video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
---|---|---|
seed46_3036
|
videos/HRA_part2/3036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage boy wearing a red jacket and khaki pants is sprinting across a grassy field, his gaze fixed ahead with determination. As he runs, a small rabbit enters the frame from the bottom right corner, bounding alongside him. The student acknowledges the rabbit with a brief glance, but both continue their run, the student maintaining his focus and the rabbit keeping pace, against the backdrop of a clear blue sky and distant green hills.]"
},
{
"from": "gpt",
"value": "Bad. The boy's face in the video is generated blurry, his hands and feet are deformed, and the rabbit is generated abnormally."
}
] |
seed44_1088
|
videos/HRA_part1/1088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space library illuminated by soft, ambient lighting, a diligent worker clad in a sleek, form-fitting silver suit with integrated tech panels runs along a moving walkway. The vast shelves of books and digital archives tower above, reflecting the movement. The worker's focused gaze and the dynamic motion of running contrast with the static, orderly environment. Nearby, a robotic arm extends from the shelving to retrieve a book, highlighting the integration of technology and human effort in this advanced setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2167
|
videos/HRA_part1/2167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, typically a wild and elusive creature, is shown in an extraordinary scene, gently interacting with the sandy beaches of a coastal landscape. The bobcat, with its distinctive tufted ears and short tail, is depicted in a moment of unexpected tenderness, seemingly caressing the sand with its paw, a behavior rarely captured on camera. This unique encounter unfolds against the serene backdrop of a beach, where the gentle touch of the bobcat's paw on the sand challenges our perceptions of these usually solitary and fierce predators.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the bobcat's claws and eyes in the video has issues."
}
] |
seed42_2572
|
videos/HRA_part0/2572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An African elephant, distinguished by its large ears and tusks, is depicted swimming in a serene, reflective body of water under a starlit sky, evoking a sense of tranquility and vastness. The elephant is shown in a three-quarter view, with water droplets visible on its skin, indicating its aquatic activity. The stars above, including the prominent red dot of Mars, twinkle in the dark, clear night sky, providing a cosmic backdrop to the scene. The elephant's trunk is partially submerged, and its eyes are closed, conveying a peaceful, almost meditative state as it floats in the water, encapsulating the unique combination of stargazing and swimming.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1365
|
videos/HRA_part2/1365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a dark green beret, black turtleneck, and brown corduroy jacket, is seen from above, walking alongside a gerbil on a wooden table. The gerbil, sporting a small red bowtie, scurries ahead on its tiny feet. The artist follows, holding a sketchbook and pencil, capturing the gerbil's movements in a series of quick, expressive sketches. The table is cluttered with art supplies, including paintbrushes, tubes of oil paint, and a half-finished canvas, adding to the creative atmosphere. Natural light filters through a nearby window, casting a warm glow over the scene.]"
},
{
"from": "gpt",
"value": "Normal. The hamster does not have a red bow."
}
] |
seed42_2267
|
videos/HRA_part0/2267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a white shirt, black vest, and black trousers, diligently mops the floor of an empty restaurant during the daytime. The space is notably devoid of customers, with only a single table set with plates and cutlery visible in the background. The waiter's focus is intense as he works, pushing the mop back and forth across the smooth, light-colored tile flooring. His movements are methodical and purposeful, emphasizing his commitment to maintaining a clean dining environment. The natural light filtering through the windows highlights the cleanliness of the space, further emphasizing the waiter's efforts.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_2614
|
videos/HRA_part1/2614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a muscular build, wearing a black tank top and blue jeans, pushes against a large, gray boulder in the middle of a lush forest. His face contorts with effort, highlighting his determination. The scene is set in a dense woodland area, with sunlight filtering through the trees and casting dappled shadows on the ground. The man's strong physique and focused expression convey a sense of strength and perseverance as he exerts himself against the immovable object.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2311
|
videos/HRA_part1/2311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 magnificent leopard, with striking golden eyes and a distinctive pattern of rosettes on its tawny fur, is captured in high definition as it lies on a branch. It begins by looking straight ahead, showcasing its majestic presence. Then, it turns its head to the right, revealing its sharp features and powerful muscles rippling beneath its coat. Next, the leopard proceeds to clean itself, licking its paw and wiping it across its face, a display of natural behavior in its untamed habitat. Throughout the sequence, the leopard remains perched on the branch, its gaze occasionally flicking towards the viewer, offering a rare glimpse into its private grooming routine.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions a leopard licking its paws and using them to wipe its face, which does not appear in the video."
}
] |
seed44_3111
|
videos/HRA_part1/3111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a gray sweater and blue jeans, steps out from a charming cottage, holding a small trash bag. She walks purposefully down a stone path, surrounded by lush greenery and flowers, to reach a large wooden bin. The scene is set in the golden hour, with soft sunlight filtering through the trees, casting a warm glow on the idyllic setting. The writer pauses for a moment, looking contemplative, before depositing the trash bag into the bin. The peaceful atmosphere and natural beauty of the surroundings provide the perfect backdrop for her daily routine, offering a glimpse into the simple yet meaningful moments in the life of an artist.]"
},
{
"from": "gpt",
"value": "Bad. The writer's face generation is abnormal, hands and feet are deformed, and the garbage bag in the writer's hand suddenly disappears in the middle frame."
}
] |
seed44_2117
|
videos/HRA_part1/2117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a well-dressed lawyer, complete with a suit, tie, and glasses, sits calmly on a wooden bench outdoors. Against a backdrop of lush greenery, the lawyer gently caresses a porcupine, which remains relaxed and quill-free. The lawyer's demeanor suggests a deep connection with nature, particularly with the docile porcupine, which is depicted without its typical defensive quills, highlighting a unique bond between human and animal in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers are missing in the video, there are issues with the generation of his eyes, and there are problems with the generation of the porcupine's mouth."
}
] |
seed44_125
|
videos/HRA_part1/125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful woman wearing a vibrant yellow apron over a casual outfit of a gray t-shirt and black leggings, her brown hair tied back in a ponytail, is seen cooking in a modern kitchen. She expertly chops vegetables on a wooden cutting board using a sharp knife, the overhead lights reflecting off the stainless-steel appliances behind her. Her hands, adorned with rings, move with practiced ease as she seasons the ingredients in a large skillet on a gas stove, steam gently rising from the pan. Throughout, she maintains a warm smile, occasionally glancing up from her task, creating an inviting atmosphere in the well-lit kitchen space.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted, and the knife is twisted and deformed."
}
] |
seed42_286
|
videos/HRA_part0/286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black cap, sits at a desk in a sparsely decorated room with a large window in the background, casting a grid-like pattern of light and shadow. He leans forward attentively, reading a document with a serious expression, his right elbow resting on the desk and his left hand holding the page. The room is filled with a sense of calm professionalism, with the window providing a source of natural light that illuminates the officer and the paperwork, highlighting his dedication to duty.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2682
|
videos/HRA_part0/2682.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, clad in a white uniform and hat, stands near a tranquil body of water where a bison is swimming, creating a unique juxtaposition of urban culinary expertise and natural wildlife. The chef looks on thoughtfully, perhaps contemplating the ingredients for a dish inspired by the majestic bison. The scene is set in a lush, green environment, with the bison calmly paddling through the water, its head and hump visible above the surface, while the chef observes from the shore, a wooden cutting board and knife in hand, ready to embrace the wilderness's offerings.]"
},
{
"from": "gpt",
"value": "Normal. The bison's head is distorted in the video, and the chef's hands are also distorted."
}
] |
seed42_1851
|
videos/HRA_part0/1851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 futuristic engineer, clad in a high-tech silver suit, is depicted running across a vast Galactic nebula, with swirling cosmic clouds and distant stars providing a dramatic backdrop. The engineer, wearing a sleek helmet that reflects the nebula's vibrant colors, is shown in various dynamic poses, conveying a sense of speed and determination. The scene is set against a massive, ethereal nebula, its colorful gas formations creating a stunning visual contrast with the engineer's metallic attire, emphasizing the thrilling combination of human endeavor and the awe-inspiring scale of the universe.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2588
|
videos/HRA_part0/2588.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer with short brown hair and glasses, wearing a gray shirt, sits at a desk cluttered with papers and pens. She is intently writing with a pen in her right hand, her focus evident on her face. Behind her, a large window reveals a bustling cityscape at twilight. A laptop and coffee mug sit on the desk beside her, while a bookshelf filled with engineering texts and a whiteboard covered in equations complete the scene, highlighting the intellectual environment. The engineer pauses briefly to look up, perhaps contemplating her next line of thought, before returning to her writing with renewed determination.]"
},
{
"from": "gpt",
"value": "Normal. The woman's hand is deformed."
}
] |
seed44_162
|
videos/HRA_part1/162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the midst of a futuristic, vibrant festival, a diverse group of people, adorned in shimmering metallic fabrics and illuminated by neon lights, dance ecstatically under the vast night sky. In the background, an advanced Solar Sail spacecraft hangs majestically above a distant horizon, its vast, reflective surface catching the dim starlight. Suddenly, a wild dingo, its fur aglow from the ambient luminescence, bounds into the frame, adding a touch of unpredictability to the scene. It weaves between the dancers, who barely notice the creature's presence as they continue their uninhibited celebration, encapsulating a unique blend of humanity, nature, and cutting-edge technology.]"
},
{
"from": "gpt",
"value": "Bad. The wild dog's movements in the video are not smooth, and the character's actions in the video are not smooth."
}
] |
seed44_2855
|
videos/HRA_part1/2855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer clad in a blue shirt and khaki pants is seen walking alongside a chimpanzee wearing a tiny red cap, both navigating through a lush, verdant forest. The engineer, carrying a backpack and holding a machete, looks thoughtful as they traverse the underbrush. The chimp, balancing on two legs with a banana in its hand, occasionally glances up at the engineer with curiosity. They continue their journey together, the engineer leading the way with purpose, while the chimpanzee follows closely, the dense greenery of the forest enveloping them.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's hand in the video is deformed, the gorilla's face and claws are generated with problems, and the machete held by the engineer is unrealistic."
}
] |
seed46_2535
|
videos/HRA_part2/2535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, temperate shrubland landscape, a chef wearing a classic white uniform and toque walks alongside a majestic, dark-furred wolf. Both figures are set against a backdrop of dense, lush vegetation, with the chef holding a large, brown paper bag presumably filled with ingredients. The pair continues their journey, moving purposefully through the shrubland, the chef's attire standing out against the rich greenery and the wolf's fur blending seamlessly into the natural surroundings. The scene conveys a sense of adventure and companionship between the chef and the wolf as they explore the wild terrain together.]"
},
{
"from": "gpt",
"value": "Normal. The chef's and the wolf's walking actions in the video are basically normal, with slight disharmony."
}
] |
seed42_2710
|
videos/HRA_part0/2710.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, resembling Colin Farrell, is seen walking through a dense forest with tall trees, wearing a brown jacket, jeans, and boots. Suddenly, the scene changes to reveal a prehistoric setting, where the actor now finds himself casually strolling beside a woolly mammoth. Both the actor and the mammoth continue their leisurely walk together, with the mammoth's massive frame towering over the actor, who appears unfazed by the extraordinary situation. They meander through the ancient landscape, surrounded by lush vegetation and underbrush, creating a surreal juxtaposition of eras and species.]"
},
{
"from": "gpt",
"value": "Bad. The actor's facial features in the video are blurry, fingers are distorted, and the woolly mammoth's head is abnormally generated."
}
] |
seed44_2590
|
videos/HRA_part1/2590.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costume reminiscent of a prehistoric mammoth, crawls across a barren, rocky terrain under a desolate, overcast sky. The actor's face is obscured by the mammoth headpiece, which features large, curved tusks and shaggy, gray-brown fur. The costume also includes a body suit with similar fur, giving the impression of a mammoth's bulk. The landscape is dotted with sparse vegetation, adding to the prehistoric feel. As the actor crawls, the camera captures the struggle and determination in the movements, conveying a sense of survival in a harsh environment.]"
},
{
"from": "gpt",
"value": "Bad. The mammoth's legs show signs of deformed mutations. An additional tusk has also grown."
}
] |
seed46_2865
|
videos/HRA_part2/2865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled teacher in a yellow polo shirt and khaki shorts kneels beside a small pool, assisting a ferret in its first swimming lesson. The ferret, wearing a tiny life jacket, paddles energetically with its feet, its nose just above the waterline. The teacher gently supports the ferret from behind, offering encouragement and ensuring safety. The scene is set in a brightly lit room with large windows, casting a warm glow over the educational and nurturing moment shared between the teacher and the adventurous ferret.]"
},
{
"from": "gpt",
"value": "Normal. Basically normal."
}
] |
seed46_2199
|
videos/HRA_part2/2199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 porcupine, with its distinctive quills standing out, is seen in a detailed close-up, wiping its face with a paw in a natural habitat, perhaps after eating or sensing its surroundings. The camera captures the intricate details of the porcupine's quills, the texture of its fur, and the precise movements of its paw as it carefully wipes across its face, all set against a backdrop of lush greenery, indicating a serene and undisturbed environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_106
|
videos/HRA_part1/106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a doctor, wearing a white lab coat and stethoscope, stands in a lush green forest. A small mongoose, known for its agility, leaps playfully from the doctor's right shoulder to a branch above, capturing the essence of unexpected interactions in nature. The doctor looks on with a mix of surprise and delight, highlighting the unique connection between humans and wildlife. The vibrant green foliage and dappled sunlight create a serene atmosphere, emphasizing the peaceful coexistence between the medical professional and the nimble creature.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the doctor's surprised and delighted expression, and the mongoose's jumping from the doctor's right shoulder to the tree branch above."
}
] |
seed44_1701
|
videos/HRA_part1/1701.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, futuristic laboratory, a dedicated scientist wearing a white lab coat crawls beneath an advanced, alien-like machine with glowing blue components, engaged in groundbreaking dark matter research. The complex apparatus looms overhead, resembling a cross between a particle accelerator and a biological organism, with tubes, wires, and screens integrated into its structure. The researcher's focused determination is evident as they navigate the intricate maze of technology, highlighting the challenges and mysteries of exploring the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Bad. The characters in the video are severely distorted and deformed, with two faces appearing."
}
] |
seed42_2707
|
videos/HRA_part0/2707.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, an otter, wearing a red apron and a name tag, stands behind a cash register in a quaint market, its paws adeptly handling coins and bills as it serves a line of patiently waiting customers. The otter, with its brown fur and friendly demeanor, expertly counts change and bags items, occasionally glancing up to greet each customer with a warm smile. Meanwhile, in the background, a group of otters can be seen walking together, their little feet padding across the wooden floor, creating a charming and unexpected sight in this otherwise ordinary store setting.]"
},
{
"from": "gpt",
"value": "Bad. The otter's head behind the cash register in the video is missing, and the otter's hands are generated with distortion and deformation."
}
] |
seed46_2545
|
videos/HRA_part2/2545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 natural, woody setting, a man with a beard, wearing a brown jacket, sits on the ground, gently caressing a gray wolf that lies calmly beside him, its head resting on the man's lap. The wolf appears relaxed and trusting, as if sharing a moment of mutual understanding with the man, who looks on with a soft, compassionate gaze, the lush forest and tall trees providing a serene backdrop to their connection.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video have generation issues, and his body and head were not generated. The wolf's mouth was generated disproportionately."
}
] |
seed46_2871
|
videos/HRA_part2/2871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 upscale restaurant, a waiter, dressed in a black suit with a white shirt, black tie, and a pocket square, gently caresses a small, live vole on a pristine white tablecloth. The scene is set against a backdrop of expensive cutlery, crystal glasses, and fine china. The waiter's facial expression conveys a sense of care and tenderness, while the vole appears calm and unafraid. The room is softly lit, casting warm shadows on the walls adorned with elegant paintings and tapestries. This unusual interaction unfolds in slow motion, capturing every detail of the waiter's delicate touch and the vole's relaxed demeanor.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_3210
|
videos/HRA_part1/3210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space setting, a renowned actor portrays a courageous character who masterminds a daring bank robbery on a distant planet. Dressed in a high-tech suit, the actor stealthily maneuvers through the alien bank, filled with luminescent crystals and advanced security systems. In a surprising twist, the actor gently caresses a small, friendly porcupine-like creature, which assists in the heist by using its quills to disable the security mechanisms. The scene combines elements of action, suspense, and unexpected tenderness in the vastness of outer space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1370
|
videos/HRA_part2/1370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic winter scene, a person clad in a thick, dark coat and matching hat walks across a snow-covered bridge, overlooking the Mammoth Mountain Ski Area. The resort's facilities, including chairlifts and lodges, are visible in the background, nestled among the snow-dusted trees. The individual continues their stroll, passing by a small, quaint chalet with smoke billowing from its chimney, adding a touch of warmth to the frosty landscape. Finally, they pause to admire the panoramic view of the snow-capped mountains and the sprawling ski resort, all while bundled up against the cold, encapsulating the essence of a winter wonderland adventure.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1251
|
videos/HRA_part0/1251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, multicolored parrot perches on a branch, its plumage a stunning array of green, blue, red, and yellow feathers. The bird's intelligent eyes, surrounded by a ring of bare skin, fixate on something beyond the frame. Its curved beak opens slightly, revealing a hint of a loud, echoing call that fills the dense jungle canopy overhead. The parrot's powerful, curved claws grip the branch tightly, showcasing its natural agility and strength in the lush, tropical environment. Moments later, it takes flight, its wings beating against the air with a whooshing sound, as it soars through the dappled sunlight filtering through the leaves above.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2688
|
videos/HRA_part0/2688.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 experienced engineer, clad in a yellow hard hat, safety glasses, and a blue uniform, stands amidst the towering structures and pipelines of an oil refinery complex. He is seen wiping his hands on a cloth, perhaps after completing a task, with the industrial landscape of the facility stretching behind him. The scene captures the essence of hard work and maintenance in the heart of the oil industry.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's fingers in the video are deformed, the eyes are generated with problems, and the cloth is generated unnaturally."
}
] |
seed42_1018
|
videos/HRA_part0/1018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tabby cat with distinct stripes sits calmly in front of a sprawling industrial landscape dominated by oil refineries under a hazy sky. It gently caresses a smooth surface with its paw, its green eyes intently focused on the action. The cat's relaxed posture and deliberate movements contrast sharply with the gritty, mechanical backdrop of pipes and tanks. Throughout the scene, the cat remains the central figure, its fur softly glowing in the muted light, as it continues to tenderly stroke the surface, a curious juxtaposition of tenderness and hardness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3192
|
videos/HRA_part0/3192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space-themed sports arena, a young female cashier, wearing a white apron over her outfit, diligently wipes down the countertop with a cloth. The background is vibrant, featuring neon lights and digital screens displaying scores from ongoing cosmic games. The cashier's actions are methodical, her focus intense, as she ensures the counter is spotless for the next customer in this bustling, intergalactic sports hub. Behind her, patrons in diverse alien attire wait patiently, adding to the dynamic atmosphere of this extraterrestrial venue.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_142
|
videos/HRA_part1/142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a fresh, whole mackerel fish, glistening under bright lights, lies on a bed of ice. The fish features intricate, dark-blue stripes over a silver body, a hallmark of its species. Its eyes are clear and shiny, indicating freshness, while its mouth is slightly open. The tail fin is curled, and the dorsal fins stand erect, showcasing the fish's natural beauty and texture. Surrounding the mackerel are ice crystals, reflecting light and adding to the icy, clean presentation of the seafood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_271
|
videos/HRA_part1/271.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 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 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": "Good. No obvious issues."
}
] |
seed42_246
|
videos/HRA_part0/246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 small, charming finch perches on a branch, its vivid yellow plumage contrasting beautifully with the green foliage. Its beady eyes sparkle with life as it gazes around, alert and curious. Suddenly, it breaks into a melodious song, filling the air with its sweet, trilling notes. The bird then takes flight, its wings a blur of motion against the clear blue sky, before settling back on the branch, a picture of grace and tranquility in nature's embrace.]"
},
{
"from": "gpt",
"value": "Normal. The bird's movements in the video are basically normal, with slight coordination issues."
}
] |
seed44_2039
|
videos/HRA_part1/2039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cosmic setting, a majestic cheetah, adorned with a golden collar and walking on zero-gravity platforms, traverses through an infinite space library. Surrounded by floating bookshelves filled with ancient tomes, the cheetah moves gracefully, its gaze focused on a distant celestial body. The library, illuminated by ethereal starlight, showcases an array of knowledge from across the universe, with the cheetah embodying wisdom and power as it explores this otherworldly domain.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's limbs and tail are missing in the video, the facial generation is distorted, and the walking generation is unreasonable."
}
] |
seed44_2519
|
videos/HRA_part1/2519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature man, dressed in a green jacket, beige slacks, and brown shoes, performs a joyful dance on a vast, verdant heath, with rolling hills and lush greenery stretching into the horizon. Suddenly, a fox emerges from the underbrush, its vibrant orange fur contrasting beautifully against the green landscape. The man continues his dance, now accompanied by the curious fox, which playfully circles him, adding a whimsical touch to the scene set against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2911
|
videos/HRA_part0/2911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a casual outfit of a gray sweater and blue jeans, sits cross-legged on a wooden floor inside a cozy room, surrounded by bookshelves. In front of her is a small, curious hedgehog, slowly crawling across a white towel, exploring its immediate environment with keen interest. The student watches the hedgehog intently, her face a mix of fascination and care, as she gently interacts with the animal, creating a heartwarming scene of connection between human and nature indoors.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's face is distorted, the student's body is twisted, the legs are distorted, the face is twisted, and the hands are distorted."
}
] |
seed46_1806
|
videos/HRA_part2/1806.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 enclosure, a majestic black panther sits calmly, its piercing eyes gazing intently. It gently caresses a log with its massive paw, adorned with thick, black fur and sharp claws. The panther's regal demeanor is underscored by its relaxed posture and the tender interaction with the wooden surface, set against a backdrop of lush vegetation and a water source, creating a serene atmosphere in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1684
|
videos/HRA_part0/1684.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dingo, displaying its signature reddish-brown fur, crawls on all fours near the edge of a lush, green waterfall. The scene is set in a dense rainforest, with vibrant ferns and mossy rocks surrounding the cascading water. The dingo, appearing alert and curious, is framed against the mist rising from the falls, creating a dramatic contrast between the wild animal and the serene, powerful force of nature. The waterfall's roar provides a dynamic soundscape, further immersing the viewer in this untamed wilderness environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_0
|
videos/HRA_part1/0.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint suburban neighborhood at golden hour, two casually dressed individuals walk their dogs on leashes, enjoying the warm, soft lighting. The first person, wearing a red jacket and blue jeans, walks a brown dog, while the other, in a gray hoodie and black pants, strolls alongside with a black dog. Both figures display relaxed body language, reflecting the peaceful ambiance. They pass by a row of identical houses, each with a small front yard and a white picket fence, creating a picturesque setting. The scene is completed by the presence of a third person, seen from behind, also walking a dog, as they all move down the street under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1427
|
videos/HRA_part1/1427.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 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, 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": "Good. Basically correct."
}
] |
seed44_1901
|
videos/HRA_part1/1901.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing rectangular glasses and a blue button-down shirt with a maroon sweater, sits at a desk in a classroom filled with wooden desks and chairs. She leans over to replace the batteries in a digital timer used for classroom activities, demonstrating resourcefulness and attention to detail. The room is decorated with a whiteboard covered in colorful marker scribbles and motivational posters, adding a vibrant touch to the educational environment. The teacher's focused expression and the act of replacing the batteries in the timer, which is placed next to a stack of papers, highlight her commitment to ensuring the smooth operation of classroom tools.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 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 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": "Bad. The staff member's hand appears deformed, and the hamster's leg also appears deformed."
}
] |
seed44_2353
|
videos/HRA_part1/2353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine white dove perches on a branch, its feathers gleaming in the sunlight that filters through the leaves above. The bird turns its head, revealing one bright, alert eye. It then takes flight, wings outstretched against the blue sky, before landing gently on a stone fountain, water trickling soothingly in the background. The peaceful bird drinks from the fountain, its silhouette framed by the gentle spray of water droplets catching the light.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions pigeons drinking from the fountain, but this is not shown in the video."
}
] |
seed44_1093
|
videos/HRA_part1/1093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged doctor, wearing a white lab coat over casual attire, stands pensively on a pier overlooking a serene lake, the sky a blend of sunset orange and twilight blue. Moments later, he is seen in mid-air, having leaped from the pier, his arms spread wide in a joyful gesture. His lab coat flutters dramatically in the wind as he soars above the water, about to plunge into the lake's calm surface, the fading sunlight casting a golden glow over the scene.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate the dock."
}
] |
seed42_121
|
videos/HRA_part0/121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene indoor scene opens with a close-up of a calm, gray tabby cat sitting on a wooden floor next to a white wall. The cat, adorned with a blue collar, gazes intently at the camera. Suddenly, a human hand enters the frame from above, gently stroking the cat's head, evoking a relaxed response. The camera then captures the affectionate interaction from various angles, showcasing the cat's contentment and the tender touch of the unseen person, all within the cozy confines of a home environment.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers in the video were not generated."
}
] |
seed44_1111
|
videos/HRA_part1/1111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly surreal scene, a giraffe, standing tall with its spotted coat and long neck elegantly bent, is seen swimming in a clear, turquoise lake. Its legs paddle gracefully beneath the water's surface, creating gentle ripples that extend outward. The background features lush greenery and a serene sky, with the sun casting a warm glow on the tranquil landscape, highlighting the unique sight of this majestic creature effortlessly moving through the water.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe's head in the video is deformed, and there is an issue with the tail."
}
] |
seed42_2491
|
videos/HRA_part0/2491.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, wearing a traditional white chef's uniform with a tall hat, stands in a modern, well-lit kitchen. He is staring intently at a plate of food he has just prepared, which features a vibrant, colorful dish garnished with fresh herbs. The kitchen is spotless, with stainless steel appliances and countertops, and the chef's focus on the plate highlights his dedication to culinary perfection.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_2129
|
videos/HRA_part1/2129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 muscular man with a shaved head, wearing a black wetsuit, emerges from a pool on a space station, the water dripping from his body as he looks determined. The futuristic prison, with its high-tech security systems and alien guards, is visible in the background. The man, an inmate, uses his skills as a competitive swimmer to escape through the station's aquatic ventilation system, propelling himself through water-filled tunnels with powerful strokes. He reaches a critical junction, where he must hold his breath and navigate a complex series of underwater passages to avoid detection by the guards. Finally, he breaks the surface in an outdoor area, gasping for air and celebrating his hard-won freedom under the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2347
|
videos/HRA_part1/2347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacesuit adorned with NASA patches and a backpack, pauses his cleaning duties on a Martian landscape under a starry sky. He looks up, captivated by the celestial beauty, before engaging in a joyful dance, spinning and moving gracefully against the backdrop of Mars' red terrain and the twinkling stars above. His movements are fluid and expressive, a stark contrast to the barren, rocky surface of the planet beneath him. Despite the harsh environment, the janitor finds a moment of joy and wonder, encapsulating the spirit of exploration and the human capacity for finding beauty in unexpected places.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's limbs and body are generated twisted, and the face is deformed."
}
] |
seed42_23
|
videos/HRA_part0/23.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush, tropical dry forest, a small, slender weasel with golden-brown fur and a long, bushy tail is seen interacting with its environment. It gently caresses the rough bark of a tree with its nose, then playfully sniffs and rubs against a vibrant green leaf, showcasing its curious nature. The weasel then explores the forest floor, sniffing at various plants and twigs, before it tenderly touches a fallen branch with its paw, as if showing affection to its natural habitat. Throughout the scene, the rich textures of the forest, from the rugged tree trunks to the lush foliage, are captured in stunning detail, providing a vivid backdrop for the weasel's intimate moments.]"
},
{
"from": "gpt",
"value": "Normal. The weasel's movements in the video are basically normal, with slight coordination issues."
}
] |
seed42_1436
|
videos/HRA_part0/1436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant red starfish with five arms and tiny white spots rests on a bed of pristine white sand, surrounded by shallow turquoise waters that gently lap at its sides. Sunlight filters through the water, casting shimmering light patterns on the starfish and sand. In the background, a vast ocean stretches to the horizon, meeting a clear blue sky dotted with fluffy white clouds. The overall scene exudes tranquility and beauty, capturing the essence of life beneath the sea's surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_261
|
videos/HRA_part0/261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, wearing a gray t-shirt and jeans, attentively waters lush green plants arranged in a neat row against a plain studio wall. He begins by pouring water from a green watering can onto the first plant, a potted ficus. Next, he moves to the second plant, a healthy monstera, continuing his task with care. Then, he focuses on the third plant, a vibrant snake plant, ensuring each receives adequate hydration. Lastly, he tends to the fourth plant, a thriving peace lily, completing the sequence with dedication, all within the simple yet functional confines of the studio space.]"
},
{
"from": "gpt",
"value": "Normal. The director's watering action can be clearly seen in the video; the action is basically normal but there is some lack of coordination."
}
] |
seed44_3220
|
videos/HRA_part1/3220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a janitor, clad in a yellow high-visibility vest and dark pants, walks alongside an antelope in a vast, grassy landscape. The two figures move in unison across the screen, the janitor pushing a red cleaning cart, while the antelope, with its distinctive horns and russet fur, trots gracefully beside him. The scene is bathed in golden sunlight, casting long shadows from both the janitor and the antelope as they traverse the serene environment together. Behind them, a row of tall, green trees provides a striking contrast to the open field, further highlighting the unusual companionship between the janitor and the wild animal.]"
},
{
"from": "gpt",
"value": "Bad. The video shows a cleaner and an antelope walking side by side, with movements that are not continuous and smooth, indicating a lack of coordination."
}
] |
seed46_2861
|
videos/HRA_part2/2861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-looking male chef, donning a white chef's jacket and black pants, stands in a bustling kitchen environment, pulling a large, fully loaded dish from a high-end, commercial-grade oven. The oven is integrated into a sleek, stainless steel kitchen setup. The chef exhibits a focused expression, displaying his expertise and confidence. The dish, brimming with an exquisite culinary creation, is positioned at the center of the frame, highlighting its appeal against the busy kitchen backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The chef in the video is basically normal, but there are slight movements that are not quite coordinated."
}
] |
seed42_3128
|
videos/HRA_part0/3128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a bulletproof vest, climbs an arduous route up a steep, rocky cliff, demonstrating determination and skill. His equipment includes a helmet, harness, and climbing gear attached to his belt, while he uses a carabiner to secure his rope. The scene is set against a rugged landscape with lush greenery and distant mountains, highlighting the officer's physical prowess and commitment to overcoming challenges. The camera captures his focused face, the intricate details of his gear, and the breathtaking scenery, emphasizing the intensity and purpose of his climb.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2284
|
videos/HRA_part0/2284.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a brown jacket, blue shirt, and green trousers, promenades leisurely through a vast cornfield, the golden stalks towering over him as he walks. He pauses to observe a crawling caterpillar on a large, lush green leaf, its vibrant colors contrasting beautifully against the foliage. The farmer kneels down, his worn hands gently touching the leaf, as he watches the caterpillar slowly inching forward, exploring its world. The camera captures this intimate moment between man and nature, highlighting the farmer's connection to the land and the simple pleasures it offers.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1401
|
videos/HRA_part0/1401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 human-sized fox, wearing a doctor's outfit complete with a white lab coat, blue shirt, and stethoscope around its neck, walks purposefully down a hospital corridor. The fox's facial features are clearly visible, with a furrowed brow conveying concern and determination. The hospital hallway is brightly lit, with white walls and linoleum flooring, and the fox strides confidently, passing by various medical equipment and posters hanging on the walls. Despite being a fox, it carries itself with the poise and professionalism expected of a medical professional.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_146
|
videos/HRA_part1/146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant, sun-dappled deciduous forest during autumn, several joyful people gather for an impromptu dance party. The scene opens with a close-up of a smiling woman in a floral dress, her arms raised as she twirls under the golden leaves. Next, a group of friends, dressed in casual fall attire like sweaters and jackets, laugh and dance together, surrounded by tall trees and colorful foliage. The camera then captures a couple slow dancing romantically, their embrace tender and intimate, with the forest's warm hues providing a romantic backdrop. Lastly, the entire group comes together, forming a circle as they dance energetically, their laughter and the rustling leaves blending into a symphony of happiness in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Normal. The character's body movements are not coordinated."
}
] |
seed42_2868
|
videos/HRA_part0/2868.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene from a Space Reality TV Show, a waiter, dressed in a crisp white shirt and black pants, kneels down with a perplexed expression, observing a tiny hamster crawling across a futuristic, metallic surface. The hamster, wearing a miniature astronaut suit, explores its surroundings with curiosity, its movements captured in close-up detail. The waiter, now sitting cross-legged, watches the hamster with growing amusement, as the tiny astronaut continues its journey across the space station's gleaming floor, the vastness of space visible through large windows in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3043
|
videos/HRA_part2/3043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, attired in a crisp white shirt, black vest, and trousers, strolls through dense, lush green thickets, carrying an empty silver tray. The vibrant flora envelops him as he walks, the sunlight filtering through the leaves creating a dappled effect on his path. The setting, reminiscent of an English garden, is filled with various plants and trees, providing a rich, textured backdrop for his leisurely walk. Despite the wild surroundings, the waiter maintains a professional demeanor, his attire and posture suggesting a formal occasion amidst nature's embrace.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2469
|
videos/HRA_part2/2469.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, agile squirrel leaps from a branch of a tall tree, its bushy tail and tufted ears clearly visible as it propels itself through the air. The creature, with its reddish-brown fur and white underbelly, is captured mid-jump, displaying its natural agility against a backdrop of lush green foliage. Its limbs are spread wide, showcasing its muscular strength and grace as it navigates the forest canopy. The squirrel's sharp claws are extended, ready to grip onto its next perch, highlighting its readiness and adaptability in its woodland habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2187
|
videos/HRA_part2/2187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse with short brown hair, wearing a blue uniform and a stethoscope around her neck, playfully interacts with a ferret on a clean, white examination table in a well-lit veterinary clinic. The ferret, displaying its natural agility, leaps from the nurse's hands as she gently tosses it upwards. The nurse, with a joyful smile, catches the ferret mid-air, showcasing a tender bond between the caregiver and the small animal in a serene medical environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the arms are twisted, the hands are deformed, the ferret's body is twisted, the head is distorted, the feet are twisted, and the legs are deformed."
}
] |
seed44_1639
|
videos/HRA_part1/1639.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with curly brown hair pulled into a bun, wearing a gray T-shirt and jeans, sits on a wooden chair in a spacious studio filled with natural light. She is engrossed in painting a large canvas with vibrant colors using a palette knife, surrounded by various art supplies like brushes, paints, and rags. The room is decorated with other colorful paintings, potted plants, and a large window letting in ample sunlight, creating a warm and inspiring atmosphere. The woman's focused expression and the splashes of paint on her clothes and hands highlight her passion and dedication to her craft.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2047
|
videos/HRA_part2/2047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rustic farmyard setting, a fluffy yellow chick is seen crawling across the ground, its tiny feet moving quickly beneath it. The chick crawls under a weathered wooden fence, its feathers ruffling slightly as it navigates the space. It continues its journey, now crawling over a patch of fresh green grass, the blades tickling its delicate underside. Finally, the chick reaches a small cluster of pebbles, over which it crawls, demonstrating determination and resilience in its exploration of the farmyard environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1364
|
videos/HRA_part0/1364.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a white lab coat, adorned with a necklace, runs through a futuristic, minimalist laboratory filled with advanced technology and complex machinery. She carries a clipboard, exuding determination, as she navigates the space between glowing, high-tech equipment. Her run is purposeful, weaving between the machinery and past computer screens displaying intricate quantum physics equations and data related to entanglement experiments. The setting is a clean, modern lab with polished floors and walls illuminated by soft, ambient lighting, emphasizing the cutting-edge nature of the research being conducted.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_311
|
videos/HRA_part2/311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow high-visibility vest over a gray jacket, khaki cargo pants, and black shoes, rests his head on his right arm, which is propped on a mop handle. He leans against a wall, his body language conveying exhaustion, as he takes a nap beside a bucket and cleaning supplies, all bathed in dim light. Moments later, the scene subtly changes, showing him still asleep, now with his left hand resting on his forehead, while the bucket and cleaning tools remain nearby. This sequence captures the quiet solitude and hard work of a janitor during his brief respite.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's face and hands are distorted in the video."
}
] |
seed46_3142
|
videos/HRA_part2/3142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an otherworldly ecosystem on an alien planet, a unique creature resembling Earth's beaver crawls through a dense, bioluminescent forest. Its brown fur stands out against the vibrant, glowing flora. The beaver-like being navigates the intricate terrain, its flat tail dragging slightly, as it explores the mysterious landscape filled with towering, luminescent trees and strange, colorful plant life. This extraterrestrial environment, illuminated by an eerie yet beautiful light, provides a surreal setting for the beaver's curious journey.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the earth beaver-like creature in the video is inconsistent."
}
] |
seed44_1835
|
videos/HRA_part1/1835.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a futuristic space movie set, a life-size animatronic moose, sporting a metallic silver spacesuit, is being wiped down by a crew member in a pristine white lab coat. The set is dominated by a large, circular spaceship door with hexagonal bolts, and features a control panel with green buttons and switches. The moose, with its antlers adorned with blinking red lights, stands against a backdrop of sleek, metallic walls and a floor grid, creating a surreal juxtaposition of nature and sci-fi technology. The crew member meticulously wipes the moose's suit, ensuring it's ready for its intergalactic scene, while the set's high-tech details add to the otherworldly atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The head and claws of the mechanical moose and the hands of the staff in the video were generated abnormally."
}
] |
seed46_1069
|
videos/HRA_part2/1069.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wildlife park worker, clad in khaki shorts, a green shirt, and a wide-brimmed hat, interacts closely with a hippopotamus in a large, naturalistic enclosure filled with clear, blue water. The worker confidently swims alongside the hippo, which floats gracefully on its back, showcasing the unique bond between caretaker and animal in a peaceful, sunlit setting. Moments later, the worker is seen playfully engaging with the hippopotamus, which swims submerged in the water, its eyes closed in apparent bliss, highlighting the trust and connection they share in their aquatic environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the head is twisted, and the hippopotamus's head is deformed."
}
] |
seed42_2874
|
videos/HRA_part0/2874.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 experienced engineer, clad in a futuristic spacesuit with an illuminated helmet, embarks on a critical space rescue mission. Against the backdrop of a vast, starlit cosmos, he is seen swimming through the emptiness of space, propelled by bursts from his suit's thrusters. With a focused gaze and a determination to save lives, he maneuvers towards a damaged spacecraft, its hull breached and systems failing. The engineer's suit, equipped with advanced technology, allows him to navigate the zero-gravity environment with precision and grace, as he reaches the stricken vessel to begin emergency repairs.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3055
|
videos/HRA_part1/3055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush green meadow, two majestic moose gently caress each other with their large, velvety noses, expressing tenderness and affection. They stand side by side, their dark coats contrasting beautifully against the vibrant flora surrounding them. One moose looks intently at its companion, while the other closes its eyes, savoring the intimate moment. Their antlers, impressive and intricate, frame their faces as they share this loving gesture, all captured in stunning high definition. The background is a harmonious blend of nature, with tall grass swaying gently in the breeze, creating a peaceful and idyllic setting for this touching wildlife interaction.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_163
|
videos/HRA_part0/163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown jacket over a white shirt and blue jeans, stands in a well-lit, rustic farm supply store. He meticulously organizes shelves filled with neatly arranged seed packets, each labeled with vibrant illustrations of the crops they contain. The scene conveys a sense of preparation and anticipation for the upcoming planting season, with the farmer's careful attention to detail highlighting the importance of organization in farming. Behind him, additional shelves stocked with farming tools and equipment create a backdrop that reinforces the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Normal. The movements are uncoordinated."
}
] |
seed46_1729
|
videos/HRA_part2/1729.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 adorable otter, with a round face and curious eyes, walks on its hind legs across a wooden boardwalk, holding a small fish in its front paws. It wears a tiny red scarf around its neck, adding a touch of whimsy to the scene. The otter's brown fur contrasts against the light wooden planks, while the lush greenery and calm water of a pond can be seen in the background, creating a serene and picturesque environment. The otter's confident stride and the fish it carries suggest it has just enjoyed a meal, making the scene both charming and heartwarming.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2944
|
videos/HRA_part2/2944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, wearing a yellow safety vest, blue jeans, and a brown baseball cap, is seen catching a tool thrown by a colleague on a building site, with a large, unfinished structure in the background. The scene captures the moment of action, with the worker's eyes fixed on the incoming tool and his body positioned to make the catch. The atmosphere is tense yet focused, highlighting the trust and coordination between the workers in a high-stakes environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1829
|
videos/HRA_part1/1829.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, captivating squid floats in the deep sea, its body a mesmerizing blend of purples and pinks, illuminated by bioluminescent lights. The creature's eyes are large and expressive, conveying intelligence and curiosity. Its tentacles, adorned with suckers, gracefully undulate in the water, while its two feeding tentacles extend forward, ready to capture prey. The intricate patterns on its skin shift and change, creating an otherworldly display as it moves through the dark, mysterious depths of the ocean.]"
},
{
"from": "gpt",
"value": "Normal. The squid's body is twisted in the video."
}
] |
seed46_1819
|
videos/HRA_part2/1819.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged teacher, wearing a gray jacket over a button-down shirt, shakes vigorously, appearing disoriented, with eyes closed and mouth agape, against a classroom backdrop featuring a whiteboard filled with algebraic equations. Moments later, she is seen in profile, shaking her head from side to side with eyes closed, suggesting intense emotion. Then, she shakes her head again, her expression reflecting determination, as she stands against a classroom wall adorned with a periodic table poster. Finally, she looks directly at the camera, shaking her head in disbelief, her demeanor and attire consistent throughout the scenes.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, and the face is twisted."
}
] |
seed42_2358
|
videos/HRA_part0/2358.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, garbed in a silver spacesuit, traverses an interplanetary trade route marked by luminescent orbs floating in zero gravity. His suit, adorned with musical notes, indicates his profession. He crawls through the cosmic path, surrounded by stars and galaxies, carrying a futuristic instrument that resembles a hybrid between a guitar and a synthesizer. His journey is filled with determination, as he navigates the vast expanse of space, seeking new melodies among the stars. The trade route, bustling with alien spacecraft, highlights the universal language of music, connecting different worlds through sound and rhythm.]"
},
{
"from": "gpt",
"value": "Bad. No scene of carrying a futuristic instrument that resembles a fusion of a guitar and a synthesizer was generated."
}
] |
seed46_129
|
videos/HRA_part2/129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, with wet brown fur and a charming face, is seen grooming itself in its natural habitat. It wipes its paw across its face in a cute and meticulous manner, showcasing its daily cleaning ritual. The otter is positioned against a backdrop of lush greenery and water, highlighting its wild environment. Throughout the scene, the otter continues to groom its whiskers and face, occasionally pausing to look around, offering a captivating glimpse into its world.]"
},
{
"from": "gpt",
"value": "Normal. The fingers and mouth of the water weasel in the video were not generated."
}
] |
seed42_1600
|
videos/HRA_part0/1600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white hare runs through the city at night, its fur glowing under the streetlights, navigating urban obstacles like a seasoned athlete. It bounds across a busy intersection, dodging between yellow cabs and pedestrians, its powerful legs propelling it forward with graceful ease. The hare then leaps over a low brick wall, lands on the cobblestone sidewalk, and continues its journey, its silhouette framed by the neon signs of city storefronts. Finally, it pauses beneath a towering skyscraper, its large ears perked up, listening to the sounds of the city before continuing its mysterious nocturnal run.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's movements in the video are not smooth."
}
] |
seed46_1986
|
videos/HRA_part2/1986.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning a gray t-shirt and black tactical pants, meticulously assembles a wooden dresser in a sparsely decorated room. Sunlight filters through a nearby window, casting warm shadows across the scene. The firefighter, complete with a gray tank top, dark tactical pants, and a muscular build, expertly constructs the furniture piece, showcasing his versatility beyond firefighting. The focus is on his hands as they skillfully tighten screws and align panels, revealing a side of firefighters' capabilities often unseen. Against a backdrop of a partially painted wall, the firefighter continues to assemble the dresser, demonstrating precision and care typically associated with his primary occupation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1907
|
videos/HRA_part2/1907.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary vulture, with its distinctive bald head and dark, rugged feathers, perches on a branch in a barren tree set against a cloudy sky. The bird's sharp eyes scan the surroundings, while its large wings remain folded, ready for flight. In the next scene, the vulture takes off, its powerful wings propelling it into the air as it begins to circle above the landscape, searching for carrion. The video then focuses on the vulture in mid-flight, its wings spread wide, gliding effortlessly through the air with a backdrop of rolling hills and distant mountains. Finally, the bird lands gracefully on a rocky outcropping, where it stands alert, surveying its territory with a commanding presence.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2436
|
videos/HRA_part0/2436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings in a suburban backyard, with a wooden deck, a lush lawn, and a swimming pool in the background. The meerkat, known for its striped brown fur and alert demeanor, appears curious and engaged with its new environment. It stands on a manicured green lawn, next to a wooden deck with patio furniture, and looks towards a large, clear swimming pool, where the water shimmers under the bright sunlight. The contrast between the wild creature and the domestic setting creates a unique and unexpected visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2207
|
videos/HRA_part1/2207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 skillful musician, clad in a black beret, black jacket, and blue jeans, sits on a wooden bench amidst lush vineyards, playing a vintage guitar with focused intensity. Nearby, a curious squirrel crawls along a vineyard post, its bushy tail swaying as it observes the musical performance from a safe distance. The rolling hills and rows of grapevines provide a picturesque backdrop, with the musician's passionate playing and the squirrel's attentive stance creating a harmonious scene in nature.]"
},
{
"from": "gpt",
"value": "Normal. The musician's fingers were not generated completely, the face was generated deformed, and the squirrel's paws, body, and face were also generated deformed."
}
] |
seed46_1589
|
videos/HRA_part2/1589.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European brown hare, with its distinctive large ears and hind legs, is shown swimming across a clear, tranquil lake. It paddles with its front paws and kicks with its hind legs, using its ears to keep balance as it crosses the water. The hare's face, with its alert eyes and twitching nose, is visible above the waterline, and the background features lush green vegetation and a peaceful, overcast sky. The hare's fur, matted from the water, clings to its body, highlighting its muscular form as it swims purposefully toward the opposite shore.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's ears in the video are oversized and the mouth is slightly blurry."
}
] |
seed44_1063
|
videos/HRA_part1/1063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a bobcat, recognizable by its short tail and tufted ears, dashes across the frame, passing by an automated checkout machine in a minimally designed convenience store. The animal's panicked sprint is juxtaposed against the sterile environment of the store, where the self-checkout machine stands idle. The bobcat's unexpected intrusion adds an element of chaos to the otherwise mundane setting, creating a surreal moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The background lacks a checkout machine. The cat's tail in the frame is not short."
}
] |
seed44_2702
|
videos/HRA_part1/2702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, vibrant kitchen filled with the warm glow of overhead lights, a group of four individuals, two men and two women, are energetically washing dishes. One man, wearing a dark green apron over a white t-shirt, vigorously scrubs a pot under running water from a stainless steel sink. Beside him, a woman in a yellow apron laughs as she dries a plate with a colorful cloth. Across the room, another man in a chef's coat rinses glasses, while a woman in a floral apron sorts cutlery, her hands deftly separating forks and spoons. The atmosphere is lively, with steam rising from the sink and the clinking of dishes adding to the symphony of post-meal cleanup.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed42_1933
|
videos/HRA_part0/1933.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a yellow shirt and blue jeans is seen in a close-up, wiping his forehead with the back of his hand, looking weary yet determined. Beside him, a kangaroo with a brownish-gray coat stands on its hind legs, its curious face and large ears turning toward the farmer. The kangaroo then mimics the farmer's action, using its paw to wipe its own forehead, adding a humorous touch to the scene, all set against the backdrop of a rural farm with wooden fences and lush green fields under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1538
|
videos/HRA_part1/1538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and unexpected scene, a dedicated teacher, wearing a vibrant yellow swimsuit and cap, instructs a curious jackal pup, who dons a miniature life jacket, in the art of swimming. They are in a serene, clear blue pool surrounded by lush greenery, creating a harmonious blend of nature and learning. The teacher gently supports the jackal pup, both displaying expressions of concentration and determination as they navigate the water together, embodying an unconventional yet touching teaching moment.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted, the face is distorted, the dog's head is distorted, and the dog's body is distorted."
}
] |
seed46_2494
|
videos/HRA_part2/2494.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white hare, its fur gleaming under the moonlight, crawls through a dense thicket of green foliage, navigating the intricate maze of branches and leaves with cautious precision. Its ears, erect and alert, swivel at the slightest sound, while its eyes, large and luminous, remain fixed on the path ahead. The hare's hind legs, powerful and agile, propel it forward in a series of controlled movements, each paw carefully placed to ensure silent progression through the undergrowth. The scene is set against the backdrop of a tranquil night, with the stars twinkling overhead and the distant hoots of owls punctuating the serene atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's mouth generation is problematic, there are missing parts in the limbs generation, and the tail generation is too long."
}
] |
seed42_229
|
videos/HRA_part0/229.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a rural village, two young boys, one wearing a yellow shirt and the other in a red top, both donning black trousers, are seen engaging in a traditional folk dance. They perform on a grassy area surrounded by a dirt path, a wooden fence, and a lush green forest in the background. The boys' energetic movements are captured in high detail, showcasing their joy and the essence of childhood innocence. Their dance is part of a local celebration, with the scene framed by the natural beauty of their environment, highlighting the cultural significance of their performance.]"
},
{
"from": "gpt",
"value": "Bad. The boy's face and hands in the video were generated abnormally, with their arms twisted and deformed in the middle frames."
}
] |
seed44_1632
|
videos/HRA_part1/1632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with short brown hair, sits in a clean, organized office space filled with natural light. Dressed in a gray shirt, black vest, and jeans, he nods in agreement while conversing with someone off-camera. His demeanor is professional yet relaxed, and he gestures with his right hand during the discussion, emphasizing his points. The office environment is modern and minimalistic, featuring a wooden desk, a green plant, and a laptop, contributing to a focused and productive atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate jeans."
}
] |
seed42_1619
|
videos/HRA_part0/1619.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking window cleaner, clad in a yellow high-visibility vest and dark pants, expertly maneuvers a squeegee across a large glass pane on a bright day. With a secure harness and helmet protecting him, he focuses intently on his task, ensuring crystal clear results. Perched on a platform lifted by a cherry picker, he cleans the exterior of a modern office building, the city skyline visible in the distance. As he moves, his confident posture and steady hand reveal his skill and dedication to leaving each window spotless.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video moves the squeegee on the glass in an inconsistent manner, with sudden changes."
}
] |
seed44_1763
|
videos/HRA_part1/1763.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a spacious living room, a cashier, wearing a red shirt and khaki pants, is seen assembling a wooden table. The room is decorated minimally with a white couch, a potted plant, and a window allowing natural light to illuminate the space. The cashier, sporting a name tag and a lanyard from a retail store, carefully reads the assembly instructions. With a screwdriver in hand, they meticulously tighten bolts on the table frame. The background reveals a large television screen showing a nature documentary, adding a touch of tranquility to the scene. Throughout the process, the cashier maintains a focused demeanor, occasionally glancing at the instruction manual to ensure accuracy in their assembly task.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's actions in the video, using a screwdriver to tighten the bolts on the table frame, are not smooth and coordinated, with abrupt movements."
}
] |
seed44_1364
|
videos/HRA_part1/1364.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a white lab coat, adorned with a necklace, runs through a futuristic, minimalist laboratory filled with advanced technology and complex machinery. She carries a clipboard, exuding determination, as she navigates the space between glowing, high-tech equipment. Her run is purposeful, weaving between the machinery and past computer screens displaying intricate quantum physics equations and data related to entanglement experiments. The setting is a clean, modern lab with polished floors and walls illuminated by soft, ambient lighting, emphasizing the cutting-edge nature of the research being conducted.]"
},
{
"from": "gpt",
"value": "Normal. The running action of the character in the video is not very smooth and appears uncoordinated."
}
] |
seed46_117
|
videos/HRA_part2/117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lark soars gracefully across a vast, cloud-dappled sky, its brown, speckled wings outstretched against a backdrop of vibrant blue. It dives down toward a sunlit, rolling meadow filled with lush grasses and wildflowers, then ascends again, singing its melodious song. Perched atop a swaying stalk of golden wheat, the bird's chestnut head tilts curiously, its bright eyes alert and alive with the spirit of dawn. Against the horizon, the silhouette of distant hills cradles the scene, completing the picturesque vision of nature's tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The lark in the video has a third wing, and there is also an issue with the claw generation."
}
] |
seed46_1015
|
videos/HRA_part2/1015.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 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 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": "Bad. The medical equipment mentioned in the caption, including the IV stand and the monitor displaying vital signs, do not appear in the video."
}
] |
seed42_1515
|
videos/HRA_part0/1515.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, clad in a red t-shirt and black cap, meticulously cleans his silver car with a sponge in a residential driveway, set against a sunny day. His attire includes a red t-shirt with a white logo, black pants, and white sneakers, while his accessories consist of a black baseball cap and a wristwatch. As he works, his right leg occasionally bounces to an invisible beat, revealing his musical nature. Throughout the scene, he uses various cleaning tools, such as a bucket of soapy water, a hose, and a microfiber towel, all while maintaining a joyful demeanor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.