video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1404
|
videos/HRA_part1/1404.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds on a moonlit beach, where a diverse group of people, dressed in vibrant, patterned shirts and shorts, gather around a bonfire. The atmosphere is festive, with a bat flying gracefully across the night sky, its silhouette visible against the glowing embers. The crowd dances energetically to lively music, their movements fluid and joyful, while others look on, clapping and cheering. Nearby, the calm sea reflects the firelight, creating a mesmerizing, shimmering effect on the water's surface. The sandy beach, dotted with palm trees, provides a picturesque setting for this nocturnal celebration.]"
},
{
"from": "gpt",
"value": "Bad. The character's body movements are not coordinated."
}
] |
seed46_1792
|
videos/HRA_part2/1792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a straw hat and denim overalls, stands on wooden docks by the water's edge, engaging in an impromptu dance with a mongoose. The mongoose, with its alert eyes and bushy tail, seems equally engaged in the dance, mirroring the farmer's playful steps. The docks, weathered and worn, creak under their movements, providing a rustic stage for this unlikely duo. The sun begins to set, casting a golden glow over the scene, adding a magical touch to the dance between the farmer and the mongoose.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, face, arms, legs, hands, and feet, and the mongoose also has a twisted body, arms, claws, and face."
}
] |
seed44_176
|
videos/HRA_part1/176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warbler, a small songbird with bright yellow underparts and olive-green upperparts, perches on a thin branch against a blurred green background. It turns its head to the side, displaying its distinct facial markings, including a black eyestripe and a white eyering. The bird opens its beak slightly, perhaps about to sing its characteristic warbling song, capturing a moment of natural beauty in the forest. Against the softly blurred greenery, the warbler stands out, a vibrant splash of color and life.]"
},
{
"from": "gpt",
"value": "Normal. The bird's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1496
|
videos/HRA_part2/1496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned farmer, wearing a brown shirt and denim overalls, drives a futuristic lunar buggy across a vast, barren moon landscape, dotted with craters and boulders under a starlit sky. Suddenly, the scene transitions to a serene, earthbound setting where the same farmer is seen leisurely floating on an inflatable raft, fully clothed, in the middle of a tranquil, crystal-clear lake surrounded by lush greenery. The peaceful atmosphere is punctuated by the occasional splash as the farmer gently moves through the water, enjoying a refreshing break from his daily chores.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's attire in the second scene does not match the text description."
}
] |
seed42_2633
|
videos/HRA_part0/2633.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, vibrant green and purple, hovers in a sunny garden, its wings a blur as it feeds from a red salvia flower. The bird moves to another scarlet blossom, its long beak piercing the flower to drink nectar, all set against a lush, green foliage backdrop. It then perches on a branch, preening its feathers with a bright pink beak, before resuming flight, hovering near a spray of orange and yellow flowers. Finally, the hummingbird returns to the red blooms, feeding once more with the sun illuminating its iridescent plumage, showcasing its agility and grace against a garden filled with various colorful flowers.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's flight in the video is very unsmooth, and the movements are uncoordinated."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a 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": "Good. Basically no problem."
}
] |
seed46_1428
|
videos/HRA_part2/1428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male waiter, wearing a crisp white shirt, black vest, and necktie, serves a couple at an elegant indoor restaurant. Suddenly, he breaks into song, passionately singing an operatic aria while continuing to serve. The camera captures his animated face as he sings, highlighting his emotional performance. Throughout, the well-lit dining area with its ornate chandelier and patrons at other tables remains visible, creating a lively atmosphere. The waiter's confident singing and the restaurant's upscale ambiance provide a memorable contrast to his regular duties.]"
},
{
"from": "gpt",
"value": "Normal. The waiter's movements in the video are not smooth."
}
] |
seed46_3065
|
videos/HRA_part2/3065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, casually dressed in a white T-shirt and beige shorts, walks along a stone path on campus, accompanied by a small, green lizard perched on their right shoulder. The student, wearing a backpack and baseball cap, strolls under the shade of lush trees, while the reptile remains calmly positioned, seemingly enjoying the ride. The scene captures the unusual yet harmonious relationship between the student and the lizard, both navigating the campus environment together.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_284
|
videos/HRA_part0/284.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lab coat over a collared shirt and khaki pants, gently caresses a hamster in a zero-gravity environment, suggesting space agriculture. The doctor, with neatly trimmed facial hair and spectacles, holds the hamster with care and attentiveness, floating effortlessly in a spaceship's cabin. The hamster, nestled in the palm of the doctor's hand, appears relaxed and comfortable, indicating a nurturing bond between the two. In the background, hydroponic plants grow in LED-lit chambers, emphasizing the agricultural aspect of the scene. The doctor's focus on the hamster, combined with the futuristic setting, conveys a sense of compassion and innovation in space farming.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_2702
|
videos/HRA_part0/2702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, vibrant kitchen filled with the warm glow of overhead lights, a group of four individuals, two men and two women, are energetically washing dishes. One man, wearing a dark green apron over a white t-shirt, vigorously scrubs a pot under running water from a stainless steel sink. Beside him, a woman in a yellow apron laughs as she dries a plate with a colorful cloth. Across the room, another man in a chef's coat rinses glasses, while a woman in a floral apron sorts cutlery, her hands deftly separating forks and spoons. The atmosphere is lively, with steam rising from the sink and the clinking of dishes adding to the symphony of post-meal cleanup.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_2771
|
videos/HRA_part1/2771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary director, dressed in a classic pinstripe suit, stands in a vast, dimly lit studio, skillfully orchestrating a surreal scene. Nearby, a Robot astronaut, adorned in a sleek silver spacesuit with gleaming gold accents, follows the director's guidance as it begins to dance. The robot's movements are fluid and precise, a captivating fusion of technology and artistry, set against the backdrop of cinematic equipment and the director's watchful gaze, creating a mesmerizing spectacle where reality meets imagination.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2473
|
videos/HRA_part0/2473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a panther costume, complete with a black leotard, detailed spots, and a lifelike mask, crawls on all fours across a dimly lit stage. The setting is enhanced by a spotlight illuminating her figure, emphasizing the fluidity and grace of her movements, akin to a real panther. The background remains shadowy, drawing attention to her performance as she embodies the essence of the wild animal through her crawling motion.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs and fingers are missing in the video, and her face is distorted."
}
] |
seed46_2966
|
videos/HRA_part2/2966.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a gray hoodie and khaki pants, walks alongside a camel in a desert landscape. The sun casts long shadows, highlighting the serene connection between the two. The student, wearing a backpack and a wide-brimmed hat, looks thoughtful as they journey together. The camel, adorned with vibrant red and orange textiles, ambles along gracefully, its large, expressive eyes gazing ahead. Together, they traverse the sandy dunes under a vast, cloudless sky, embodying a sense of adventure and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows students and camels walking in the desert, with basically normal movements, but there is slight disharmony."
}
] |
seed42_2854
|
videos/HRA_part0/2854.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone coyote, with a gray and cream coat, runs across a sunlit prairie, its ears perked and tail held low. It bounds through the tall grass, leaving a slight dust cloud in its wake, indicating speed and purpose. The coyote's focused gaze and agile movements showcase its hunting prowess, as it navigates the open landscape under a clear blue sky. Moments later, it leaps over a small obstacle, demonstrating its agility and grace, all while maintaining its steady pace across the vast, golden plains.]"
},
{
"from": "gpt",
"value": "Normal. No generation of obstacles."
}
] |
seed42_2268
|
videos/HRA_part0/2268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cave-like setting, a brown bat clings to the rocky ceiling, its wings folded, and its form illuminated by a faint light source, evoking a sense of mystery and exploration. Nearby, a scientist wearing a white lab coat examines a high-tech device, possibly a particle detector, which emits a soft glow, indicating advanced research into dark matter. On the ground, a small, unidentified creature crawls slowly across the rocky floor, adding an element of intrigue to the scene. The juxtaposition of the bat, the scientist, and the crawling creature creates a captivating narrative about the intersection of nature, science, and the unknown.]"
},
{
"from": "gpt",
"value": "Bad. The bat's body is twisted, and its wings are deformed."
}
] |
seed42_2521
|
videos/HRA_part0/2521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, donning a black hat and dressed in a brown jacket over a white shirt, plays a wind instrument passionately in an art gallery filled with contemporary art pieces. Suddenly, a gazelle, a symbol of grace and freedom, jumps into the frame from the right side, leaping over a low sculpture, adding an unexpected yet harmonious element to the scene. The focus remains on the musician and the gazelle, with the vibrant artwork providing a stimulating backdrop, all captured in a single, continuous shot.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2180
|
videos/HRA_part0/2180.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vast school of silver sardines elegantly maneuvers through the clear blue ocean, their synchronized movements creating mesmerizing patterns as they navigate around a large, rocky coral reef structure. Sunlight filters through the water, illuminating the fish and highlighting their metallic scales against the vibrant coral and lush underwater flora. The sardines' fluid dynamics and the contrast between their silvery bodies and the colorful marine environment create a stunning visual display in the depths of the sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2042
|
videos/HRA_part1/2042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a green spacesuit with a clear helmet, stands on an alien planet with vibrant purple foliage and orange skies, holding a tablet displaying educational diagrams. Nearby, a body of water shimmers under the exotic sky, showing aquatic life adapted to this unique ecosystem, swimming gracefully beneath the surface. The teacher occasionally glances up from the tablet to observe the surrounding alien flora and fauna, integrating real-world examples into the lesson. Throughout the scene, the focus remains on the teacher's engagement with the alien environment, using it as a teaching tool, while the colorful, otherworldly landscape provides a captivating backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The movements are slightly unsmooth."
}
] |
seed42_2032
|
videos/HRA_part0/2032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red kangaroo, distinguishable by its ruddy fur, bounds across a vast, arid landscape under a cloud-dappled sky, showcasing its powerful hind legs and long, muscular tail for balance. It leaps gracefully over the terrain, highlighting its natural agility and strength in motion. The kangaroo's focused gaze and determined posture emphasize its purposeful sprint across the open, scrubland environment, with distant hills providing a scenic backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's limbs in the video are severely distorted, and there is a frame with five legs in the middle."
}
] |
seed46_1001
|
videos/HRA_part2/1001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 smiling firefighter, clad in full gear and a helmet, stands against the backdrop of a fire station. His turnout coat is unzipped, revealing a yellow safety vest, and he holds his helmet in one hand. The fire engine bay is visible behind him, with a red fire truck and a large American flag hanging on the wall. His cheerful demeanor is accentuated by the bright sunlight shining through the open garage door, casting a warm glow over the scene. Despite the serious nature of his profession, his smile conveys a sense of pride, resilience, and community spirit.]"
},
{
"from": "gpt",
"value": "Normal. Basically normal."
}
] |
seed44_246
|
videos/HRA_part1/246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, charming finch perches on a branch, its vivid yellow plumage contrasting beautifully with the green foliage. Its beady eyes sparkle with life as it gazes around, alert and curious. Suddenly, it breaks into a melodious song, filling the air with its sweet, trilling notes. The bird then takes flight, its wings a blur of motion against the clear blue sky, before settling back on the branch, a picture of grace and tranquility in nature's embrace.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1373
|
videos/HRA_part0/1373.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red plaid shirt and khaki pants, stands tall with his hands resting on a wooden fence, his gaze directed at a stunning sunset. Behind him, a lush green forest stretches into the distance, while the golden rays of the setting sun illuminate the landscape, casting a warm glow over everything. The man's posture suggests a sense of peace and tranquility as he takes in the breathtaking view before him.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_189
|
videos/HRA_part0/189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a gray hoodie and blue jeans, sits cross-legged on a hardwood floor in a room with large windows, a desk with a laptop, and a bookshelf in the background. A curious cat crawls onto the student's lap, interrupting their study session. The student gently strokes the cat, which is adorned with a red collar, as it snuggles into their lap. The room is filled with natural light from the windows, creating a warm and cozy atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The student's legs in the video are generated unreasonably, the fingers are generated with issues, the cat's limbs and tail are partially missing, and the paws are also missing."
}
] |
seed46_2703
|
videos/HRA_part2/2703.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park setting, a young woman with dark hair pulled back into a ponytail works at a ticket booth decorated with colorful animal illustrations. She wears a green polo shirt with a name tag, signifying her role as a cashier. A small, friendly kinkajou rests on her shoulder, its fur blending with her brown hair. The animal playfully explores the area around her head as she smiles warmly, gently caressing it with her right hand, her nametag partially visible. This intimate interaction between the cashier and the kinkajou occurs within the vibrant, wildlife-themed environment of the zoo.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is slightly distorted, hands are distorted, the kinkajou's face is distorted, and the claws are distorted."
}
] |
seed46_1419
|
videos/HRA_part2/1419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and a helmet, is sprinting with intense focus through a lush, green park. He's gripping a fire hose as he runs beside a serene lake, where ducks are seen swimming in the background. The scene conveys a sense of urgency and determination, with the firefighter's muscular physique straining against his equipment. The park is filled with vibrant greenery and tall trees, providing a stark contrast to the firefighter's urgent mission. As he races past a wooden bench and a playground, the peaceful setting underscores the potential danger lurking nearby.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the face is deformed, and the legs are twisted."
}
] |
seed46_1319
|
videos/HRA_part2/1319.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a gray jacket and jeans, sits cross-legged on a wooden deck by a lake, gently stroking a small brown beaver. The scene is set during the golden hour, with the student's face showing affection and the beaver seemingly comfortable with the interaction. The student, with tousled hair and a warm smile, holds the beaver with both hands, providing a sense of safety and care, while the creature, with its distinctive flat tail and sharp teeth, appears relaxed and unafraid in this peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The faces of the students showing affection were not generated, and there were issues with the generation of the students' hands, as well as the faces and paws of the beavers."
}
] |
seed42_190
|
videos/HRA_part0/190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jaguar, marked by its distinctive black spots on tawny fur, walks purposefully across a lush, green savanna landscape under the dappled shade of scattered trees. Its powerful muscles ripple beneath its coat as it strides with feline grace, the camera capturing every detail in high definition. The surroundings are alive with the sounds of nature, from chirping birds to the distant call of other wildlife, creating an immersive environment that highlights the beauty and power of this wild cat in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The head and paws of the jaguar in the video have issues."
}
] |
seed42_1119
|
videos/HRA_part0/1119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Asian cashier, wearing a red apron over a white collared shirt, black pants, and black shoes, is seen mid-air, jumping with both feet off the ground, her ponytail bouncing behind her. The camera captures her from various angles, showing her enthusiasm and energy as she performs this unexpected action within the confines of her workplace, a modern convenience store with neatly arranged shelves and bright lighting.]"
},
{
"from": "gpt",
"value": "Bad. The woman's jumping motion in the video is not smooth and continuous, with abrupt changes in her limbs' movements."
}
] |
seed44_2503
|
videos/HRA_part1/2503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mouse leaps through the air in a grassy field, its tiny body arched gracefully as it propels itself forward. The scene is set against a backdrop of lush green foliage and blue skies, with the mouse's agile movement captured mid-jump. Its wiry tail extends behind it, adding to the sense of dynamic motion, while its round ears and beady eyes give it a characteristically cute appearance. The mouse lands softly on a patch of green grass, ready to spring into action again at a moment's notice.]"
},
{
"from": "gpt",
"value": "Bad. The brown rat's jumping action in the video is not continuous and smooth, very uncoordinated."
}
] |
seed42_1776
|
videos/HRA_part0/1776.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-aged student, wearing a full-body red fox mascot costume, performs an entertaining dance routine in the middle of a lively campus quad. The mascot, with its distinctive bushy tail and comical fox features, energetically moves to an unseen beat, captivating a group of seated students in the background. The mascot's exaggerated dance steps, set against the backdrop of a sunny day on campus with students enjoying the outdoors, adds to the festive atmosphere. Throughout the performance, the fox mascot continues to dance animatedly, drawing laughter and applause from the surrounding students.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves of the student in the red fox mascot costume in the video are not smooth and coordinated, with sudden changes in the limbs in the middle frames."
}
] |
seed44_1150
|
videos/HRA_part1/1150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy gerbil dons a miniature engineer's outfit, complete with a hat, as it energetically operates toy-sized control panels in a fantasy power plant. The vibrant room, filled with dancing lights and kinetic energy, pulses to an upbeat tune. The gerbil, now spinning gleefully on a tiny dance floor, is bathed in the colorful glow, its cheeks puffed out in pure delight. Surrounded by cartoonish power plant machinery, the gerbil continues its joyful dance, embodying a unique fusion of industrial might and playful abandon.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3096
|
videos/HRA_part2/3096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, tropical dry forest, a distinguished film director, clad in a beige safari jacket, beige pants, and a wide-brimmed hat, meticulously orchestrates a captivating scene. Surrounded by the rich tapestry of nature, featuring tall, sun-bleached trees and vibrant green foliage, the director focuses intently on the action unfolding before him. The scene transitions to a stunning natural pool, where an athletic swimmer, wearing a black swimming cap and goggles, slices through the crystal-clear water with powerful strokes, showcasing grace and strength. The director watches from the edge, his expression a blend of concentration and appreciation for the beauty of both the forest and the swimmer's fluid movements.]"
},
{
"from": "gpt",
"value": "Bad. The swimmer in the video swims very unsmoothly, with uncoordinated movements, and the director's actions are also slightly uncoordinated."
}
] |
seed42_1026
|
videos/HRA_part0/1026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a beige jacket, black t-shirt, and khaki pants, stands thoughtfully at a hot springs site, contemplating a unique shot. Suddenly, a rhinoceros emerges from the mist, leaping gracefully over a small pond within the springs. The director watches intently, camera in hand, ready to capture the extraordinary moment as the sun sets behind, casting a golden hue over the scene. The rhinoceros, now the central figure, jumps with surprising agility amidst the steamy waters, creating an unforgettable juxtaposition of nature and wildlife against the backdrop of the director's vision.]"
},
{
"from": "gpt",
"value": "Bad. The rhinoceros appears with five legs, and at the end of the video, it becomes deformed, with its body shrinking and head disappearing."
}
] |
seed44_2401
|
videos/HRA_part1/2401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, athletic woman with a pixie haircut, wearing a blue t-shirt and khaki cargo pants, kneels on a concrete floor in a garage. She focuses intently on repairing a mountain bike, her tools spread out on a red mat beside her. Her blue scrubs, adorned with colorful medical symbols, hint at her profession as a nurse. In another angle, she lifts the bike, revealing her strength and determination. Throughout, she exhibits a confident smile, demonstrating her dual passions for healthcare and cycling. The garage space is filled with various tools and equipment, emphasizing her hands-on approach to both her work and hobbies.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1052
|
videos/HRA_part0/1052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid outdoor scene, three young children sprint across a vast, sunlit chaparral landscape, their movements captured in slow motion to emphasize their carefree joy. Dressed in a red shirt, blue shorts, and black shoes, one child leads the pack, arms outstretched like wings. Another child, wearing a yellow top, green shorts, and brown sandals, follows closely behind, laughing gleefully. Trailing just behind, a third child in a purple dress and pink sneakers completes the trio, their faces alight with excitement as they race beneath the clear blue sky. The chaparral vegetation, with its rugged shrubs and distant mountain backdrop, provides a natural, textured setting for their energetic play.]"
},
{
"from": "gpt",
"value": "Bad. The child in the red clothes has a third hand, and the child in the yellow clothes has a deformed arm. Both children's hair does not conform to reality."
}
] |
seed42_1219
|
videos/HRA_part0/1219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic classroom adorned with space-themed decorations, a dedicated teacher, wearing a sleek silver jumpsuit, instructs students about the cosmos. Suddenly, the focus shifts to a grand, romantic Space wedding, where the bride, dressed in a stunning, traditional white gown with a flowing veil, and the groom, in a classic black tuxedo, exchange vows against a backdrop of stars and planets. Following the ceremony, the newlyweds, now wearing matching white spacesuits, joyfully run together down a long, narrow corridor aboard a spaceship, their laughter echoing in the weightless environment.]"
},
{
"from": "gpt",
"value": "Normal. The upper body movements are not coordinated."
}
] |
seed42_2076
|
videos/HRA_part0/2076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, cheerful nurse, wearing a white uniform and a badge, is seen running through a lush, green landscape dotted with tall trees and vibrant vegetation. In the distance, a serene hot springs oasis comes into view, its steam gently rising against the backdrop of a clear blue sky. The nurse, with a backpack and running shoes, continues her jog towards this peaceful destination, her movements fluid and energetic. Upon arrival, she pauses to enjoy the tranquil atmosphere, the steam from the hot springs swirling around her, before continuing her run along the scenic path that meanders through the verdant scenery.]"
},
{
"from": "gpt",
"value": "Normal. The nurse is missing a badge."
}
] |
seed46_2358
|
videos/HRA_part2/2358.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone musician, garbed in a silver spacesuit, traverses an interplanetary trade route marked by luminescent orbs floating in zero gravity. His suit, adorned with musical notes, indicates his profession. He crawls through the cosmic path, surrounded by stars and galaxies, carrying a futuristic instrument that resembles a hybrid between a guitar and a synthesizer. His journey is filled with determination, as he navigates the vast expanse of space, seeking new melodies among the stars. The trade route, bustling with alien spacecraft, highlights the universal language of music, connecting different worlds through sound and rhythm.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a distorted body, head, hands, and legs."
}
] |
seed42_2641
|
videos/HRA_part0/2641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 city scene, a waiter wearing a black apron over a white shirt is diligently wiping tables outdoors, where various shops with colorful awnings line the street. A friendly-looking golden retriever dog, possibly the waiter's pet, sits attentively nearby, watching him work. The atmosphere is lively, with passersby and the sounds of city life in the background, creating a dynamic and engaging environment. The waiter's focused expression and the dog's patient demeanor add a touch of warmth to the urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's hand in the video is distorted and deformed."
}
] |
seed44_2389
|
videos/HRA_part1/2389.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 person wearing a brown bear costume and another individual, both standing in a lush green forest, engage in playful interaction. The person in the bear suit wipes their face with a cloth, as if perspiring from the heat inside the costume, while the other person looks on with amusement. The vibrant greenery of the forest and the clear, sunny sky provide a cheerful backdrop for this lighthearted moment between friends, one of whom is dressed as a bear, playfully wiping their face as they enjoy each other's company in the great outdoors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2232
|
videos/HRA_part0/2232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a green apron over a gray shirt and dark pants, runs down a dimly lit corridor in a large cinema complex. The hall is lined with red carpeting and features a series of doors leading into various screening rooms. The man's facial hair and glasses are distinctive, and he carries a cleaning tool in his right hand. As he sprints, his eyes are set forward, and he passes by a sign with movie titles and showtimes, creating a sense of urgency in the vast, quiet space. The scene captures the hurried pace and isolated environment of the janitor's duties within the cinema.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate cleaning tools, glasses, or signs."
}
] |
seed42_1398
|
videos/HRA_part0/1398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with curly brown hair tied back in a ponytail and wearing a red apron over a casual outfit stands in a modern kitchen, illuminated by bright overhead lights. She focuses intently on slicing a red bell pepper on a white cutting board, her silver ring catching the light. Next, she stirs a sizzling pan of vegetables on a stainless steel stove, steam rising from the pan. Then, she adds a pinch of salt and a sprinkle of fresh herbs to the dish, enhancing its aroma. Finally, she smiles as she plates the finished meal, garnishing it with a sprig of parsley, ready to serve a delicious dinner.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2986
|
videos/HRA_part0/2986.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cheerful nurse wearing a green uniform jumps playfully over a fallen log in the lush rainforest, surrounded by vibrant green foliage, exotic flowers, and towering trees. She lands gracefully on the moss-covered ground, her smile conveying a sense of freedom and joy. Nearby, a small waterfall cascades into a crystal-clear pool, adding to the serene atmosphere of the tropical environment. The nurse's unexpected presence in the rainforest, combined with her playful leap, creates a captivating and memorable scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1861
|
videos/HRA_part0/1861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a crisp white shirt, black vest, and tie, stands in a cozy, warmly-lit room with wooden floors. He gently caresses a fluffy, white cat sitting on a table covered with a red checkered cloth. Beside him, a glass bottle and a wine glass are visible. The cat, adorned with a pink ribbon, looks content as it receives affection from the attentive waiter, whose demeanor suggests a tender, caring personality.]"
},
{
"from": "gpt",
"value": "Normal. The server's action of petting the cat in the video is not smooth and coordinated."
}
] |
seed42_2714
|
videos/HRA_part0/2714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom aboard a space station, a compassionate teacher, dressed in a blue jumpsuit with patches and pins adorning her chest, gently caresses the head of a curious alien student. The student, with large, expressive eyes and a small, round body, sits attentively at a desk cluttered with advanced technology and educational tools. The room is filled with natural light from a large window showing a stunning view of Earth and the vast cosmos beyond, emphasizing the peaceful diplomatic mission of education among the stars.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's hands are distorted, and the student's head is not fully generated."
}
] |
seed44_1810
|
videos/HRA_part1/1810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrial engineer in a gray shirt and khaki pants stands confidently in a modern factory, surrounded by large machinery and pipes, with a swimming pool visible through a window in the background. He then walks purposefully toward the camera, passing by the heavy industrial equipment, with the pool still visible in the distance. Next, he is seen from behind, approaching a large machine with pipes, while the pool can be glimpsed outside through the window. Finally, the engineer takes a break from his work, enjoying a refreshing swim in the outdoor pool, which is now the focal point, set against the backdrop of the industrial facility.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers were not fully generated."
}
] |
seed42_1630
|
videos/HRA_part0/1630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, passionate writer in a vibrant red dress is captured in a series of captivating moments, all set within the lush, golden ambiance of an orchard during autumn. She begins by standing pensively, holding a vintage typewriter, embodying creativity and inspiration. Next, she's shown mid-dance, arms elegantly extended, her movements expressive and free, the typewriter now resting on the ground, symbolizing her liberation from constraints. In another scene, she leans back, laughing joyously, her feet slightly off the ground, the typewriter still visible, highlighting her uninhibited spirit. Lastly, she strikes a confident pose, hands on hips, with a serene smile, the typewriter by her side, signifying her connection to both art and nature. Throughout, the orchard's warm colors and abundant fruit provide a rich, textured setting for her expressive journey.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2600
|
videos/HRA_part2/2600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blend of scenes, a majestic African lion strides powerfully across a vast, barren asteroid, its golden coat contrasting starkly against the monochrome landscape pockmarked with craters. The lion, undeterred by the alien environment, explores the rocky terrain as if it were a savannah, with distant stars and a nebula providing a cosmic backdrop. Nearby, a futuristic mining facility operates diligently, extracting precious resources from the asteroid's surface, emphasizing the juxtaposition of nature and technology in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. No generation of mining facilities."
}
] |
seed46_2734
|
videos/HRA_part2/2734.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic, silver-furred wolf stands on a platform at the base of a colossal space elevator, its massive structure stretching into the starlit sky. The wolf gently caresses the sleek, metallic surface of the elevator with its snout, as if acknowledging a familiar presence. Its piercing golden eyes reflect the surrounding ethereal lights, adding an otherworldly touch to the interaction between the creature and the futuristic architecture. The platform is surrounded by a vast, moonlit landscape, with distant mountains silhouetted against the night sky, creating a dramatic contrast to the looming space elevator.]"
},
{
"from": "gpt",
"value": "Bad. The wolf's head is twisted in the video."
}
] |
seed44_3014
|
videos/HRA_part1/3014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its bright green body with yellow fins and a striking pink head, swims gracefully in clear blue waters. Its unique appearance is highlighted as it explores a coral reef ecosystem, surrounded by various marine life. The fish's body, featuring bold colors and patterns, contrasts beautifully with the sandy seabed and lush underwater vegetation. As it moves, the parrotfish reveals its distinctive form and coloration, making it a captivating subject in the rich tapestry of oceanic biodiversity.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2764
|
videos/HRA_part2/2764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone penguin stands majestically on a frosty, ice-covered shore, its sleek black and white feathers glistening under the soft, diffused light of an overcast sky. The penguin, with its round body, small flippers, and distinctive tuxedo-like appearance, looks out to the vast, icy sea, creating a sense of solitude and resilience in the harsh Antarctic environment. The scene is framed by rugged, snow-capped mountains in the distance, emphasizing the penguin's natural habitat and the stark beauty of its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1895
|
videos/HRA_part2/1895.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid outdoor setting, two young boys, one wearing a red t-shirt and the other in a white shirt, engage with a curious monkey sitting on a wooden table. The monkey, holding a banana, looks intently at the children. One boy, in a red t-shirt, wipes the monkey's face with a cloth, while the other, in a white shirt, watches with amusement, capturing a tender moment of interaction between the children and the primate. The scene is set against a backdrop of lush greenery and a clear blue sky, adding to the idyllic atmosphere of the encounter.]"
},
{
"from": "gpt",
"value": "Bad. The boy in the red T-shirt's hand, the monkey's face, and the banana are generated abnormally; the boy's hand and the banana suddenly deform or disappear and reappear in the middle frames."
}
] |
seed46_1873
|
videos/HRA_part2/1873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape dominated by skyscrapers, a young female cashier, dressed in a black apron over a white shirt and black pants, stands behind a checkout counter in a modern, glass-walled convenience store. She gently caresses the edge of the counter with her right hand, her eyes softly closed, as if cherishing a moment of peace amidst the urban rush. The city's towering buildings loom outside the large windows behind her, contrasting with her intimate gesture.]"
},
{
"from": "gpt",
"value": "Normal. No black pants were generated."
}
] |
seed42_3162
|
videos/HRA_part0/3162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant scene unfolds where a musician, clad in a leopard-print jacket and dark sunglasses, passionately plays a saxophone under a spotlight. Nearby, a cheetah with a golden collar and bell, standing on its hind legs, dances gracefully to the music. The setting is a stage decorated with colorful neon lights, creating an electrifying atmosphere as the audience watches in awe. The musician's performance is captivating, and the cheetah's movements are fluid and expressive, both in perfect harmony with the upbeat jazz melody.]"
},
{
"from": "gpt",
"value": "Bad. The musician's hands are deformed in the video, and the cheetah is generated abnormally."
}
] |
seed46_1488
|
videos/HRA_part2/1488.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned firefighter, clad in full gear and a yellow fire-resistant jacket, stands against the backdrop of a blazing inferno, his helmet askew to reveal a focused gaze. Amidst the chaos, he stares intently at the raging fire, his face a mask of determination and resolve. His eyes, shielded by a clear protective visor, never waver from the flames, conveying a sense of duty and bravery in the face of danger. Behind him, the fire rages on, casting an orange glow on his figure, highlighting his steadfast stare and unwavering commitment to extinguishing the blaze.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1076
|
videos/HRA_part1/1076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vivid scene, a janitor, dressed in a traditional uniform with a helmet, rides a majestic jaguar across a Mars-like landscape filled with orange sand dunes under a pinkish-red sky. The jaguar, adorned with a decorative saddle and reins, gallops gracefully, leading the viewer into a dreamlike world. The janitor then dismounts, exchanging the jaguar for a spirited Martian horse, which has a reddish-brown coat and carries him across the alien terrain with ease. The action shifts to a close-up of the janitor crawling on the Martian soil, examining the unique rock formations and textures of this extraterrestrial environment with fascination and curiosity.]"
},
{
"from": "gpt",
"value": "Normal. No Martian horse let the cleaner ride; the cleaner does not descend off the horse."
}
] |
seed44_2649
|
videos/HRA_part1/2649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a navy blue NASA spacesuit with patches and a white name tag, walks purposefully down a pristine, metallic corridor aboard a futuristic space station. The station's interior is illuminated by soft, ambient lighting, and features advanced technology, including touch-screen panels and monitoring equipment, highlighting the cutting-edge nature of the facility. The doctor's movements are unhurried yet deliberate, conveying a sense of routine and familiarity within the microgravity environment. The backdrop showcases the intricate design of the space station, with various modules visible through windows, offering glimpses into different areas where scientific research and daily activities take place.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3058
|
videos/HRA_part2/3058.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious monkey, dressed in a red life jacket, sits on a wooden pier extending over a serene body of water, surrounded by lush greenery and tall trees. The monkey then playfully jumps into the clear blue water, creating ripples that spread outward. It swims energetically, its small arms paddling through the water, while a pair of sunglasses float nearby, adding a touch of whimsy to the scene. The monkey eventually climbs back onto the pier, shaking off droplets of water, with the sun casting a warm glow over the entire setting.]"
},
{
"from": "gpt",
"value": "Bad. The monkey's body is twisted, its head is twisted, its legs are twisted, and its arms are twisted."
}
] |
seed46_1080
|
videos/HRA_part2/1080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna dotted with small shrubs and trees, a large herd of buffalo gathers. Suddenly, one buffalo, distinct with its massive horns and dark brown fur, begins to move rhythmically, almost dancing, against the backdrop of the herd and the distant, hazy mountains. Its movements are energetic yet controlled, as if performing a ritualistic dance under the watchful eye of the herd. The camera focuses on this unique spectacle, capturing the buffalo's dance in the midst of its natural habitat, surrounded by the rest of the herd and the serene beauty of the African landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2997
|
videos/HRA_part2/2997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush tropical dry forest, two smiling children, a boy and a girl, are seen caressing a friendly wild animal, possibly a capybara, against the backdrop of a dense forest with tall trees and patches of sunlight filtering through the leaves. The children wear simple clothing suitable for outdoor adventures, and their joyful expressions convey a sense of connection with nature. They sit on the forest floor covered with dry leaves and twigs, surrounded by various plants and vegetation typical of a tropical dry forest environment. The scene captures a tender moment of human-animal interaction in a natural setting, highlighting the innocence and curiosity of childhood amidst the wonders of the natural world.]"
},
{
"from": "gpt",
"value": "Bad. It generates three children."
}
] |
seed42_1813
|
videos/HRA_part0/1813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and khaki pants, stands in the midst of a vast desert landscape, the golden sand stretching to the horizon under a clear blue sky. Holding a paintbrush in one hand, he wipes it across a large canvas, which rests on an easel, revealing strokes of orange and yellow that mirror the fiery sunset in the background. The artist's face is intense, his eyes fixed on the canvas as he captures the essence of the desert's beauty, with the sun's last rays casting long shadows across the dunes.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1075
|
videos/HRA_part2/1075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and khaki pants, stands in a lush, green forest clearing, gently wiping mud off the antlers of a majestic deer using a soft cloth. The deer, with large, inquisitive eyes, tolerates the man's ministrations, standing still as the man carefully cleans each tine of the impressive antlers. Sunlight filters through the canopy above, casting dappled shadows on the scene below, highlighting the tender interaction between the man and the wild creature.]"
},
{
"from": "gpt",
"value": "Normal. The video shows a scene with three hands, indicating an issue with the character's hand generation."
}
] |
seed44_3210
|
videos/HRA_part1/3210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 setting, a renowned actor portrays a courageous character who masterminds a daring bank robbery on a distant planet. Dressed in a high-tech suit, the actor stealthily maneuvers through the alien bank, filled with luminescent crystals and advanced security systems. In a surprising twist, the actor gently caresses a small, friendly porcupine-like creature, which assists in the heist by using its quills to disable the security mechanisms. The scene combines elements of action, suspense, and unexpected tenderness in the vastness of outer space.]"
},
{
"from": "gpt",
"value": "Bad. The animal's head is twisted in the video."
}
] |
seed46_2806
|
videos/HRA_part2/2806.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, wearing a dark blue jacket, beige pants, and carrying a brown backpack, runs along the docks on a misty day, passing by large ships and industrial buildings. He stops momentarily to gaze at the water, his reflection visible in the wet pavement. Continuing his run, he passes wooden benches and green spaces, with the city skyline in the distance. Throughout his journey, he remains engrossed in his thoughts, occasionally glancing down at a notebook tucked into his backpack, the colors of the docks' wood and metal contrasting against the muted tones of the surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are deformed, his face is deformed, his feet are twisted, and the chairs by the roadside are deformed."
}
] |
seed46_293
|
videos/HRA_part2/293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic lion, defying expectations, swims powerfully through a tranquil body of water, its golden coat glistening as it propels itself forward with muscular strokes. Its piercing gaze is fixed ahead, conveying determination and grace in this unusual aquatic setting. The lion's head remains above the waterline, mane billowing softly, while its body undulates beneath the surface, showcasing an unexpected display of strength and agility in the liquid environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1178
|
videos/HRA_part1/1178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene reminiscent of a futuristic sci-fi film, a CGI-generated cobra, adorned with bioluminescent patterns, slithers across a metallic, interstellar platform set against the backdrop of a cosmic wormhole. The snake's scales shimmer with neon colors, creating a mesmerizing contrast against the cold, metallic surface. As it moves, the cobra passes by a series of glowing control panels, hinting at advanced technology integrated into the environment. In the distance, the swirling vortex of the wormhole pulses with vibrant hues, adding an element of mystery and wonder to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The cobra's head in the video is generated abnormally, and the body is generated too long."
}
] |
seed42_2602
|
videos/HRA_part0/2602.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 starling perches on a branch, its iridescent feathers shimmering in the sunlight, showcasing shades of green and purple against a blurred background of lush green foliage. The bird's beady eye and curved beak are sharply detailed, while its body language suggests alertness. Moments later, it takes flight, wings spread wide, revealing the full spectrum of its plumage's colors against the clear blue sky. The video concludes with a close-up of the starling's head, its distinctive features and vibrant feathers displayed prominently against a softly blurred green backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_250
|
videos/HRA_part1/250.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 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 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": "Bad. The little boy's movements in the video are not smooth."
}
] |
seed42_1673
|
videos/HRA_part0/1673.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly imagined scene, a majestic African lion, distinguished by its thick mane and muscular build, runs across a futuristic landscape where solar sails, vast and gleaming, catch the sunlight high above like enormous kites adrift in the sky. The lion's powerful strides and focused gaze contrast beautifully with the serene, almost surreal sight of the solar sails, which seem to float effortlessly in the still air, their surfaces shimmering with reflected light. This unlikely juxtaposition of nature and technology creates a striking and memorable visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_306
|
videos/HRA_part1/306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, donning a white tank top, beige shorts, and brown leather sandals, assembles a wooden table in a bright room with large windows and a view of greenery outside. He starts by carefully examining the instructions, his brows furrowed in concentration. Next, he skillfully uses a screwdriver to attach the legs to the tabletop, showcasing his handyman abilities. Then, he wipes his forehead with the back of his hand, a small smile on his lips, indicating satisfaction in his progress. Finally, he stands back to admire the finished product, hands on hips, revealing the completed table in the well-lit space, surrounded by lush vegetation visible through the window.]"
},
{
"from": "gpt",
"value": "Bad. The male actor's movements in the video are not smooth."
}
] |
seed42_1394
|
videos/HRA_part0/1394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome waiter, donning a classic black vest, crisp white shirt, and black tie, diligently cleans the expansive windows of a charming bistro. The scene is set against a vibrant city backdrop, with the golden hour casting a warm glow. He meticulously wipes the glass, revealing the bustling café interior, filled with patrons enjoying their meals. The waiter's attention to detail is evident as he ensures every corner of the window is spotless, enhancing the inviting atmosphere of the establishment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1564
|
videos/HRA_part1/1564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, dressed in a white shirt and brown trousers, leads a llama on a leash through the verdant pathways of a zoological park, surrounded by lush greenery and exotic plants. The llama, adorned with a decorative blanket and colorful tassels, follows obediently as the farmer guides it past various enclosures housing different species. They walk alongside a water feature, such as a pond or stream, adding to the tranquil atmosphere of the park. The farmer's attire complements the natural surroundings, creating a harmonious scene as they navigate the scenic route together.]"
},
{
"from": "gpt",
"value": "Normal. The llama's body structure in the video is abnormal, with scenes showing five legs; there are issues with the generation of the human hand and the llama's head."
}
] |
seed46_2329
|
videos/HRA_part2/2329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, dressed in a yellow vest and hard hat, stands in awe, experiencing time dilation as he watches a kangaroo jump in slow motion against a backdrop of a bustling city skyline at sunset. The kangaroo, mid-leap, appears weightless and graceful, its powerful hind legs propelling it forward. The worker's expression reflects a mix of surprise and fascination, as if witnessing a surreal moment where the laws of physics seem to bend. The scene is bathed in golden hour light, adding to the dreamlike quality of the encounter.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo in the video is severely distorted and deformed, with its head and tail suddenly swapping positions in the middle frames."
}
] |
seed46_1584
|
videos/HRA_part2/1584.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, wearing a yellow high-visibility vest, blue jeans, and a gray shirt, dances with uninhibited joy in the vastness of a desert canyon. The landscape features towering red rock formations, lush greenery, and a distant mountain range under a clear blue sky. The janitor, holding a broom as if it were a dance partner, spins and twirls with abandon, embodying a spirit of freedom and happiness amidst the stark beauty of nature. As the camera pans out, the scale of the canyons becomes apparent, contrasting the figure of the dancing janitor against the immense natural surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1384
|
videos/HRA_part1/1384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, spiky European hedgehog runs energetically across a lush, green garden, its tiny legs moving swiftly beneath it. The hedgehog, with its distinctive white-tipped spines, navigates through the foliage with determination, its snout pointed forward. In another scene, the hedgehog continues its journey, now scampering across a wooden deck, its movements quick and agile. The video captures the hedgehog's active nature, showcasing its ability to navigate various terrains with ease, all under the cover of night, as indicated by the dimly lit surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2853
|
videos/HRA_part0/2853.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 musician's hands are distorted, the object in hand is distorted, the face is distorted, the feet are distorted, the dingo's face is slightly distorted, and the legs are distorted."
}
] |
seed46_1380
|
videos/HRA_part2/1380.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ruggedly handsome actor, sporting a full beard, stands in a rural setting under an overcast sky, gently caressing a brown horse with white markings. He wears a gray shirt, blue jeans, and a brown belt, while the horse stands placidly in a grassy area dotted with small trees. The actor's affectionate interaction with the animal conveys a sense of peace and connection in the pastoral environment. The horse, with its mane and tail blowing slightly in the wind, is clearly comfortable with the actor, who continues to stroke its neck with tenderness and respect.]"
},
{
"from": "gpt",
"value": "Bad. The video generates the horse's tail behind the person, which is unrealistic; there are issues with the generation of the person's hand and the horse's face."
}
] |
seed46_2267
|
videos/HRA_part2/2267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a white shirt, black vest, and black trousers, diligently mops the floor of an empty restaurant during the daytime. The space is notably devoid of customers, with only a single table set with plates and cutlery visible in the background. The waiter's focus is intense as he works, pushing the mop back and forth across the smooth, light-colored tile flooring. His movements are methodical and purposeful, emphasizing his commitment to maintaining a clean dining environment. The natural light filtering through the windows highlights the cleanliness of the space, further emphasizing the waiter's efforts.]"
},
{
"from": "gpt",
"value": "Normal. The person's face, arms, hands, feet, and the mop in their hand are distorted in the video."
}
] |
seed46_1730
|
videos/HRA_part2/1730.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown shirt and glasses, is seen in a unique scenario, engaging with a hyena at a public swimming pool. The director, standing at the edge of the pool, interacts with the wild animal, which is swimming in the water, creating an extraordinary juxtaposition of human and beast in an unexpected urban setting. The director's attire, complete with brown shirt and glasses, contrasts with the untamed presence of the swimming hyena, capturing a surreal and captivating moment.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the director standing at the edge of the pool."
}
] |
seed46_2877
|
videos/HRA_part2/2877.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a black leather jacket, gray jeans, and a black beret, stands on a lush green hillside under a clear blue sky, engaging in an eccentric dance. In the foreground, a majestic leopard, its golden eyes locked on the director, prowls among the tall grass, adding a sense of wild energy to the scene. The director's animated movements contrast with the leopard's watchful stillness, creating a captivating interplay between human creativity and untamed nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2273
|
videos/HRA_part0/2273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting illuminated by vibrant neon lights, a diligent worker clad in a gray jumpsuit and helmet stands on a sleek, anti-gravity vehicle. The vehicle, featuring a metallic finish and aerodynamic design, hovers above a clean, white platform. The worker is engaged in wiping the vehicle's surface with a cloth, ensuring its spotless condition. Behind the scene, a vast hangar filled with advanced technology and equipment can be seen, emphasizing the high-tech environment in which the worker operates. The worker's focused expression and meticulous attention to detail highlight their commitment to maintaining the anti-gravity vehicle's pristine state.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2089
|
videos/HRA_part2/2089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a creative blend of scenes, two smiling children, a boy in a blue jacket and a girl in a pink jacket, walk alongside a life-sized zebra puppet, its distinctive black and white stripes vivid against a neutral background. The children hold hands, looking up in wonder, as the zebra puppet, operated by an unseen handler, walks alongside them. Behind them, a large, high-definition screen displays a captivating visualization of dark matter research, featuring swirling galaxies and complex data visualizations, seamlessly merging elements of nature, childhood innocence, and scientific exploration.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, the hand is twisted, the face is twisted, the legs are twisted, the zebra's face is slightly twisted, and the legs are twisted."
}
] |
seed44_1516
|
videos/HRA_part1/1516.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious male engineer, wearing a blue button-down shirt and glasses, meticulously irons his clothes in a modestly furnished room with a wooden floor and cream walls. He stands at an ironing board covered with a white cloth, carefully smoothing out wrinkles in a garment. The room is illuminated by natural light from a window behind him, casting a warm glow over the scene. On the wall to his right, a large painting in shades of green adds a splash of color to the otherwise simple space. Beside the window, a desk with a laptop and engineering blueprints hints at his professional life, while a shelf filled with books and a houseplant brings a personal touch to the environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_17
|
videos/HRA_part2/17.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated teacher, wearing a vibrant yellow raincoat and matching boots, stands in the shallow waters of a lush wetland, surrounded by cattails and water lilies. She holds a large, transparent jar filled with water and aquatic insects, engagingly teaching a group of students who sit cross-legged nearby, dressed in waterproof jackets and pants. The students attentively listen, some with binoculars around their necks, as they learn about the wetland ecosystem. The teacher then leads the students in a safe, supervised activity where they wade into the water, using nets to catch and examine small fish and plants, all while standing in the calm, knee-deep water of the wetland.]"
},
{
"from": "gpt",
"value": "Bad. No generation of students wearing waterproof jackets and pants, students surrounding teachers with binoculars around their necks, and students standing in knee-deep water holding nets to capture small fish and plants."
}
] |
seed42_266
|
videos/HRA_part0/266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, identifiable by his black-framed glasses and neat appearance, stands in a modern kitchen with a clean, white countertop and stainless steel appliances. He wears a white chef's coat over a blue shirt and dark pants, and sports a neatly trimmed beard. He focuses intently on his cooking task, holding a whisk in his right hand and stirring a mixture in a bowl with precision and care. Behind him, a window allows natural light to illuminate the space, adding to the clean and professional atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's movements in the video are basically normal, but there is some lack of coordination."
}
] |
seed42_1813
|
videos/HRA_part0/1813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a brown jacket and khaki pants, stands in the midst of a vast desert landscape, the golden sand stretching to the horizon under a clear blue sky. Holding a paintbrush in one hand, he wipes it across a large canvas, which rests on an easel, revealing strokes of orange and yellow that mirror the fiery sunset in the background. The artist's face is intense, his eyes fixed on the canvas as he captures the essence of the desert's beauty, with the sun's last rays casting long shadows across the dunes.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1134
|
videos/HRA_part0/1134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, balding with graying hair, meticulously dusts furniture in a large, elegant room filled with antique wooden furnishings, including a desk, a table, and a shelf. He is dressed in a simple gray shirt and brown trousers, moving methodically around the space. He pauses to look at an item on the desk, perhaps a photo or a book, before continuing his work. The room is bathed in warm, golden light from windows not shown, highlighting the dust motes swirling in the air as he works. He finishes by straightening a framed picture on the wall, ensuring everything is perfectly aligned, demonstrating his pride in his work.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1776
|
videos/HRA_part1/1776.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing a full-body red fox mascot costume, performs an entertaining dance routine in the middle of a lively campus quad. The mascot, with its distinctive bushy tail and comical fox features, energetically moves to an unseen beat, captivating a group of seated students in the background. The mascot's exaggerated dance steps, set against the backdrop of a sunny day on campus with students enjoying the outdoors, adds to the festive atmosphere. Throughout the performance, the fox mascot continues to dance animatedly, drawing laughter and applause from the surrounding students.]"
},
{
"from": "gpt",
"value": "Normal. The fox's head and hands, as well as the students' faces, have issues in the video."
}
] |
seed44_2185
|
videos/HRA_part1/2185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an unexpected juxtaposition, a small, fluffy hamster wearing a red life jacket floats in a clear plastic ball filled with water. This unique scene unfolds against the backdrop of an industrial area, complete with factories, smokestacks, and large metal containers. The hamster appears content and relaxed, paddling gently within the ball as it bobs on the water's surface near the edge of a pool. The industrial landscape, featuring tall buildings, cranes, and machinery, provides a striking contrast to the innocent and playful hamster enjoying its unconventional swim.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2722
|
videos/HRA_part0/2722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green park under the bright summer sun, two happy children, a boy and a girl, are energetically chasing each other on the grass. The boy, wearing a red t-shirt and blue shorts, stretches out his hands, playfully trying to catch the girl. She, donned in a yellow dress and sandals, giggles as she skillfully dodges him, both enjoying the thrill of the chase. They run amidst a scattering of colorful wildflowers, their laughter echoing through the serene environment, encapsulating the joy and innocence of childhood.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1720
|
videos/HRA_part0/1720.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large grouper fish, displaying a mottled brown and white skin pattern, swims serenely in clear blue waters, its wide mouth and curious eyes prominent. It passes by a vibrant coral reef, home to smaller, colorful fish darting in and out of the crevices. The sunlight filters through the water, casting dappled light on the sandy ocean floor and highlighting the intricate details of the grouper's body and its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_107
|
videos/HRA_part2/107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 temperate grassland, a dedicated doctor, clad in a white lab coat, blue shirt, and khaki shorts, runs along a dirt path, passing by tall, swaying grass and isolated trees under a partly cloudy sky. The doctor, wearing sunglasses, a white medical coat, blue t-shirt, and brown shorts, sprints with focused determination across the open landscape, the scenery punctuated by distant hills and clear blue skies. Throughout the video, the doctor maintains a steady pace, showcasing resilience and strength in the midst of nature's tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands are distorted, the face is twisted, and the legs are deformed."
}
] |
seed46_1269
|
videos/HRA_part2/1269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, brown capybara slowly crawls through a lush, green meadow dotted with small shrubs and trees, its round ears and alert eyes scanning the environment. It moves deliberately, showcasing its unique gait, as it navigates the vibrant grassland under a bright, sunny sky. The rodent's textured fur glistens in the sunlight, highlighting its wet, semi-aquatic nature, as it continues its unhurried crawl across the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's face and legs are distorted in the video."
}
] |
seed46_1318
|
videos/HRA_part2/1318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 setting illuminated by neon lights, a police officer, clad in a silver metallic uniform with a red sash, stands solemnly. Beside him, a robotic dog with glowing blue eyes sits attentively. The officer holds a ceremonial staff, participating in a galactic religious ceremony on a vast, holographic dance floor. Alien beings of various species gather around, some in traditional garb, others in futuristic attire, all engaged in a synchronized dance that combines elements of ancient rituals with modern electronic beats. The dance is a ritual to honor the cosmic connection between law enforcement, technology, and spirituality in this interstellar society.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the face is distorted, and the dog's face is also twisted."
}
] |
seed42_2434
|
videos/HRA_part0/2434.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda, donning a red-and-white striped shirt, black pants, and a green apron, works as a cashier in a grocery store decorated with Chinese lanterns and bamboo plants. The panda, complete with a name tag and a lanyard, interacts with customers at the register. Suddenly, the panda starts dancing joyfully, swaying to an unseen beat, captivating the shoppers with its playful antics. The panda continues to dance, moving around the store, engaging with various customers, who look on in amusement, while still managing to scan items and handle transactions with dexterity. Throughout the scene, the panda's infectious energy fills the store, creating a memorable and delightful shopping experience.]"
},
{
"from": "gpt",
"value": "Bad. The panda's arms and legs show deformities."
}
] |
seed44_1755
|
videos/HRA_part1/1755.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow safety vest and a hard hat, finds himself in a whimsical scenario where he's crawling on his hands and knees through a narrow, dimly lit tunnel. The setting is enhanced by the presence of a stuffed weasel toy, which has somehow joined him on this unusual journey, adding a touch of humor and unexpectedness to the scene. The engineer's serious expression contrasts with the playful atmosphere created by the stuffed animal, making for a unique and memorable visual.]"
},
{
"from": "gpt",
"value": "Normal. The limbs should be on the ground when crawling."
}
] |
seed42_2663
|
videos/HRA_part0/2663.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 desert-dwelling lizard, specifically a Bearded Dragon, is shown swimming underwater in clear, sunlit water. Its body is fully submerged, and it moves gracefully through the water, showcasing its rarely seen aquatic locomotion. The lizard's skin ripples as it propels itself forward, and its claws can be seen extended as it navigates the aquatic environment. The water is crystal clear, allowing for a detailed view of the lizard's texture and movement, contrasting with its typical arid habitat. Sunbeams penetrate the water, illuminating the scene and highlighting the unique sight of a lizard swimming.]"
},
{
"from": "gpt",
"value": "Normal. The lizard in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed42_1600
|
videos/HRA_part0/1600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white hare runs through the city at night, its fur glowing under the streetlights, navigating urban obstacles like a seasoned athlete. It bounds across a busy intersection, dodging between yellow cabs and pedestrians, its powerful legs propelling it forward with graceful ease. The hare then leaps over a low brick wall, lands on the cobblestone sidewalk, and continues its journey, its silhouette framed by the neon signs of city storefronts. Finally, it pauses beneath a towering skyscraper, its large ears perked up, listening to the sounds of the city before continuing its mysterious nocturnal run.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit in the video has a twisted body, twisted paws, a twisted face, and twisted legs."
}
] |
seed44_312
|
videos/HRA_part1/312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 virtual reality environment, a stunningly realistic cheetah lies calmly on a holographic savanna, its sleek golden body adorned with black spots. A person, clad in a full-body VR suit, gently caresses the virtual cheetah's head and back, their movements tracked in detail within the immersive space. The cheetah responds with relaxed body language, indicating comfort and trust, as the human participant experiences the sensation of touching the wild animal through advanced haptic feedback technology. The scene is set against a vast, computer-generated landscape, complete with distant acacia trees and a vivid blue sky, creating an almost tangible illusion of being present in the African wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1041
|
videos/HRA_part1/1041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young boys, one wearing a yellow shirt and the other in red, energetically scrub the bathroom floor with sponges, creating soapy lather. They are focused on their task, with one boy on his hands and knees, working diligently, and the other standing, intently cleaning the wall tiles. The room is filled with the soft sound of water and the energetic movements of the children, who seem to find joy in the chore, transforming the mundane task into a playful activity. Their faces are expressions of determination and delight, turning the bathroom into a space of unexpected fun and teamwork.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.