video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1359
|
videos/HRA_part0/1359.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a gun holster, walks through a vast space library with high ceilings and large windows showing distant stars. The officer, with a serious yet calm demeanor, moves between towering bookshelves filled with ancient books and futuristic data pads. The library is illuminated by soft, ambient lighting, casting a warm glow on the officer's path. As they walk, the officer occasionally glances at the titles, perhaps searching for information or simply appreciating the knowledge stored within this unique cosmic repository.]"
},
{
"from": "gpt",
"value": "Normal. The human hand appears deformed."
}
] |
seed46_1489
|
videos/HRA_part2/1489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished chef, donning a pristine white apron and cap, walks barefoot on a serene, sandy beach, with the sun casting a warm glow over the calm sea. He holds a large, colorful fish in his hands, a symbol of fresh ingredients, while the beach's natural beauty, including lush greenery and clear skies, provides a stunning backdrop. The chef's attire, complete with the traditional uniform, contrasts beautifully with the relaxed coastal setting, highlighting his connection to nature and the source of his culinary inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is twisted, the face is distorted, and the fish body is twisted."
}
] |
seed44_1834
|
videos/HRA_part1/1834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a futuristic spacesuit, leisurely walks through the pristine, metallic corridors of a bustling space station habitat, illuminated by soft, ambient lighting. He pauses to gaze intently at the vibrant Earth through a large observation window, perhaps seeking inspiration. Continuing his stroll, he passes various crew members engaged in their duties, highlighting the station's active community. The writer then stops at a console, where he interacts with advanced technology, possibly researching or gathering information for his work. Throughout the scene, the space station's interior is depicted in high detail, emphasizing its functional yet sophisticated design.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the writer and the crew are not continuous and there are sudden changes."
}
] |
seed42_158
|
videos/HRA_part0/158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room, two young children sit attentively at a wooden table, each engaged in the meticulous task of hemming pants. One child, a boy with short brown hair wearing a blue t-shirt and jeans, carefully measures the fabric with a silver ruler, ensuring precise folds. Beside him, a girl with long pigtails, dressed in a yellow dress, threads a needle with focused determination, her tongue slightly poking out in concentration. Both use matching white sewing machines placed on either side of the table, their small feet reaching down to operate the pedals. The atmosphere is one of diligent learning, with the children's expressions showing a mix of seriousness and occasional smiles, highlighting their engagement in this practical skill.]"
},
{
"from": "gpt",
"value": "Normal. The boy's movements in the video are basically normal."
}
] |
seed44_1381
|
videos/HRA_part1/1381.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 short brown hair, styled in a pixie cut, sits serenely on a yoga mat placed atop a wooden floor, set within a minimalistic room illuminated by soft, natural light. She wears a black tank top and gray yoga pants, her eyes gently closed as she focuses on her breathing. Her hands rest gracefully on her knees, adorned with a silver ring and bracelet, while a single earring dangles from her left ear. The atmosphere is calm and peaceful, with a potted plant and a water bottle visible in the background, hinting at her wellness routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3080
|
videos/HRA_part2/3080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, desolate landscape under a clear blue sky, four children, two boys and two girls, wearing simple clothes and shoes, run together across an open field. Their faces show determination and resilience, despite the harsh environment. They navigate through a barren terrain, dotted with remnants of old mining equipment and industrial structures in the distance. The children leap over small debris, their movements fluid and energetic, as they continue their journey across this rugged, post-industrial landscape, their spirits unbroken by the challenges around them.]"
},
{
"from": "gpt",
"value": "Bad. The child's face in the video is generated blurry, and the hands and feet are distorted."
}
] |
seed44_2869
|
videos/HRA_part1/2869.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional nurse, clad in a light blue scrubs top and dark blue scrubs pants, sits attentively at a desk in a modern hospital setting, her hands deftly typing on a laptop keyboard. Behind her, the bustling hospital environment is visible, adding context to her role. She wears her hair in a neat bun, and her focused gaze is directed at the screen, indicating her concentration on the task at hand. Despite the busy surroundings, she maintains a calm demeanor, highlighting her dedication to her work in the healthcare field.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3070
|
videos/HRA_part1/3070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, dressed in a brown jumpsuit and cap, is playfully crawling on his hands and knees across a stable floor, chasing after a curious horse. The horse, with a full brown mane and tail, looks back at the janitor with a sense of amusement, its hooves stepping lightly on the straw-covered ground. The stable's wooden beams and stalls provide a rustic backdrop, while the janitor's playful demeanor adds a touch of unexpected humor to the otherwise ordinary task of cleaning.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2646
|
videos/HRA_part2/2646.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a costumed character resembling a janitor, complete with a green jumpsuit, gray mustache, and brown hair, performs an energetic jump. This quirky figure, embodying both the roles of maintenance worker and woodland creature, is set against a neutral backdrop. The playful scene is enhanced by the addition of an animated beaver, which appears to mimic the janitor's jumping action, creating a comical and engaging visual narrative. Both characters are depicted in vibrant colors, with the beaver sporting realistic features and the janitor maintaining his distinct uniform and facial details.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1059
|
videos/HRA_part0/1059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, adorned in a red jacket, blue jeans, and a white t-shirt, explores the vibrant streets of Tokyo, holding a sketchbook and pencil. The bustling cityscape surrounds him, featuring neon signs, crowded sidewalks, and eclectic architecture. Suddenly, the scene shifts to a serene indoor swimming pool, where the same artist is seen diving into the water, the reflection of the pool lights creating a mesmerizing pattern on the ceiling. The artist swims with grace and determination, their red swim cap standing out against the blue water, encapsulating a moment of tranquility amidst the urban chaos.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2431
|
videos/HRA_part2/2431.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, clad in a green uniform and safety vest, is seen intently wiping a large, realistic lizard statue with a cloth, ensuring its scales gleam under the bright sun. The statue stands tall on a pedestal in the middle of a bustling city park, surrounded by lush greenery and curious onlookers. The worker's focused expression and meticulous movements highlight the importance of maintaining public art, while the vibrant colors of the lizard statue contrast beautifully with the verdant foliage in the background.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers and arms are missing in the video, and there are issues with the eyes."
}
] |
seed42_2201
|
videos/HRA_part0/2201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two young girls wearing colorful party dresses and headbands with attached animal ears are seen dancing joyfully in a room decorated with balloons and streamers. Amidst the celebration, a small, live hedgehog sits calmly on a table covered with a checkered cloth, surrounded by party snacks and a cake. The hedgehog occasionally moves its quills, seemingly joining in the festivities, as the girls continue their lively dance, their movements filled with laughter and the innocence of childhood joy.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_1537
|
videos/HRA_part1/1537.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene and lush environment, a graceful gazelle is seen gently caressing the face of another smaller gazelle, possibly its offspring, creating a tender and intimate moment between them. The scene is set in a verdant savanna landscape, with tall grass swaying softly in the breeze and trees scattered in the background, providing a peaceful and natural setting for this heartwarming interaction. The larger gazelle, with its delicate features and caring demeanor, conveys a sense of protection and affection toward the younger one, emphasizing the bond between them.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2057
|
videos/HRA_part2/2057.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, with its fur darkened by water, swims gracefully in a lush, green outdoor enclosure, moving purposefully towards the camera. It shares the water with another chimpanzee, both navigating their environment with ease. In the next scene, the chimpanzee, now soaking wet, interacts playfully with another chimp in the water, highlighting their social bond. Finally, a lone chimpanzee, drenched from swimming, sits pensively at the edge of the water, offering a captivating close-up of its expressive face, all set against a backdrop of dense foliage and trees.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1515
|
videos/HRA_part2/1515.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful 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": "Normal. The character's movements are not smooth."
}
] |
seed42_32
|
videos/HRA_part0/32.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, complete with a tailored suit, tie, and leather briefcase, finds himself in an unexpected scenario: cleaning windows. With a microfiber cloth in hand, he meticulously wipes a large, clear window pane, revealing a cityscape beyond. The scene is set in a spacious office with modern decor, where natural light illuminates the room, highlighting the lawyer's dedication to detail in an unconventional task. Despite his professional attire, he approaches the chore with the same seriousness and precision as his legal work.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1621
|
videos/HRA_part1/1621.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional lawyer, dressed in a dark gray suit with a light gray shirt and red tie, prepares coffee in a modern kitchen. The lawyer, wearing glasses, carefully measures coffee grounds into a French press, adding hot water from a sleek electric kettle. The scene captures the lawyer's meticulous attention to detail, from pouring the water to stirring the mixture gently. The lawyer then presses down the plunger slowly, ensuring a rich brew, all while surrounded by stainless steel appliances and minimalist design elements, creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the electric kettle mentioned in the caption."
}
] |
seed46_2003
|
videos/HRA_part2/2003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man wearing a casual jacket and jeans walks through a futuristic cityscape, where the architecture blends elements from different eras, creating a sense of time distortion. He moves with purpose, passing by a mix of old-world cobblestone streets and modern glass skyscrapers. The sky above is tinted with a slight orange hue, suggesting a world where the laws of physics have been altered. As he continues his journey, the background subtly shifts, revealing glimpses of historical landmarks juxtaposed with advanced technology, alluding to the concept of time dilation affecting his walk.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2354
|
videos/HRA_part0/2354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic juxtaposition, a rugged firefighter, clad in full gear and holding a fire hose, stands tall against a backdrop of scientific equipment and dark matter research posters. The scene shifts to focus on the firefighter gently caressing the side of a large, complex machine, symbolizing a tender connection between humanity and the pursuit of knowledge. The firefighter's protective clothing contrasts with the sterile environment of the research facility, creating a compelling visual narrative. Behind him, screens display data related to dark matter studies, emphasizing the unusual fusion of two vastly different worlds.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3156
|
videos/HRA_part1/3156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 suburban neighborhood, a majestic moose stands near a residential street, its large frame contrasting with the mundane setting. The creature is seen wiping its antlers on a tree branch, possibly marking its territory. The scene is set against a backdrop of houses and greenery, giving the impression of wildlife encroaching upon human living spaces. The moose, with its shaggy fur and imposing stature, interacts with its environment in a display of natural behavior, despite the suburban backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3062
|
videos/HRA_part1/3062.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room, a thoughtful writer sits at a cluttered desk, typing away on a laptop with determination. Suddenly, the scene focuses on a small vole, its fur a mix of brown and gray, crawling out from beneath the wooden desk. The rodent explores its surroundings, nibbling on a pencil and climbing onto a pile of books, all while the writer continues to work, seemingly unaware of the tiny creature's presence.]"
},
{
"from": "gpt",
"value": "Bad. The writer's fingers are missing in the video, there are issues with the eyes, and the hamster is overall distorted."
}
] |
seed42_1686
|
videos/HRA_part0/1686.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy, baby panda with distinctive black and white fur crawls across a lush, green forest floor, surrounded by vibrant vegetation and bamboo shoots. It moves with a curious, almost playful demeanor, its tiny paws gripping the mossy ground. The scene is filled with natural light filtering through the dense canopy above, casting dappled shadows on the panda as it explores its environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1916
|
videos/HRA_part1/1916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bearded man, possibly a writer, sits in a hotel room, wearing a brown jacket and glasses, wiping a wooden table with a cloth. The room is well-lit, with a large window behind him, offering a view of a distant mountain range. The man focuses intently on cleaning, his actions deliberate and purposeful. Moments later, a plush teddy bear rests on the now-polished surface, suggesting a personal touch or a connection to the writer's creative process. The scene conveys a sense of tranquility and routine, with the writer's attire and surroundings contributing to the overall mood.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_250
|
videos/HRA_part2/250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room filled with bookshelves, two young boys, one wearing a gray shirt and the other in a navy blue sweater, are diligently organizing books on a lower shelf. The atmosphere is calm and focused, with the boys working attentively side by side. One child carefully selects a book from a pile, examining it before placing it on the shelf, while the other arranges the books alphabetically, ensuring each title is correctly positioned. The room is warm and welcoming, with sunlight streaming in through a nearby window, casting a soft glow over the children as they engage in this educational activity together.]"
},
{
"from": "gpt",
"value": "Normal. The little boy's face and hands are distorted in the video."
}
] |
seed44_2803
|
videos/HRA_part1/2803.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a white lab coat over a blue button-up shirt and khaki pants, walks alongside a capybara on a leash in a lush, green park. The doctor, sporting a neatly trimmed beard and a friendly smile, interacts with the large rodent, which is calmly trotting beside him on the grass. They pass by a wooden bench under the shade of leafy trees, creating a unique and peaceful scene in an urban oasis. The capybara, known for its docile nature, seems comfortable in the presence of the doctor, who gently guides it with the leash, both enjoying a leisurely stroll in the verdant surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's movements in the video are unsmooth."
}
] |
seed46_1925
|
videos/HRA_part2/1925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature male silverback gorilla, marked by a prominent sagittal crest and large, powerful body, crawls through dense, lush vegetation in a misty, mountainous habitat. His dark fur stands out against the vibrant greenery, and his expressive face, complete with attentive eyes and a strong jawline, conveys a sense of intelligence and strength. The scene is set in a protected wildlife reserve, where the gorilla moves purposefully through the undergrowth, highlighting the beauty and resilience of these endangered primates in their natural environment.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth."
}
] |
seed46_2967
|
videos/HRA_part2/2967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lark soars gracefully across a vast, cloud-dappled sky, its russet and brown plumage shimmering in the sunlight. It sings a jubilant melody, filling the air with its clear, melodious notes. The bird then descends into a lush, green meadow dotted with vibrant wildflowers, where it lands softly on a swaying stalk of grass. Its bright eyes scan the surroundings, alert and curious, before taking flight again, its song echoing through the peaceful landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1290
|
videos/HRA_part1/1290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man wearing a brown leather jacket and a tan hat sits on a large rock in the middle of a vast, grassy plain, writing intently in a small notebook. In the background, a majestic bison is seen grazing peacefully on the lush vegetation. Suddenly, the man lowers his book, revealing a look of awe and inspiration as he watches the bison. He then resumes writing, his posture reflecting deep concentration. The scene shifts to show the bison lying down, seemingly resting, as the man continues to write, now with a sense of urgency, capturing the essence of his experience in the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1550
|
videos/HRA_part0/1550.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 crew neck shirt, khaki pants, and black shoes, is seen from above, loading a stainless steel dishwasher in a well-lit kitchen. The kitchen features white cabinets, a white refrigerator, and a gray countertop. The teacher, with short brown hair and glasses, carefully places dishes into the lower rack of the dishwasher. In another angle, the teacher, now wearing a gray shirt and dark pants, continues loading the dishwasher, placing a cup in the upper rack. The room is brightly lit, with white walls and ceiling, and the teacher's focused expression conveys a sense of routine and responsibility.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, arms are deformed, and feet are contorted."
}
] |
seed46_2458
|
videos/HRA_part2/2458.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its dark brown coat and impressive, backward-curving horns, walks steadily across a rocky mountain landscape, offering a close-up view of its sturdy hooves gripping the stone surface. It moves with purpose, navigating the rugged terrain with ease, its alert eyes scanning the surroundings. The ibex continues its journey, the camera capturing the detail of its textured fur and the dramatic mountain scenery that serves as its habitat, highlighting the animal's resilience and adaptability in its natural environment.]"
},
{
"from": "gpt",
"value": "Normal. The ibex's movements are not smooth."
}
] |
seed46_2024
|
videos/HRA_part2/2024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, bespectacled female student sits cross-legged on a clean, white surface, diligently hemming a pair of black pants with a focused expression. She wears a grey cardigan over a white collared shirt and blue jeans, her attire casual yet neat. The environment is bright and minimalistic, with ample natural light illuminating her task. Tools of her activity, such as scissors, thread, and a needle, are neatly arranged within reach, highlighting her attention to detail and organization. The scene captures her absorbed in the sewing process, her hands skillfully manipulating the fabric, demonstrating a blend of practical skill and academic studiousness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2606
|
videos/HRA_part0/2606.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek, spotted jaguar leaps powerfully across a narrow stream in a lush, green rainforest, its muscles rippling beneath golden-brown fur, with water droplets splashing upwards. The big cat's intense gaze is fixed ahead, showcasing its agility and grace in motion against the vibrant jungle setting, complete with lush vegetation and the misty atmosphere of the rainforest environment.]"
},
{
"from": "gpt",
"value": "Normal. The jaguar's running motion in the video is not smooth and coordinated."
}
] |
seed42_2915
|
videos/HRA_part0/2915.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cheetah, embodying grace and power, rests on a dry, grassy savanna, its body curved in a relaxed position. It turns its head, using its paw to wipe its face, showcasing a natural, intimate grooming moment. The cheetah's distinctive black spots stand out against its tan fur, while its piercing eyes and pronounced facial features add depth to the scene. This close-up shot captures the animal's wild beauty and the serene environment surrounding it, with distant trees adding a sense of place to the composition.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2830
|
videos/HRA_part0/2830.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cityscape illuminated by neon lights, a waiter dressed in a sleek, silver apron over a black uniform walks purposefully across a crowded outdoor plaza filled with diverse patrons enjoying their meals. Behind him, an AI pilot, recognizable by its advanced humanoid form with a polished metallic exterior and glowing blue eyes, strides confidently, carrying what appears to be a flight helmet under its arm. Both figures navigate through the bustling scene, the waiter balancing a tray laden with exotic dishes, while the AI pilot's movements are precise and efficient, highlighting the seamless integration of technology and service in this high-tech environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2424
|
videos/HRA_part1/2424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a black vest and tie, crouches low, engaging in a playful crawl across a textured wooden floor. Unexpectedly, a squirrel appears, its bushy tail bouncing, as it curiously crawls alongside the waiter. The two crawl in unison, the squirrel mirroring the waiter's movements, against a backdrop that subtly hints at a 'Quantum Leap' style time warp, indicated by a faint, swirling visual effect. This surreal moment captures the unusual pairing of the crawling waiter and squirrel, blending elements of fantasy and reality.]"
},
{
"from": "gpt",
"value": "Normal. The waiter lacks crawling movements, almost remaining stationary."
}
] |
seed46_2382
|
videos/HRA_part2/2382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and name tag, is fixing a mountain bike in a community center. The space is filled with various tools hanging from the walls, and the officer is seen working intently on the bike's rear wheel. He wears a utility belt with a radio and other equipment, emphasizing his official role. The bicycle, with its vibrant red frame, is partially disassembled, showing the officer's commitment to helping the community beyond his law enforcement duties. The scene takes place indoors, with fluorescent lights casting a warm glow on the officer and the bike, highlighting the act of service in a public space.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are deformed, there are issues with the generation of his arms and face, and the bicycle is generated unreasonably."
}
] |
seed44_2977
|
videos/HRA_part1/2977.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned worker, donning a brown jacket and blue jeans, leads a strong, brown horse by a red halter, walking together in unison on a dirt path. The pair moves at a steady pace, the man guiding the horse with care and respect. The horse, with its muscular build and glossy coat, follows obediently, the two sharing a bond reflective of their partnership. The setting is a rural landscape, with distant hills and trees providing a serene backdrop to their peaceful walk.]"
},
{
"from": "gpt",
"value": "Bad. The horse's head and legs in the video have generation issues, the position of the horse's lead rope is incorrect, and the worker's head was not generated."
}
] |
seed42_1905
|
videos/HRA_part0/1905.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, imposing goose stands tall on the bank of a misty lake, its yellow beak agape as it emits a loud honk. Its body is a mix of gray and white feathers, with a distinctive black mark around one eye. The goose's webbed feet are visible as it wades into the water, creating ripples that disturb the stillness of the early morning. Against the backdrop of a cloudy sky, the goose swims gracefully, its head held high, exuding an air of confidence and territorial dominance. The scene is set in a natural, serene environment, with the goose being the focal point, highlighting its majestic presence in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3138
|
videos/HRA_part2/3138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek black panther walks with measured steps through a dense, shadowy forest, its eyes gleaming with an almost otherworldly green hue. The majestic feline's coat shimmers under the dappled sunlight filtering through the thick canopy above. With each confident stride, the panther's muscles ripple beneath its inky fur, exuding raw power and grace. The underbrush parts gently as the panther moves, revealing the intricate play of light and shadow on the forest floor, punctuated by the occasional flash of vibrant foliage.]"
},
{
"from": "gpt",
"value": "Normal. The black panther in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed46_1463
|
videos/HRA_part2/1463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 subtropical dry forest, a group of five individuals, three women and two men, engage in a cleaning ritual. The women, dressed in green shirts and beige shorts, wipe leaves from a wooden table under the shade of a large tree. One of the men, wearing a yellow shirt and brown shorts, wipes the surface of a fallen log nearby. The other man, in a white shirt and blue shorts, wipes his brow, likely from the physical exertion of the task. The scene is filled with vibrant green foliage, and a sense of camaraderie and purpose is evident among the group members as they work together in the serene forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The action of the girl wiping leaves off the wooden table in the video is not continuous and has sudden changes."
}
] |
seed42_2130
|
videos/HRA_part0/2130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 office cluttered with books and papers, a distinguished lawyer, wearing a gray suit, sits pensively at his desk, his glasses perched on the tip of his nose as he scrutinizes documents. Unbeknownst to him, a tiny brown mouse crawls across the worn wooden surface of the desk, pausing to nibble on a crumb near a row of neatly arranged ink bottles. The lawyer's focus remains on his work, unaware of the small creature sharing his workspace, as the mouse continues its journey across the desk.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1029
|
videos/HRA_part1/1029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 brown rat, with patches of white fur, walks methodically across a weathered wooden surface. It pauses momentarily, its whiskers twitching, before continuing its journey. The rat's movements are deliberate, each step calculated, as it navigates the worn planks. Its tail, long and pink, sways gently behind it, adding to the creature's curious demeanor. Throughout the scene, the rat remains the sole focus, walking with purpose on the textured wood, creating a compelling narrative of survival and exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1303
|
videos/HRA_part2/1303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 North American porcupine, distinguished by its brown and white quills, runs through a dense forest environment, navigating between moss-covered trees. The porcupine, with its quills standing out prominently, dashes across the screen from right to left, showcasing its agility. Its facial features, including small eyes and a pointed nose, are clearly visible as it moves quickly, demonstrating the animal's unexpected speed and grace in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The porcupine's movements in the video are not smooth."
}
] |
seed44_2563
|
videos/HRA_part1/2563.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a crisp blue uniform and black shoes, stands in a spotless hallway illuminated by overhead lights, holding a large, black trash bag. Moments later, he walks down the hall, passing neatly arranged lockers, as he heads towards a propped-open exit door. Upon reaching the door, he pauses under the EXIT sign, preparing to step outside. Finally, he exits into the well-lit outdoors, walking towards a dumpster, his figure silhouetted against the bright sky, embodying the essence of hard work and cleanliness.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner can be clearly seen in the video carrying a black garbage bag and walking towards the exit, with basically normal movements, but there is some lack of coordination."
}
] |
seed44_2470
|
videos/HRA_part1/2470.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical scene, a muscular firefighter in full gear, complete with a red helmet, yellow reflective stripes, and a breathing apparatus, sprints across the rugged terrain of Jupiter's Great Red Spot. The vast, swirling storm serves as a dramatic backdrop, its crimson hues contrasting starkly with the firefighter's outfit. The firefighter's intense gaze and determined stride convey a sense of urgency and purpose, even in this otherworldly environment. The unique landscape, characterized by swirling gas clouds and turbulent weather patterns, adds to the dramatic effect, making this an unforgettable depiction of bravery and athleticism in an extraterrestrial setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_1664
|
videos/HRA_part1/1664.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 market filled with vibrant stalls and the sounds of commerce, a young male cashier, dressed in a blue button-down shirt and khaki pants, walks purposefully across the busy floor. He carries a green plastic bag, possibly containing produce or goods, adding a touch of realism to the scene. The market is alive with activity, from the colorful array of fruits and vegetables on display to the lively chatter of customers and vendors. The cashier navigates this energetic environment, his journey through the market captured in a series of dynamic shots that convey the lively atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed."
}
] |
seed46_2955
|
videos/HRA_part2/2955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow fire-resistant jacket, is kneeling by a blocked drain on a rainy day, amidst urban surroundings. He wields a long, coiled hose and a specialized tool, methodically working to unclog the drain. His focused expression and the rain-soaked environment underscore the challenging task at hand. Moments later, he pulls the clog from the drain, revealing a mix of debris, while water begins to flow freely again, thanks to his diligent efforts. Throughout, the firefighter's protective gear and the wet cityscape provide context to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_3182
|
videos/HRA_part1/3182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male chef, wearing a clean white chef's jacket with short sleeves, meticulously polishes silverware in a well-lit kitchen. The utensils, which include forks, knives, and spoons, gleam under the bright lights as he works. Behind him, a large window reveals a bustling city skyline during daytime, adding a touch of urban sophistication to the scene. The chef's focused expression and the contrast between the shiny silverware and the white chef's jacket create a visually appealing composition.]"
},
{
"from": "gpt",
"value": "Bad. The chef's facial expressions in the video are generated inconsistently, and the hands and utensils are deformed."
}
] |
seed42_1236
|
videos/HRA_part0/1236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome, clean-shaven actor with short brown hair and wearing a black turtleneck sweater and gray blazer is seen in a dimly lit room. He gently caresses a small bat, which rests calmly on his hand, demonstrating a tender interaction between man and animal. The bat, with its leathery wings folded, seems comfortable in his presence, creating a unique and intimate scene. The actor's other hand, adorned with a watch, occasionally enters the frame, adding to the personal nature of the moment. Throughout the video, the focus remains on the actor's face and the bat, capturing the essence of their connection in a softly lit environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, and the bat's body is deformed."
}
] |
seed42_1975
|
videos/HRA_part0/1975.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome waiter, dressed in a white shirt, black vest, and striped tie, walks through a bustling market, surrounded by vibrant stalls selling fruits, vegetables, and spices. The scene captures him navigating the lively crowd, his confident stride and focused gaze highlighting his purposeful movement. Market vendors and customers are visible in the background, adding to the dynamic atmosphere of the location. The waiter's attire contrasts with the colorful market environment, emphasizing his role as he moves through this energetic space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2616
|
videos/HRA_part2/2616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, muscular man, shirtless and wearing only swimming trunks, stands on a vast Martian landscape, gazing up at the star-studded night sky. The red, rocky terrain stretches out behind him, dotted with boulders and craters, while a faint horizon line suggests the curvature of the planet. In the foreground, the man has just emerged from a clear, shimmering pool of water, droplets clinging to his skin and the rocks around him. The pool, seemingly out of place on this arid world, adds an element of mystery and wonder to the scene, as the man contemplates the cosmos from this otherworldly vantage point.]"
},
{
"from": "gpt",
"value": "Bad. There is one extra person in the video."
}
] |
seed42_2659
|
videos/HRA_part0/2659.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting under a clear blue sky, a man wearing a brown jacket and khaki pants kneels on lush green grass, observing a small weasel. The weasel, with its distinct brown fur and white underbelly, crawls along the edge of a weathered stone wall that separates neatly arranged houses from the garden. The man watches intently as the weasel explores its surroundings, highlighting the unexpected encounter between the two in this idyllic residential area.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's body is twisted, the head is twisted, the feet are twisted, the legs are twisted, the character's face is distorted, the hands are twisted, and the legs are twisted."
}
] |
seed42_2319
|
videos/HRA_part0/2319.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic, space-themed setting, a large, friendly capybara wearing a golden astronaut helmet embarks on a diplomatic mission. The capybara, donning a silver spacesuit and a golden astronaut helmet, crawls purposefully across a metallic space station floor, surrounded by high-tech equipment and screens displaying cosmic visuals. Its determined gaze and deliberate movements convey the importance of its interstellar diplomatic task. Nearby, alien delegates watch curiously, their various forms and colors contrasting with the capybara's brown fur and the sterile environment. The scene conveys a sense of unity and cooperation among different species in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's movements in the video are not smooth."
}
] |
seed42_1477
|
videos/HRA_part0/1477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene, a distinguished film director, clad in a black jacket, blue jeans, and brown boots, stands on a rocky outcropping, passionately directing the action. Nearby, an agile ibex leaps over a boulder with remarkable grace, its brown fur and curved horns vivid against the craggy landscape. The camera focuses on the ibex mid-jump, capturing the animal's strength and agility, while the director observes intently, his silhouette framed against the dramatic mountain scenery.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_1121
|
videos/HRA_part0/1121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a khaki safari outfit, is seen in a lush, green jungle environment, carefully cleaning a majestic tiger with a large cloth. The tiger, displaying distinctive orange stripes on a white underbelly, remains calm and cooperative during the process. The director, showing respect and gentleness, focuses intently on wiping the tiger, highlighting a unique bond between human and animal in a wild setting.]"
},
{
"from": "gpt",
"value": "Bad. The hand of the character in the middle frame of the video suddenly distorts, and the tiger's body proportions are inconsistent."
}
] |
seed46_260
|
videos/HRA_part2/260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow t-shirt and khaki shorts, sits at a wooden desk in a rural backyard, typing on a laptop while referencing notes about wormhole travel. Nearby, a brown chicken pecks at the ground, seemingly curious about the writer's work. The scene then shifts to show the writer swimming in a clear blue pool, contemplating the mysteries of the universe and wormhole navigation. The camera captures the water droplets on the writer's face, hinting at the fluidity of time and space, while the chicken watches from the poolside, adding a touch of whimsy to the intellectual exploration.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands appear deformed when typing, and his body appears deformed when in the pool."
}
] |
seed46_2209
|
videos/HRA_part2/2209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a well-dressed doctor, wearing a white coat and a stethoscope around his neck, finds himself in a vibrant restaurant filled with lively music. Surprisingly, he is accompanied by a monkey dressed in miniature clothing, sitting on a chair beside him. As the captivating beat takes over, the doctor and the monkey begin to dance together, their movements synchronized in a comical yet endearing manner. The other patrons, seemingly unfazed, continue dining, providing a backdrop of casual elegance to this unusual dance spectacle.]"
},
{
"from": "gpt",
"value": "Bad. The characters in the video have distorted bodies, twisted heads, twisted legs, and twisted arms; the monkey also has a distorted body, twisted head, and twisted paws."
}
] |
seed42_160
|
videos/HRA_part0/160.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic manta ray glides effortlessly through crystal clear waters, its vast wingspan casting a shadow on the sandy seabed below. The graceful creature is adorned with a constellation of spots and lines, unique to each individual, as it moves with a serene, almost meditative quality. Sunlight filters through the surface, creating a mesmerizing play of light around the manta ray, which occasionally flips upside down to feed on plankton near the water's surface, showcasing its acrobatic abilities in the vibrant marine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1573
|
videos/HRA_part1/1573.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a helmet, digs vigorously with a shovel in hand, surrounded by charred debris and ash under a smoke-filled sky. The scene is set in the aftermath of a fierce fire, with the firefighter's muscular arm raised high, illustrating the strenuous nature of the task. His face is obscured by a breathing apparatus, emphasizing the hazardous conditions. Nearby, another firefighter, also in full protective clothing, aids in the excavation, both working tirelessly amidst the ruins of a burned-out structure, their actions highlighting the determination and bravery required in their line of duty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2028
|
videos/HRA_part1/2028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated teacher, dressed in a green and white striped shirt, khaki shorts, and brown shoes, playfully interacts with a panda cub at a zoo enclosure designed like a natural habitat. The teacher gently guides the panda, which is wearing a tiny red swim vest, as they both splash around in a shallow pool. The panda's curiosity and the teacher's patient instruction create a heartwarming scene, with the water shimmering under the sunlight and the lush greenery of the enclosure providing a serene backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, the panda's arm is distorted, and the face is twisted."
}
] |
seed44_2803
|
videos/HRA_part1/2803.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a white lab coat over a blue button-up shirt and khaki pants, walks alongside a capybara on a leash in a lush, green park. The doctor, sporting a neatly trimmed beard and a friendly smile, interacts with the large rodent, which is calmly trotting beside him on the grass. They pass by a wooden bench under the shade of leafy trees, creating a unique and peaceful scene in an urban oasis. The capybara, known for its docile nature, seems comfortable in the presence of the doctor, who gently guides it with the leash, both enjoying a leisurely stroll in the verdant surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3081
|
videos/HRA_part2/3081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 contemporary art gallery with high ceilings and modern architecture, a janitor wearing a dark green vest, khaki pants, and a name tag, meticulously sweeps the floor. In an unexpected scene, he gently caresses a small vole that has wandered into the gallery, showing a tender side amidst the sterile environment filled with abstract paintings and sculptures. The interaction between the janitor and the vole adds a touch of warmth and humanity to the otherwise cold and impersonal space.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's facial features were not generated completely, the fingers were deformed, and the hamster was deformed overall."
}
] |
seed42_1272
|
videos/HRA_part0/1272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush subtropical wet forest, a striking red fox curiously approaches a musician seated on a moss-covered log. The artist, dressed in a green shirt and brown vest, gently wipes away sweat from their brow, momentarily pausing their harmonious tune played on a wooden flute. Sunbeams filter through the dense foliage overhead, casting a warm glow on the scene, as ferns and tall trees surround them, creating a serene and enchanting atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The musician's face and hands, as well as the red fox's head and paws, are generated abnormally in the video."
}
] |
seed46_1427
|
videos/HRA_part2/1427.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, 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": "Bad. The character's hands are distorted, the face is twisted, and the hand drum is deformed."
}
] |
seed44_281
|
videos/HRA_part1/281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and a yellow firefighting suit, interacts with a hyena at a unique wildlife sanctuary. The firefighter, helmet in hand, stands beside a swimming pool, while the hyena, sporting a brownish coat and black spots, looks on curiously. The two share a moment of connection, with the firefighter's reassuring presence and the hyena's inquisitive gaze, all set against the backdrop of a tranquil, water-filled pool. The scene highlights an unexpected bond between a protector of human safety and a wild animal, both seemingly at ease in each other's company.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's eyes were not generated in the video, and there is a missing part of the arm."
}
] |
seed44_2916
|
videos/HRA_part1/2916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown rat crawls across a desolate volcanic landscape, featuring dark, rocky terrain and smoldering vents emitting wisps of smoke. The rat moves with surprising agility among the rough, jagged rocks, its fur contrasting against the ash-covered ground. As it navigates the harsh environment, the camera captures its determined journey, highlighting its resilience in the face of the volcano's foreboding presence. Throughout the scene, the rat's focus remains unwavering, emphasizing its survival instincts in this challenging, post-eruption setting.]"
},
{
"from": "gpt",
"value": "Normal. The brown mouse in the video walks basically normally, but there is slight uncoordination in its movements."
}
] |
seed44_1500
|
videos/HRA_part1/1500.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic deer, with a full, dark brown coat and large, expressive eyes, is seen swimming across a serene lake at sunrise. Its antlers, elegantly curved and substantial, break the water's surface as it gracefully propels itself forward. The deer's head emerges from the water, its ears alert, as it navigates the tranquil lake surrounded by lush greenery and tall trees, creating a peaceful, almost mystical atmosphere. The water, clear and reflective, gently laps against the deer's body, highlighting the strength and beauty of this wild creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The deer's mouth in the video is generated incorrectly, and the antlers are missing one."
}
] |
seed44_1003
|
videos/HRA_part1/1003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man wearing a sleek, form-fitting spacesuit, adorned with intricate details and a VR helmet, is seen in a futuristic, high-tech room filled with advanced equipment. He leaps into the air, seemingly weightless, as the virtual environment around him simulates the zero-gravity conditions of space. The room is illuminated by soft, ambient lighting, highlighting the man's movements as he trains for space missions, surrounded by screens displaying complex data and simulations. The focus remains on the astronaut in the center of the room, his body language conveying determination and excitement as he experiences the thrill of jumping in a virtual space environment.]"
},
{
"from": "gpt",
"value": "Bad. Middle frame characters have abnormally twisted limbs, with arms and legs disappearing or appearing suddenly."
}
] |
seed46_2483
|
videos/HRA_part2/2483.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 spotted hyena, mid-jump, leaps across a grassy savanna landscape, its powerful hind legs fully extended beneath it, capturing the essence of its agility and strength. The hyena's spotted coat is vivid against the green vegetation, and its mouth is open, revealing sharp teeth, as it focuses on an unseen target ahead. The scene is set during the golden hour, with warm sunlight casting a glow over the hyena and the surrounding environment, highlighting the texture of the grass and the depth of the landscape.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the spotted hyena in the video are missing, the body is deformed, and there are issues with the tail generation."
}
] |
seed46_2498
|
videos/HRA_part2/2498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, reminiscent of Michael B. Jordan, sits at a desk in a modern office space. Dressed in a casual white shirt, sleeves rolled up, and stylish glasses perched on his nose, he focuses intently on typing on a sleek, black keyboard. The desk is clutter-free, save for a single, elegant desk lamp casting a warm glow over the scene. Behind him, a large window frames a view of a bustling city skyline, hinting at the high-stakes narrative unfolding as his fingers dance across the keys.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2719
|
videos/HRA_part2/2719.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station adorned with lavish decorations for an extravagant wedding, a neatly-dressed cashier, wearing a classic black vest and bow tie, diligently wipes the immaculate glass counter with a small cloth. The backdrop features elegant table settings, floral arrangements, and a large, illuminated dance floor, all indicative of an upscale celebration. The cashier's meticulous attention to detail ensures the space station's cash register area remains spotless amidst the grand festivities.]"
},
{
"from": "gpt",
"value": "Normal. The cashier cleaning the glass is basically normal, but there are slight coordination issues."
}
] |
seed44_2810
|
videos/HRA_part1/2810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a black turtleneck sweater and khaki pants, walks through a sterile, white space medical facility, illuminated by soft, ambient lighting. He carries a notebook in his right hand, occasionally jotting down notes as he observes various medical procedures taking place in the background. The facility is equipped with futuristic medical equipment, including robotic surgical arms and holographic diagnostic displays, which are visible through glass walls. The writer stops at a large window overlooking a distant planet, offering a glimpse into the vastness of space, providing inspiration for his writing. Throughout the video, the focus remains on the writer's journey through the space station, capturing his curiosity and engagement with the advanced medical technology surrounding him.]"
},
{
"from": "gpt",
"value": "Bad. No noteboo and distant planet generated."
}
] |
seed44_1489
|
videos/HRA_part1/1489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a pristine white apron and cap, walks barefoot on a serene, sandy beach, with the sun casting a warm glow over the calm sea. He holds a large, colorful fish in his hands, a symbol of fresh ingredients, while the beach's natural beauty, including lush greenery and clear skies, provides a stunning backdrop. The chef's attire, complete with the traditional uniform, contrasts beautifully with the relaxed coastal setting, highlighting his connection to nature and the source of his culinary inspiration.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2929
|
videos/HRA_part0/2929.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a brown jacket over a striped shirt and khaki pants, performs a surprising leap over a row of yellow school lockers, demonstrating unexpected athleticism. In the next scene, he jumps again, this time over a green garbage can, showcasing his lively spirit. Then, he leaps over a red fire extinguisher mounted on a wall, his movements fluid and agile. Finally, the janitor, still clad in his brown jacket and khakis, clears a hurdle formed by a mop and bucket, his face expressing pure delight in these spontaneous acts of physicality, all within the confines of a school corridor.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's movements in the video are not smooth."
}
] |
seed42_1391
|
videos/HRA_part0/1391.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 a young Tom Hardy, wearing a futuristic space suit with a gorilla mascot emblem, embarks on an exhilarating lunar buggy ride across a desolate moon landscape, capturing the essence of adventure in outer space. Later, he is seen walking purposefully, leading the lunar buggy with ease, as if navigating through a challenging mission. The actor then pauses to admire the vast, starry expanse, evoking a sense of awe and wonder, before continuing his journey, showcasing determination and resilience. Throughout the scenes, the lunar buggy, with its distinctive design and rugged tires, remains a prominent feature, highlighting the vehicle's role in the astronaut's lunar exploration.]"
},
{
"from": "gpt",
"value": "Normal. The character's body is twisted, the arms are twisted, the hands are twisted, and the legs are twisted."
}
] |
seed46_1578
|
videos/HRA_part2/1578.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, adorned in a cozy gray sweater and glasses, stands in a modern kitchen with sleek appliances, ready to craft stories. They pour water into a high-tech coffee machine, its illuminated screen displaying the brewing process, setting the scene for a productive day of writing. The individual then adds coffee grounds to the machine, preparing a perfect cup of coffee to fuel their creative endeavors. Dressed in a comfortable outfit and with a laptop nearby, they embody the ideal image of a writer ready to tackle the day, all while the aroma of freshly brewed coffee fills the air.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate coffee grounds."
}
] |
seed46_1231
|
videos/HRA_part2/1231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter wearing a black vest, white shirt, and black trousers leaps into the air, displaying an unexpected burst of energy, against a backdrop of lush subtropical shrubland. The landscape is filled with vibrant green bushes and trees, creating a vivid contrast to the waiter's formal attire. As he jumps, his posture suggests both playfulness and professionalism, blending the elements of surprise and elegance in an outdoor setting characterized by rich vegetation and natural beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2523
|
videos/HRA_part2/2523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a tailored gray suit, white shirt, and red tie, takes an unconventional break from his legal duties to clean windows on a busy city street. Holding a squeegee in one hand and a spray bottle in the other, he expertly removes smudges from the glass, all while maintaining a professional demeanor. Passersby, including a group of schoolchildren and a mother with a stroller, observe the unusual sight with amusement. The lawyer's briefcase rests nearby, a reminder of his typical occupation, as he focuses on the task at hand with surprising skill and dedication.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the lawyer's hands, windshield wipers, spray bottle, and limbs of passersby in the video is abnormal, with the spray bottle in the lawyer's hand suddenly disappearing in the middle frames."
}
] |
seed46_1856
|
videos/HRA_part2/1856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, identifiable by her backpack, dances whimsically across the screen, transitioning from a campus setting to an unexpected otter enclosure at a zoo. She's wearing a yellow top, denim shorts, and sneakers, embodying youthful energy. Suddenly, the scene shifts to a somber cemetery, where she continues to dance among the tombstones, now adorned in a black dress and boots, carrying a red umbrella. The juxtaposition of lively dancing in these varied locations, from educational grounds to wildlife exhibits to a place of remembrance, creates a surreal and captivating narrative.]"
},
{
"from": "gpt",
"value": "Bad. The jumping action of the girl in the school scene is not smooth and coordinated, and there are sudden changes in her hands; the dancing actions of the girl in the cemetery are also not smooth and coordinated."
}
] |
seed44_1067
|
videos/HRA_part1/1067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 stylish woman, wearing a vibrant red dress and black high heels, gracefully dances in the center of a bustling restaurant. The place is filled with the warm glow of hanging lights and lively chatter from the patrons seated at their tables. She moves with confidence and joy, her dress swirling around her as she twirls to the rhythm of the live band playing in the corner. The camera captures her expressive face, full of happiness, and the admiring glances of those around her who pause to watch her performance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_297
|
videos/HRA_part1/297.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the lush, green undergrowth of a temperate rainforest, a wildlife worker, clad in a khaki shirt and hat, carefully crawls on his hands and knees, examining the rich flora. Nearby, a chimpanzee, adapted to this cooler, wetter habitat, curiously observes the human from behind a moss-covered tree trunk, its fur darker due to the climate. The scene captures the unique bond between the worker, dedicated to studying and preserving this ecosystem, and the chimpanzee, a rare sight in temperate rainforests, both interacting within the dense, verdant surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, and the gorilla's face is distorted."
}
] |
seed44_3188
|
videos/HRA_part1/3188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a white chef's uniform with black stripes and a matching hat, is seen in a small, empty room with white walls and a gray floor. He stands on a brown wooden ladder, holding a paintbrush in his right hand and a white roller brush in his left. The room is illuminated by a large window to his right, casting a soft glow over the space. The chef, with a full beard and a concentrated look on his face, is in the process of painting the wall a vibrant shade of green. The scene captures his transformation of the room, as he applies the paint with precision and care, highlighting his skills beyond the kitchen.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands and arms show signs of abnormal mutation, and the tool in his hand also undergoes deformation."
}
] |
seed46_3031
|
videos/HRA_part2/3031.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man with a full beard, dressed in a green shirt and brown pants, is kneeling in a forest clearing. He gently wipes a small, injured porcupine with a white cloth, his face expressing deep concern and care. The porcupine, quills visible, lies quietly on a bed of moss and leaves, seemingly aware of the man's protective presence. The forest surroundings, with tall trees and dappled sunlight, provide a natural and peaceful setting for this tender interaction between man and wildlife.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_308
|
videos/HRA_part1/308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, with distinctive tufted ears and a rufous-colored coat, leaps from a rocky outcropping, its body arched and legs extended, showcasing its agility and power. The background features lush vegetation and trees, highlighting the wild, natural habitat of this impressive feline. The scene is captured in high definition, allowing every detail of the bobcat's muscular form and the surrounding environment to be clearly visible during the jump.]"
},
{
"from": "gpt",
"value": "Bad. The sable's jumping action is not smooth."
}
] |
seed44_1473
|
videos/HRA_part1/1473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches on a branch, its vibrant green feathers contrasting against a clear blue sky, before taking flight against a backdrop of lush greenery and distant mountains. It swoops down gracefully, its long, slender beak aimed at capturing prey. The bird then returns to the branch, where it proudly displays its catch, a honeybee, before consuming it. Throughout the scene, the bee-eater's striking plumage, featuring shades of green, blue, and brown, catches the eye against the serene landscape.]"
},
{
"from": "gpt",
"value": "Normal. The bee-eater's claws are missing in the video, and the bee has become deformed."
}
] |
seed44_2092
|
videos/HRA_part1/2092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic actor, wearing a sleek black suit and tie, performs an elegant dance move against a backdrop of Saturn's magnificent ring system, which glimmers with ethereal beauty in the distance. His confident posture and engaging smile captivate the viewer, while the celestial wonder behind him adds a touch of grandeur to the scene. The actor's polished shoes and well-groomed appearance contrast with the vastness of space, creating a unique juxtaposition between human artistry and cosmic splendor.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_136
|
videos/HRA_part1/136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a white martial arts uniform with a red stripe, executes a high kick against a blue sky, showcasing agility and precision. Surrounded by lush greenery, including palm trees and bushes, the scene highlights the contrast between nature and human skill. The artist's ponytail swings during the kick, emphasizing the dynamic motion. Nearby, a wooden fence and a building with a thatched roof add to the tropical setting. Throughout the sequence, the artist maintains a focused gaze, highlighting determination and control.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1758
|
videos/HRA_part0/1758.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, middle-aged teacher waves energetically with both hands from a classroom filled with colorful decorations, wearing a bright yellow sweater over a patterned dress, against a backdrop of windows showing a clear blue sky, conveying a sense of warmth and welcome. She stands in front of a whiteboard adorned with educational posters and student artwork, her smile and enthusiastic gesture creating an inviting atmosphere for students. The room is bathed in natural light, highlighting the teacher's animated expression and the vibrant learning environment.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video has uncoordinated movements."
}
] |
seed44_285
|
videos/HRA_part1/285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray long-sleeved shirt and khaki pants, is seen wiping down a hippopotamus with a large cloth. The scene takes place in a spacious, well-lit room with concrete walls and floor, resembling a zoo enclosure or animal care facility. The engineer, wearing safety glasses and a name badge, approaches the docile hippopotamus with a bucket of soapy water and a sponge, carefully cleaning its skin. The hippo, appearing calm and cooperative, stands in the middle of the room, surrounded by various tools and equipment typically found in an engineering workshop, creating an unusual yet intriguing juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's facial features and fingers are generated blurily and distortedly; in the middle frame, the engineer's hand passes directly through the hippo's body, and there is an issue with the generation of the hippo's head."
}
] |
seed46_2274
|
videos/HRA_part2/2274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, Mars-like landscape painted in shades of orange and red, a woman wearing a futuristic silver suit gently caresses a majestic bison, while a second bison stands nearby. Behind them, a man clad in a matching silver suit rides a robust, armored horse, creating a striking contrast against the barren, rocky terrain and the distant, hazy horizon. The woman's tender touch on the bison's fur and the man's confident posture on the horse convey a sense of harmony and adventure in this otherworldly setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2758
|
videos/HRA_part2/2758.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a red plaid shirt, blue jeans, and a wide-brimmed straw hat, diligently sweeps his wooden porch with a long-handled broom, the early morning sun casting a warm glow over the rural scene. Beside him, a white dog rests lazily on the porch, enjoying the peaceful ambiance. The farmer pauses to wipe sweat from his brow, revealing a face lined with years of hard work and dedication to his land. He continues sweeping, the rhythmic sound of the broom against the wood providing a soothing soundtrack to the quiet countryside morning. Behind him, a lush green landscape stretches out, dotted with crops and farm buildings, a testament to his labor and connection to the earth.]"
},
{
"from": "gpt",
"value": "Bad. The man's actions of sweeping the wooden porch with a long-handled broom are not continuous and smooth, there are abrupt changes; the man's action of stopping to wipe the sweat off his forehead is not continuous and coordinated."
}
] |
seed42_1103
|
videos/HRA_part0/1103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 reality TV show set against a metallic spaceship interior, a muscular firefighter wearing a red swim cap, goggles, and a black swimsuit floats weightlessly in zero gravity. He performs swimming strokes in mid-air, surrounded by floating water droplets, while a diverse group of fellow firefighters observes from a viewing platform. The scene conveys a sense of camaraderie and adventure among the crew members, who are participating in a unique aquatic challenge aboard the spacecraft. The firefighter's robust physique and focused expression highlight his determination and skill, even in the unconventional setting of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2149
|
videos/HRA_part0/2149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant display under the aurora-lit sky, several figures clad in traditional fur coats and hats, reminiscent of indigenous Siberian attire, gather around a blazing bonfire set amidst the dense taiga forest. They begin to sway in unison, their movements a harmonious blend of ancient and modern dance styles. The firelight flickers across their faces, casting dramatic shadows as they leap and twirl, their feet barely touching the snow-covered ground. The camera captures the dancers from various angles, emphasizing the connection between their lively steps and the serene, starlit wilderness that surrounds them.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a distorted body, head, legs, and arms."
}
] |
seed46_2014
|
videos/HRA_part2/2014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of a sea urchin reveals its intricate, symmetrical structure as it clings to a rocky surface underwater. Sunlight filters through the clear, blue water, casting a soft glow on the urchin's spines, which are a striking contrast to the dark rocks. The camera captures the water gently swaying the urchin, emphasizing its resilience in the marine environment. The scene is framed by the rocky crevices of the seabed, highlighting the creature's natural habitat, while the muted colors of the rocks and sand provide a serene backdrop for the brightly colored sea urchin.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2803
|
videos/HRA_part0/2803.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a white lab coat over a blue button-up shirt and khaki pants, walks alongside a capybara on a leash in a lush, green park. The doctor, sporting a neatly trimmed beard and a friendly smile, interacts with the large rodent, which is calmly trotting beside him on the grass. They pass by a wooden bench under the shade of leafy trees, creating a unique and peaceful scene in an urban oasis. The capybara, known for its docile nature, seems comfortable in the presence of the doctor, who gently guides it with the leash, both enjoying a leisurely stroll in the verdant surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's limbs are missing in the video, the ears were not generated, there is an issue with the mouth, the doctor's fingers are deformed, and the face generation is blurry."
}
] |
seed44_1793
|
videos/HRA_part1/1793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 setting, a skilled musician, dressed in a black leather jacket, plays a gleaming silver electric guitar. Nearby, an enormous, friendly bear, adorned with a red bow tie, listens intently, its paw gently resting on the musician's shoulder in a gesture of companionship. Suddenly, a shimmering wormhole opens behind them, revealing a kaleidoscope of colors and swirling galaxies. The musician and the bear look into the wormhole, their expressions a mix of awe and curiosity, as they contemplate the mysteries of the universe together.]"
},
{
"from": "gpt",
"value": "Normal. The bow tie in the video has issues, the musician's face and hands are generated abnormally, and there is sudden distortion in the middle frames."
}
] |
seed44_1586
|
videos/HRA_part1/1586.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station habitat, illuminated by soft, ambient lighting, a caring teacher, wearing a navy blue jumpsuit with silver accents, gently caresses the head of a young student seated at a desk. The student, dressed in a matching uniform, looks up with wide eyes, feeling comfort and support. Behind them, a large window reveals the stunning view of Earth, while various educational tools and floating objects fill the zero-gravity environment, creating an immersive learning atmosphere. The teacher's compassionate touch and the unique setting emphasize the nurturing bond between educator and pupil in this extraordinary space classroom.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed."
}
] |
seed42_1259
|
videos/HRA_part0/1259.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum hall with marble floors, an antelope taxidermy mount is displayed under a spotlight, its majestic form captured mid-leap. A diligent custodian wearing a green apron wipes the glass display case, ensuring the exhibit is pristine. The antelope, with its striking coat and alert posture, seems to leap over a miniature landscape within the display. The custodian, in a green uniform, carefully cleans the case, her reflection visible alongside the antelope's image. Throughout, the museum's grandeur is evident, with high ceilings, ornate moldings, and other exhibits surrounding the featured antelope.]"
},
{
"from": "gpt",
"value": "Bad. The deer has an extra front leg."
}
] |
seed46_2470
|
videos/HRA_part2/2470.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a fantastical scene, a muscular firefighter in full gear, complete with a red helmet, yellow reflective stripes, and a breathing apparatus, sprints across the rugged terrain of Jupiter's Great Red Spot. The vast, swirling storm serves as a dramatic backdrop, its crimson hues contrasting starkly with the firefighter's outfit. The firefighter's intense gaze and determined stride convey a sense of urgency and purpose, even in this otherworldly environment. The unique landscape, characterized by swirling gas clouds and turbulent weather patterns, adds to the dramatic effect, making this an unforgettable depiction of bravery and athleticism in an extraterrestrial setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2853
|
videos/HRA_part2/2853.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic musician, adorned in a stylish leather jacket and holding a harmonica, walks alongside a dingo in a serene natural landscape. Both figures stroll leisurely, the musician's outfit complemented by faded jeans and a classic white T-shirt, while the dingo, with its reddish-brown fur, matches the earthy tones of the surroundings. They move in harmony, the musician occasionally playing the harmonica, creating a peaceful melody that resonates with the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are deformed, his facial features are distorted, the harmonica is malformed, there are issues with the feet, and the wild dog has missing limbs."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.