in the background, creating a dramatic contrast between the tender moment and the raw force of nature.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's movements in the video are very uncoordinated, and the firefighter's movements are slightly uncoordinated."
}
] |
seed46_1681
|
videos/HRA_part2/1681.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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-covered tundra landscape, a small, furry badger emerges from its burrow, the entrance barely visible among the icy terrain. It cautiously crawls out, its round body and short legs moving slowly against the stark white backdrop. The badger, with its distinct black and white striped face, looks around with beady eyes, alert and ready to retreat at any sign of danger. Its movements are deliberate and measured as it explores the frigid environment, searching for food beneath the snow. The scene is framed by the endless expanse of the tundra, dotted with sparse, low-lying shrubs and ice formations, creating a sense of isolation and survival in the harsh wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2543
|
videos/HRA_part0/2543.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a vibrant orange pipefish, resembling a seahorse, gracefully hovers near a bed of lush green seagrass, its elongated body and small fins elegantly propelling it through the crystal-clear waters. Its distinctive snout extends forward as it explores its environment, surrounded by the swaying blades of seagrass that provide a stunning contrast to its unique form. The sunlight filters through the water, casting dappled light on the scene, highlighting the intricate details of the pipefish's skin and the delicate movements of its fins as it navigates its aquatic habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2113
|
videos/HRA_part2/2113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a gray jacket over a white shirt and black pants, is hard at work unclogging a drain in a dimly lit room. He kneels on the floor, his focus intense as he uses a metal tool to clear the clog. The scene is framed by pipes and machinery, emphasizing the industrial setting. His work is meticulous, as he carefully removes debris from the drain, revealing the inner workings of the pipe. Throughout, his dedication to the task is evident, as he ensures the drain is thoroughly cleared, the water now flowing freely, with the satisfaction of a job well done apparent in his demeanor.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1444
|
videos/HRA_part1/1444.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic scene unfolds, featuring a creative individual sitting at an easel, engrossed in painting a detailed landscape, with a curious squirrel perched on the artist's shoulder. Nearby, a tranquil pond offers a serene contrast, its glassy surface broken only by ripples as a squirrel, perhaps inspired by its surroundings, bravely ventures into the water, swimming with surprising grace. The artist, still absorbed in their work, occasionally glances at the unexpected swimmer, capturing the unique moment on canvas.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2728
|
videos/HRA_part0/2728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, donning a black beret and a red and black striped shirt, dances whimsically in a studio filled with vibrant paintings and art supplies. In their right hand, they hold a ferret that matches their playful energy, engaging in a synchronized dance that reflects their unique bond. The ferret, wrapped around their wrist like a furry bracelet, seems to enjoy the movement, adding a touch of eccentricity to the scene. The artist's left hand gestures expressively, complementing their dance moves, while the chaotic yet colorful environment around them enhances the creative atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2989
|
videos/HRA_part2/2989.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen illuminated by neon lights, a chef wearing a sleek, silver uniform and gravity-defying boots stands aboard an anti-gravity vehicle. The vehicle, resembling a levitating platform with intricate, glowing circuitry, hovers above a metallic countertop cluttered with advanced cooking gadgets. The chef, with a focused gaze, wipes a stainless steel utensil with a microfiber cloth, preparing for culinary innovation amidst the backdrop of a high-tech, floating workstation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1301
|
videos/HRA_part2/1301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of four young children, two boys and two girls, are joyfully splashing in a clear blue swimming pool, their laughter echoing in the bright, sunny day. One boy, wearing green swim trunks, playfully jumps into the water from the side of the pool, creating a splash. Meanwhile, a small, curious brown mouse peers over the edge of the pool, its tiny head poking out, seemingly intrigued by the commotion and the splashing water. The children, unaware of the mouse's presence, continue to swim and play, their faces full of delight and energy, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show two girls, nor does it generate the action of a boy in green swimming trunks jumping into the water from the edge of the pool."
}
] |
seed44_2679
|
videos/HRA_part1/2679.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a man wearing a spacesuit and holding a large cosmic cloth wipes across the icy, rocky surface of Saturn's rings, set against the vastness of space with stars twinkling in the distance. The man, with a determined expression, is shown from different angles as he meticulously cleans the ring material, creating a stark contrast between the mundane act of cleaning and the extraordinary setting of space. Throughout the sequence, the majestic planet Saturn looms large in the background, its distinct rings partially obscured by the man's cleaning efforts, adding a touch of whimsy to the otherwise serious task.]"
},
{
"from": "gpt",
"value": "Bad. The man's facial features and hands in the video have generation issues."
}
] |
seed46_2788
|
videos/HRA_part2/2788.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a flannel shirt, worn jeans, and a wide-brimmed straw hat, meticulously repairs a wooden fence under the golden glow of the setting sun. His hands, strong and capable, are wrapped around a hammer as he replaces a broken slat, embodying a rugged, down-to-earth character. The rural landscape stretches behind him, dotted with tall grass and distant trees, creating a serene backdrop for his focused labor. The fence, now mended, stands as a testament to his efforts, while the actor takes a moment to lean against it, surveying his work with a sense of accomplishment and satisfaction.]"
},
{
"from": "gpt",
"value": "Bad. The actor's arm is missing in the video, the fingers are deformed, and the face is blurry."
}
] |
seed46_1384
|
videos/HRA_part2/1384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, spiky European hedgehog runs energetically across a lush, green garden, its tiny legs moving swiftly beneath it. The hedgehog, with its distinctive white-tipped spines, navigates through the foliage with determination, its snout pointed forward. In another scene, the hedgehog continues its journey, now scampering across a wooden deck, its movements quick and agile. The video captures the hedgehog's active nature, showcasing its ability to navigate various terrains with ease, all under the cover of night, as indicated by the dimly lit surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the hedgehog with an issue of having too many legs."
}
] |
seed46_1615
|
videos/HRA_part2/1615.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, dressed in a sky-blue scrubs top and matching cap, tends to a patient in an expansive, sunlit grassland. She gently wipes the patient's face with a soft cloth, her caring demeanor evident in her focused eyes and gentle smile. The serene landscape of tall, swaying grass and distant, rolling hills provides a peaceful backdrop to the intimate moment of care. The nurse's attire, emblematic of her profession, contrasts beautifully with the lush greenery, highlighting her role as a caregiver in this unexpected outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's face and hands in the video were poorly generated, with the nurse having three hands in some frames."
}
] |
seed42_2552
|
videos/HRA_part0/2552.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate female teacher, wearing a blue blouse and glasses, sits at her desk in a classroom after school hours. She quietly cries, her face in her hands, revealing her vulnerability. Behind her, a world map hangs on the wall, adding depth to the scene. As she weeps, her shoulders gently shaking, the peaceful classroom with its neatly arranged desks and chairs provides a stark contrast to her emotional state. The dim afternoon light filtering through the window highlights her silhouette, emphasizing the solitude and intensity of her private moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2655
|
videos/HRA_part1/2655.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An innovative engineer, wearing a casual button-down shirt and khaki pants, is seen sketching mall blueprints on a large, clear desk, surrounded by architectural models and technical drawings. Moments later, the scene shifts to a vibrant mall interior, where the same engineer is seen interacting with a diverse group of shoppers, pointing out design features and technological advancements. Finally, the video captures the engineer enjoying a well-deserved break by swimming leisurely in a modern, glass-enclosed pool, located on the mall's rooftop, showcasing a harmonious blend of work and relaxation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1252
|
videos/HRA_part1/1252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city park during autumn, two diverse groups of people sit separately on long, wooden benches under tall, leafy trees with golden foliage. One group consists of four friends, two women and two men, engaged in lively conversation, with one woman laughing heartily. They wear casual fall attire, including jackets, scarves, and hats. The other group features three elderly individuals, two women and a man, sitting quietly and observing the surroundings. They are dressed warmly in coats, sweaters, and gloves, with the women wearing headscarves. The scene captures the essence of human connection and the peaceful coexistence of different generations in a beautiful outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_300
|
videos/HRA_part0/300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic brown horse gallops across a lush, green meadow under a clear blue sky, its muscular body rippling with each powerful stride. The horse's mane and tail flow dramatically in the wind, creating a sense of speed and freedom. A pair of vibrant yellow flowers appear briefly in the foreground, adding a pop of color to the scene. The horse continues its run, hooves kicking up small clumps of earth, highlighting its strength and grace as it moves through the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_216
|
videos/HRA_part1/216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male lawyer, wearing a dark suit and a white shirt, attentively listens in a courtroom setting, his face expressing concern and focus. Seated at a wooden desk adorned with legal documents, he leans forward intently, his right hand resting on his chin in a gesture of deep consideration. The background features a traditional court setting with wood-paneled walls and a high ceiling, emphasizing the seriousness and formality of the legal proceedings. The judge and other participants are partially visible, adding context to the scene without detracting from the central figure of the engaged lawyer.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1900
|
videos/HRA_part1/1900.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, wearing a small backpack adorned with patches, walks purposefully across a barren lunar landscape under a star-studded sky, holding a well-thumbed copy of a science fiction novel in its mouth. Its eyes, filled with curiosity and determination, reflect the distant stars. It passes by a small, glowing campfire, hinting at a recent gathering of fellow space book club members, who have presumably shared tales from their latest galactic reads. The fox continues its journey, the book's title, \"Cosmic Chronicles,\" visible as it strides forward into the cosmic night, leaving footprints on the moon's dusty surface.]"
},
{
"from": "gpt",
"value": "Normal. The fox in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2438
|
videos/HRA_part0/2438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, dressed in a futuristic silver spacesuit, is depicted in zero gravity within a space station habitat, performing a series of jumps against a backdrop of LED-lit panels. He executes a powerful jump, legs spread wide, arms extended, and face obscured by his helmet's visor, capturing the essence of weightlessness. In another frame, he appears to push off from a handrail, propelling himself through the air with a sense of effortlessness. Throughout the sequence, the space station's cylindrical structure, complete with porthole windows and complex machinery, provides a vivid setting for his graceful movements.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs in the video are deformed and partially missing."
}
] |
seed42_1203
|
videos/HRA_part0/1203.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single kangaroo, identifiable by its reddish-brown fur, large muscular tail, and defined facial features, is seen jumping across a vast, arid landscape. The kangaroo bounds through the dry, sparsely vegetated terrain, its movements fluid and powerful. Its ears are alert, and its eyes are focused, conveying a sense of purpose and energy. The background is a vast, open space, punctuated by distant trees and a clear blue sky, emphasizing the kangaroo's natural habitat and the scale of its environment. The kangaroo's motion is captured in mid-air, showcasing the unique and iconic jumping ability that defines these marsupials.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's movements in the video are not smooth and are uncoordinated."
}
] |
seed44_1305
|
videos/HRA_part1/1305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 black panther leaps majestically across a moonlit savannah, its muscles rippling beneath dark fur that shimmers under the celestial glow. The powerful feline bounds over tall grasses, leaving a trail of disturbed foliage in its wake, as it propels itself forward with a burst of speed and grace. Upon landing, the panther crouches low, ready for its next spring, against the backdrop of a vast landscape, dotted with distant trees and illuminated by the silvery light of the full moon.]"
},
{
"from": "gpt",
"value": "Bad. The jumping motion can be seen, but the movements are not continuous and there are sudden changes."
}
] |
seed46_3102
|
videos/HRA_part2/3102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical prehistoric scene, a massive woolly mammoth leaps over a frozen log in a snow-covered forest during the Ice Age, with tall pine trees framing the action. The mammoth, complete with shaggy brown fur and impressive tusks, is captured mid-air, its large body defying expectations as it clears the obstacle with surprising agility. The icy landscape, dotted with ancient conifers, adds to the dramatic effect of this unlikely jump, highlighting the creature's strength and adaptability in its harsh environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2379
|
videos/HRA_part2/2379.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, donning a gray suit, sits at a desk cluttered with law books and papers, attentively reading a document. He momentarily pauses, lifting a fork loaded with pasta to his mouth, revealing his multitasking nature. The room is illuminated by the warm glow of a table lamp, casting a soft light on the busy scene. A cup of coffee and a glass of water sit nearby, within easy reach for this hardworking legal professional as he sustains himself through his demanding workday.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2255
|
videos/HRA_part1/2255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weathered farmer, clad in a brown jacket, gray beanie, and khaki pants, dances gleefully in a grassy field under a partly cloudy sky, with rolling hills in the background. An ibex, standing nearby, observes the farmer's antics with curiosity. The farmer, his face etched with lines from years of hard work, performs a series of playful dance moves, his boots kicking up tufts of grass. The ibex, its horns curving gracefully upward, seems to mimic the farmer's movements, creating an unexpected yet charming duet between man and animal. Throughout the scene, the farmer's joyful expressions and the ibex's inquisitive gaze capture the essence of an unlikely friendship forged in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2226
|
videos/HRA_part1/2226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a navy uniform with a badge and a peaked cap, kneels in a park surrounded by green grass and trees, gently caressing a small brown hare with soft, comforting strokes. The officer's compassionate expression and careful handling of the hare, which sits calmly in the palm of his hand, convey a sense of tenderness and care. The peaceful setting, with the lush vegetation and clear sky, adds to the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1185
|
videos/HRA_part1/1185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kingfisher bird perches regally on a weathered branch that extends over a serene body of water, its vibrant blue and orange feathers glistening in the sunlight. The bird's piercing gaze is fixed on the water below, hinting at its hunting prowess. Suddenly, it takes flight, its wings a blur of color against the tranquil backdrop of the pond, surrounded by lush green foliage. As it hovers above the water, about to dive, the scene captures the kingfisher's agility and the beauty of nature in a single, captivating moment.]"
},
{
"from": "gpt",
"value": "Ba. The kingfisher's wing movements in the video are uncoordinated."
}
] |
seed46_2969
|
videos/HRA_part2/2969.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a uniform consisting of a blue shirt and black pants, is seen in a pet store setting, gently caressing a hamster with care. The hamster, nestled in the palm of the worker's hand, is calm and seemingly comfortable with the interaction. The scene is set against a backdrop of various pet supplies and cages, creating a familiar environment for animal lovers. The worker's facial expression conveys a sense of tenderness and respect for the small creature, highlighting the bond between humans and pets.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the worker's face or black pants."
}
] |
seed42_2314
|
videos/HRA_part0/2314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, clad in a brown jacket and wide-brimmed hat, traverses the icy terrain of a vast glacier, crawling on all fours to navigate the challenging landscape. Against a backdrop of towering ice formations, he crawls over the frosty surface, his form contrasting starkly with the pristine white expanse. The farmer's methodical movements and determined expression convey his resilience and connection to the harsh yet awe-inspiring environment. Throughout the scene, he continues to crawl across the glacier, his actions emphasizing the human spirit's perseverance in the face of nature's grandeur.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.