video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_126
|
videos/HRA_part1/126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, distinguished by his uniform and badge, stands in a cozy kitchen, illuminated by warm overhead lights. He focuses intently on chopping vegetables on a wooden cutting board placed on a granite countertop. The kitchen is modern, featuring stainless steel appliances and a tile backsplash. The officer, displaying a serious yet calm demeanor, proceeds to sauté the vegetables in a large skillet on a gas stove, the flames providing a vibrant contrast to the neutral tones of the kitchen. Throughout, he maintains the disciplined bearing of a law enforcement professional, even as he prepares a home-cooked meal.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a wooden cutting board, nor did it generate scenes of a police officer cutting vegetables and stir-frying."
}
] |
seed44_2600
|
videos/HRA_part1/2600.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": "Good. Basically no issues."
}
] |
seed46_2240
|
videos/HRA_part2/2240.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, clad in a mint green scrubs top and black pants, dances joyfully in the lush, vibrant setting of a subtropical moist forest. The dense green foliage and tall trees surround her, providing a natural, verdant backdrop. Her movements are lively and expressive, conveying a sense of freedom and happiness amidst the rich biodiversity of the forest environment. The sunlight filters through the leaves, casting dappled shadows on her as she gracefully leaps and twirls, embodying the harmony between humanity and nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1489
|
videos/HRA_part0/1489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished chef, donning a pristine white apron and cap, walks barefoot on a serene, sandy beach, with the sun casting a warm glow over the calm sea. He holds a large, colorful fish in his hands, a symbol of fresh ingredients, while the beach's natural beauty, including lush greenery and clear skies, provides a stunning backdrop. The chef's attire, complete with the traditional uniform, contrasts beautifully with the relaxed coastal setting, highlighting his connection to nature and the source of his culinary inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands and feet are distorted in the video, and the fish generation is problematic, with the fish suddenly appearing in the character's hands in the middle frame."
}
] |
seed42_3034
|
videos/HRA_part0/3034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, dressed in a black puffer jacket, dark jeans, and brown boots, shovels snow from a suburban driveway, revealing a sense of determination and hard work. The scene is set in a residential area during daytime, with the actor pushing the snow shovel in a methodical manner. Snowflakes continue to fall gently around him, settling on his black woolen hat and the branches of nearby trees. The actor's focused gaze and steady movements convey a message of perseverance and dedication, even in the midst of a snowstorm.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2613
|
videos/HRA_part0/2613.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in full gear and helmet, finds himself at the base of a towering space elevator, its sleek silver structure piercing the clouds. Against this futuristic backdrop, he begins to dance, his movements a surprising juxtaposition of grace and strength. The flames from a nearby controlled fire flicker and dance along with him, casting an orange glow on the space elevator's metallic surface. The firefighter's steps are lively and expressive, a mix of joy and determination, as he performs beneath the vast starlit sky, the space elevator standing tall and unwavering behind him.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed46_2427
|
videos/HRA_part2/2427.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dons a spacesuit and helmet, adorned with vibrant colors and patterns, resembling a solar sail, as they crawl across a barren lunar landscape, backlit by the Earth's glow. The suit, with its reflective, sail-like design, catches the sunlight, creating mesmerizing reflections and shadows. The artist moves slowly, emphasizing the suit's unique texture and the dramatic contrast between the suit and the moon's surface. This artistic portrayal on the moon's surface, with the distant Earth providing a serene backdrop, highlights the intersection of art and space exploration.]"
},
{
"from": "gpt",
"value": "Normal. The artist's crawling in the video is basically normal, but there is slight movement disharmony."
}
] |
seed42_2659
|
videos/HRA_part0/2659.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 quaint village setting under a clear blue sky, a man wearing a brown jacket and khaki pants kneels on lush green grass, observing a small weasel. The weasel, with its distinct brown fur and white underbelly, crawls along the edge of a weathered stone wall that separates neatly arranged houses from the garden. The man watches intently as the weasel explores its surroundings, highlighting the unexpected encounter between the two in this idyllic residential area.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's movements in the video are not smooth."
}
] |
seed42_1211
|
videos/HRA_part0/1211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a traditional conical hat and a long-sleeved shirt walks down a narrow dirt path bordered by tall grasses and lush greenery, reminiscent of a tropical landscape. In his right hand, he carries a long wooden staff, while his left hand rests gently on his hip. Suddenly, his attention is drawn to a cobra emerging from the foliage, its hood dramatically spread as it rises to meet his gaze. The farmer stops, standing tall and watchful, maintaining eye contact with the snake, creating a tense standoff between man and wild creature. The cobra, with its distinctive hood fully expanded, remains in a defensive posture, mirroring the farmer's cautious stance, as they both seem to assess each other in the midst of the dense vegetation.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's walking in the video is basically normal, with slightly uncoordinated movements."
}
] |
seed42_1041
|
videos/HRA_part0/1041.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."
}
] |
seed44_2577
|
videos/HRA_part1/2577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a dark blue shirt and gray pants, walks purposefully through a modern art gallery, surrounded by large, abstract paintings and sculptures. He pauses to examine a piece closely, his posture attentive and engaged. Continuing his stroll, he passes by minimalist artworks, each occupying its own space within the spacious, well-lit gallery. Finally, he stops before a particularly striking sculpture, tilting his head to study it from different angles, his attire and demeanor contrasting with the avant-garde surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The man walks basically normally in the video, but there is a slight lack of coordination in his movements."
}
] |
seed46_2991
|
videos/HRA_part2/2991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a lush, green meadow, a majestic turkey struts proudly, its vibrant plumage of bronze, green, and copper feathers shimmering in the sunlight. The turkey's head, adorned with fleshy caruncles, bobs with each step it takes on the soft grass. Surrounding the turkey are scattered wildflowers and tall grass, swaying gently in the breeze, creating a picturesque countryside scene. The turkey, undisturbed, continues its regal procession, its wings occasionally flaring out as if presenting its splendid feathers to the viewer. The serene atmosphere is punctuated only by the distant sounds of nature, adding to the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Bad. The turkey's head is deformed in the video, and there is a frame where the turkey has three legs, which is unrealistic."
}
] |
seed44_1917
|
videos/HRA_part1/1917.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully cooked piece of salmon, expertly seared to achieve a perfect golden crust, sits center stage on a white ceramic plate. The salmon boasts a vibrant orange-pink interior, flaky yet moist, with a hint of dill sprinkled over it. Surrounding the fish are vibrant green asparagus spears, steamed to retain their crisp texture and natural color. Completing the dish is a drizzle of creamy sauce, likely a blend of lemon, butter, and capers, adding a touch of elegance and flavor. The plate is garnished with a sprig of parsley, enhancing the visual appeal of this exquisite salmon dish.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3042
|
videos/HRA_part0/3042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gentleman with salt-and-pepper hair sits in a dimly lit room, wearing a gray blazer and a white shirt with the top button undone. He leans back in a brown leather armchair, holding a book in his hands. The camera captures him from the side, highlighting his profile as he reads intently. Beside him, a wooden table holds a glass of red wine, a vintage lighter, and a half-smoked cigar resting in an ashtray. The atmosphere is cozy and intimate, with the warm glow of a nearby lamp illuminating the scene. Behind the chair, a large bookshelf filled with books adds to the scholarly ambiance. The man's eyes are fixed on the pages, his lips slightly parted, indicating deep concentration as he delves into the story. The setting conveys a sense of leisurely intellectual pursuit, with the elements of wine, cigar, and reading material suggesting a refined evening routine.]"
},
{
"from": "gpt",
"value": "Normal. The man's head was not generated, the fingers were deformed, there were issues with the book generation, and the smoke on the book was generated unreasonably."
}
] |
seed46_278
|
videos/HRA_part2/278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clear, close-up underwater shot, a tiny ghost shrimp, nearly transparent with faint grayish-blue hues, scuttles along the sandy bottom of a freshwater environment. Its delicate, see-through body reveals its intricate internal structure, while its antennae and legs move rapidly as it navigates its habitat. Surrounded by small stones and plant roots, the shrimp pauses momentarily before continuing its journey, showcasing its unique ability to blend into the aquatic surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The ghost shrimp walks basically normally in the video, but there is slight uncoordination in the movements."
}
] |
seed42_1348
|
videos/HRA_part0/1348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stylish woman stands tall in the middle of a crosswalk in a bustling city, clad in a long, camel-colored coat that reaches her knees, dark trousers, and high-heeled boots. Her outfit is complemented by a brown leather handbag hanging from her right shoulder. The cityscape behind her, featuring pedestrians, traffic lights, and urban architecture, adds to the dynamic setting. Her confident stance and the urban environment create a captivating scene, with the woman at the center, embodying poise and independence.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3065
|
videos/HRA_part0/3065.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, 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": "Normal. The walking actions of the character in the video are slightly unsmooth."
}
] |
seed42_2867
|
videos/HRA_part0/2867.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic worker, clad in a high-tech silver spacesuit and helmet, walks across the expansive surface of an enormous solar sail, which glimmers under the vivid light of a distant star. The sail, a vast expanse of shimmering material, stretches out behind the figure, capturing the celestial radiance. The worker, equipped with a portable tool kit attached to the suit, is seen moving purposefully along the sail's surface, conducting maintenance or inspection tasks in the vastness of space. The background is filled with the dark void of space, dotted with distant stars, emphasizing the isolation and grandeur of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the future worker in the video are missing, and there are issues with the proportions of the fingers and body."
}
] |
seed42_1338
|
videos/HRA_part0/1338.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A diligent window cleaner, equipped with a squeegee and a bucket of soapy water, stands on a ladder propped against a tall, glass-paneled building. Dressed in a yellow high-visibility vest and dark pants, he methodically wipes the glass, leaving a streak-free shine. The bustling cityscape forms the backdrop, with pedestrians passing by and cars moving on the streets below. The sun casts a golden glow on the scene, highlighting the cleaner's hard work as he moves from pane to pane, ensuring crystal clarity for the occupants inside.]"
},
{
"from": "gpt",
"value": "Normal. The worker's arm and ladder in the video are not fully generated, and there is an issue with the squeegee generation."
}
] |
seed44_2018
|
videos/HRA_part1/2018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a leopard print scarf, sits in a dimly lit room, engaged in caressing a small, furry creature. Behind her, a screen displays complex diagrams related to quantum entanglement experiments, adding a layer of intrigue. Her attire, which includes the eye-catching leopard print accessory, contrasts with the scientific theme of the scene. The focus is on her gentle interaction with the creature, while the backdrop hints at her intellectual pursuits, creating a compelling juxtaposition between the personal and professional aspects of her life.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2394
|
videos/HRA_part1/2394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical, anthropomorphic setting, a weasel, dressed in a white doctor's coat over a blue shirt and tie, crawls on its belly across a cluttered desk filled with medical books and instruments, its eyes intently focused on a miniature stethoscope just out of reach. The desk is awash in a warm, golden light, casting long shadows and highlighting the weasel's determination. Behind the desk, a large window frames a bustling city skyline at sunset, adding a sense of urgency and drama to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's crawling action on the ground in the video is discontinuous and has sudden changes."
}
] |
seed44_297
|
videos/HRA_part1/297.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the lush, green undergrowth of a temperate rainforest, a wildlife worker, clad in a khaki shirt and hat, carefully crawls on his hands and knees, examining the rich flora. Nearby, a chimpanzee, adapted to this cooler, wetter habitat, curiously observes the human from behind a moss-covered tree trunk, its fur darker due to the climate. The scene captures the unique bond between the worker, dedicated to studying and preserving this ecosystem, and the chimpanzee, a rare sight in temperate rainforests, both interacting within the dense, verdant surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow 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": "Good. Basically no problem."
}
] |
seed44_1391
|
videos/HRA_part1/1391.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling a young Tom Hardy, wearing a futuristic space suit with a gorilla mascot emblem, embarks on an exhilarating lunar buggy ride across a desolate moon landscape, capturing the essence of adventure in outer space. Later, he is seen walking purposefully, leading the lunar buggy with ease, as if navigating through a challenging mission. The actor then pauses to admire the vast, starry expanse, evoking a sense of awe and wonder, before continuing his journey, showcasing determination and resilience. Throughout the scenes, the lunar buggy, with its distinctive design and rugged tires, remains a prominent feature, highlighting the vehicle's role in the astronaut's lunar exploration.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, and the arm is twisted."
}
] |
seed42_2031
|
videos/HRA_part0/2031.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and helmet, sits on a vintage red fire engine, enjoying a hearty meal of spaghetti with meatballs from a white plastic plate balanced on his lap. The scene is set against the backdrop of a bustling fire station, with the garage doors open, revealing the interior where fellow firefighters are engaged in various activities, creating a vivid snapshot of life at the station. Despite the chaos around him, the firefighter finds a moment of respite, his face illuminated by the warm glow of the setting sun filtering through the open bay doors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2249
|
videos/HRA_part0/2249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, dressed in full gear except for a red chicken hat, crawls through a dimly lit, misty hot springs area. The water reflects the ambient light, creating an ethereal glow around the unique character. Surrounded by the steamy, rocky landscape of the hot springs, the firefighter continues to crawl, adding an element of intrigue to the surreal setting.]"
},
{
"from": "gpt",
"value": "Normal. No chicken hat was generated."
}
] |
seed46_1074
|
videos/HRA_part2/1074.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a white shirt and brown trousers, stands in the middle of a lush green field under a clear blue sky. He is in mid-action, throwing hay bales with ease and precision. His weathered hands grip a bale tightly as he winds up for the toss, muscles straining beneath his shirt. The hay bales are scattered around him, some neatly stacked, others awaiting his expert throw. The farmer's face is set in determination, eyes focused on the target, embodying the hard work and strength synonymous with farming life.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1401
|
videos/HRA_part2/1401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 human-sized fox, wearing a doctor's outfit complete with a white lab coat, blue shirt, and stethoscope around its neck, walks purposefully down a hospital corridor. The fox's facial features are clearly visible, with a furrowed brow conveying concern and determination. The hospital hallway is brightly lit, with white walls and linoleum flooring, and the fox strides confidently, passing by various medical equipment and posters hanging on the walls. Despite being a fox, it carries itself with the poise and professionalism expected of a medical professional.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_207
|
videos/HRA_part2/207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 zero gravity, a whimsical scene unfolds where a small, brown porcupine floats, performing a delightful dance. It gracefully pirouettes against a backdrop of stars and the vast cosmos, its quills gently swaying in the absence of gravity. The porcupine then leaps playfully, executing mid-air flips and twists with an infectious joy, its quills shimmering under celestial lights. Throughout the dance, the porcupine's movements are fluid and weightless, embodying the freedom and fun of dancing in space, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Normal. The porcupine's movements in the video are not smooth."
}
] |
seed44_3065
|
videos/HRA_part1/3065.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, 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": "Normal. The walking movements of the character in the video are slightly unsmooth."
}
] |
seed42_1894
|
videos/HRA_part0/1894.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a navy suit, white shirt, and striped tie, races through a lush green forest, holding a koala in one arm. The koala, clinging tightly, wears a tiny barrister's wig and round spectacles, adding a whimsical touch to the scene. They run past tall trees, ferns, and flowers, with the lawyer's facial expressions alternating between determination and a smile, highlighting the unusual yet playful nature of the chase. The vibrant forest setting, complete with sunlight filtering through the leaves, enhances the dynamic and surreal atmosphere of the scenario.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_3200
|
videos/HRA_part2/3200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jackal leaps through the air, its body stretched in mid-jump, against the backdrop of a desolate volcanic landscape. The creature, with its sandy fur and alert expression, bounds over rugged terrain as steam rises from vents in the ground. The jackal lands and pauses, ears pricked, silhouetted against the smoldering volcano that fills the horizon, its eyes reflecting the fiery glow. Moments later, it springs into action again, bounding away across the rocky, moon-like surface, leaving plumes of dust in its wake.]"
},
{
"from": "gpt",
"value": "Bad. The jackal's head is twisted, legs are twisted, and body is twisted."
}
] |
seed42_1799
|
videos/HRA_part0/1799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green meadow under a partly cloudy sky, a majestic stag stands tall, its large, expressive eyes gazing into the distance. It shakes its head vigorously, sending droplets of water flying from its fur. The stag, with its impressive antlers and auburn coat, continues to shake itself dry after what seems to have been a refreshing drink from a nearby stream. The rolling hills and scattered trees provide a serene backdrop, emphasizing the beauty and tranquility of nature. As it finishes drying off, the deer looks around, alert and aware, before returning to its peaceful grazing.]"
},
{
"from": "gpt",
"value": "Normal. The deer's mouth in the video has an issue with its generation."
}
] |
seed46_1768
|
videos/HRA_part2/1768.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid, close-up shot, a sleek, black king cobra emerges from the underbrush, its distinctive hood fully spread as it propels itself forward with surprising speed. Its body, covered in smooth scales, undulates gracefully over the forest floor, showcasing the powerful muscles beneath. The cobra's intense, amber eyes remain fixed ahead, conveying a sense of purpose and determination as it navigates the complex terrain with agility and precision. The lush greenery and dappled sunlight create a dynamic contrast against the snake's dark form, highlighting the primal energy of this extraordinary creature in motion.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2857
|
videos/HRA_part1/2857.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant flamingo stands tall and proud on a sandy shore, its pink feathers glowing under the golden rays of the setting sun. Its long, slender legs elegantly support its body as it gazes out over the calm waters, creating a serene and picturesque scene. The flamingo's curved neck gracefully bends, while its beak rests gently on its chest, exuding a sense of tranquility and contentment. Surrounding palm trees sway gently in the breeze, adding to the idyllic atmosphere of this stunning coastal landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1777
|
videos/HRA_part0/1777.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city square, under the soft glow of streetlights and the clear night sky, a diverse group of individuals, including a man with a beard, a woman with glasses, and another woman with a ponytail, are all looking intently at something above them. Their postures and facial expressions convey a sense of awe and wonder, suggesting they are captivated by an extraordinary sight in the urban landscape. Among them, a man with a beard and a woman with glasses stand side by side, both gazing upwards with intense focus. Beside them, a woman with her hair in a ponytail also looks up, her face reflecting a mix of surprise and fascination. All around, the city continues its nightly activities, but these people remain transfixed, united in their shared attention to an unseen marvel overhead.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1118
|
videos/HRA_part2/1118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a brown jacket, beige slacks, and brown boots, takes a break from his typewriter to rake a large pile of colorful autumn leaves in his backyard, capturing the essence of seasonal change. He pauses, tool in hand, casting a thoughtful gaze at the vintage typewriter sitting on a wooden desk, which is placed under a large, leafy tree. The scene transitions to show him raking leaves with vigor, his attire unchanged, as the leaves form a vibrant heap, evoking a sense of tranquility and the beauty of fall. Finally, he pauses again, this time with a satisfied smile, surveying his neatly raked yard, the pile of leaves a testament to his labor, while the typewriter remains in the background, hinting at his dual passions for writing and nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1258
|
videos/HRA_part2/1258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and imaginative scene, a cheerful nurse, clad in a crisp white uniform and cap, is playfully chasing a capybara across a vast, sandy terrain reminiscent of Mars. The capybara, surprisingly agile, bounds ahead with its short legs, its wet nose glistening under the alien sun. Meanwhile, a Mars rover, equipped with intricate mechanical arms and advanced sensors, rolls steadily alongside, capturing the unusual chase on its high-definition cameras. The rover's solar panels gleam, and its wheels kick up puffs of red dust as it follows the unlikely pair, documenting their lively interaction on the Martian surface.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's limb movements are uncoordinated and the actions are not continuous."
}
] |
seed42_1936
|
videos/HRA_part0/1936.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform and a crisp white shirt, is spotted joyfully dancing in the middle of a highway during the golden hour. The unexpected scene unfolds as a small vole curiously watches from the roadside grass, adding a touch of whimsy. The officer's movements are lively, yet controlled, drawing the attention of passing motorists who slow down to witness this unusual spectacle. Despite the gravity of his profession, the officer's spontaneous dance embodies a lighthearted moment, offering a brief respite from the monotony of highway travel.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2072
|
videos/HRA_part1/2072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, with short brown hair and a neatly trimmed beard, stands in a modern kitchen with white cabinets and countertops. He is wearing a casual outfit consisting of a gray t-shirt and dark blue jeans. The kitchen is well-lit, and natural light filters in from a nearby window. The man is focused on making coffee, pouring water into a sleek, stainless steel coffee maker. He then measures coffee grounds carefully, ensuring the perfect cup. As the coffee brews, steam rises gently, and the aroma fills the room, creating a warm and inviting atmosphere. The man waits patiently, his expression one of anticipation, as the coffee completes its cycle, ready to be enjoyed.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1831
|
videos/HRA_part0/1831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat and blue gloves, is seen wiping the nose of a friendly coyote who is sitting calmly on a checkered medical table. The room is brightly lit, with medical supplies neatly arranged on shelves in the background. The doctor's compassionate expression and the coyote's trusting demeanor create a heartwarming moment, highlighting an unusual yet tender interaction between human and wild animal in a clinical setting.]"
},
{
"from": "gpt",
"value": "Normal. The hands of the character and the paws of the jackal in the video have generation issues."
}
] |
seed44_2471
|
videos/HRA_part1/2471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal juxtaposition, a distinguished doctor, clad in a lab coat and stethoscope, runs alongside a prehistoric mammoth through an industrial landscape dotted with colossal power plants. Their breaths form visible clouds in the crisp air, as they navigate the terrain under an overcast sky. The mammoth's massive frame and the doctor's determined gaze create an unlikely alliance, their journey unfolding against the backdrop of towering smokestacks and power lines, blending elements of fantasy and reality in a captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The doctor and the prehistoric mammoth's running actions are not continuous and smooth, there is a lack of coordination."
}
] |
seed46_2927
|
videos/HRA_part2/2927.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a rural backyard filled with lush greenery and wooden fences, two young children, a boy in a red shirt and blue shorts and a girl in a yellow dress, chase after a lively chicken, their laughter echoing in the sunny afternoon. The boy, with short brown hair, and the girl, her hair tied in pigtails, gleefully pursue the bird across the yard. Their playful antics are framed by a background of vibrant green trees and shrubs, with the chicken's colorful feathers standing out against the natural setting. The scene captures a moment of innocent childhood joy, with the children's faces alight with excitement and the chicken adding a touch of whimsy to the idyllic outdoor space.]"
},
{
"from": "gpt",
"value": "Bad. The child's chasing movements and the chicken's walking movements in the video are not smooth."
}
] |
seed46_2042
|
videos/HRA_part2/2042.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 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 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": "Good. Basically correct."
}
] |
seed44_1744
|
videos/HRA_part1/1744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly contrasting scene, a lone hyena stands in the foreground, its silhouette framed against a golden sunset, while in the distance, meticulously aligned rows of lush green vines stretch across the landscape, indicating a vast vineyard. As the camera pans, a luxurious swimming pool comes into view, nestled amidst the vineyard, shimmering under the fading sunlight, offering a surreal juxtaposition of wild and cultivated beauty.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2988
|
videos/HRA_part2/2988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a slender gazelle, elegantly attired in a black apron and cap, diligently wipes down a wooden countertop with a green cloth. The setting is a quaint, rustic grocery store, filled with shelves of produce and goods. The gazelle, with its distinctive horns and graceful demeanor, performs the task with meticulous care, embodying an unexpected yet captivating scenario behind the register.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1655
|
videos/HRA_part0/1655.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white rabbit with pink ears sprints across a grassy field adjacent to a busy highway, its powerful hind legs propelling it forward urgently. The highway, bustling with vehicles, forms a stark contrast to the natural landscape where the rabbit runs. Sunlight filters through cumulus clouds, casting dynamic shadows on the scene as the rabbit continues its hurried journey, highlighting the unexpected encounter between nature and urban infrastructure.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2410
|
videos/HRA_part1/2410.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a brown jacket over his white medical coat, shovels snow from the sidewalk outside his clinic on a cold winter day. His attire includes dark pants, brown boots, and a brown cap, providing contrast against the snow-covered landscape. He pauses to wipe his brow, revealing a sense of effort, before continuing to clear the path, demonstrating his commitment to his patients. Behind him, the clinic's sign is visible, adding context to the scene. Throughout, the focus remains on the doctor's actions and the snowy environment, highlighting his dedication amidst the wintry conditions.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's fingers and arms are poorly generated, the face is blurry, and the snow shovel is deformed."
}
] |
seed44_2610
|
videos/HRA_part1/2610.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a gray suit with a blue shirt and striped tie, stands in a modern office space. He is attentively checking a smoke detector mounted on the ceiling, exhibiting a careful and professional demeanor. The office features a large window offering views of a city skyline, a desk with a laptop and documents, and a bookshelf filled with law books, creating a setting that blends professionalism with safety awareness. The lawyer's actions highlight the importance of routine safety checks in a workplace environment.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's limbs are deformed in the video, and there are issues with the generation of the eyes and body."
}
] |
seed46_332
|
videos/HRA_part2/332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, attired in a khaki safari outfit, navigates through the dense undergrowth of a tropical dry forest. The sunlight filters through the canopy, casting dappled shadows on the rugged terrain. Lush, gnarled trees surround him, their leaves whispering in the gentle breeze. Insects buzz softly in the background, adding to the ambiance of the wild. The director walks purposefully, his boots crunching on the carpet of fallen leaves and twigs, holding a detailed map in one hand and occasionally stopping to consult it, his focus intense and unwavering.]"
},
{
"from": "gpt",
"value": "Bad. The director's fingers are deformed in the video, the face is generated blurry, and there are missing parts in the limbs and map generation."
}
] |
seed46_1328
|
videos/HRA_part2/1328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Neptune's ethereal atmosphere, human figures, clad in futuristic, silver, metallic swimsuits and equipped with advanced breathing apparatus, swim gracefully through the gaseous clouds. Their movements are fluid and balletic, almost as if they are performing an underwater dance in the sky. The humans, both male and female, exhibit expressions of wonder and awe as they navigate the alien environment. They perform synchronized swimming routines, moving in perfect harmony with each other and the surrounding gas giant atmosphere. The scene is illuminated by a distant sun, casting a soft, dreamlike glow on the figures as they glide through the thick, swirling clouds of Neptune.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_104
|
videos/HRA_part2/104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, wearing a gray jacket and blue jeans, walks through the lush greenery of a botanical garden, surrounded by vibrant flowers and towering trees. They pause to examine a particularly interesting plant, their backpack resting on the ground beside them. The sunlight filters through the leaves overhead, casting dappled shadows on the path. In the background, the serene sound of a nearby fountain can be heard, adding to the peaceful atmosphere of the scene. The student continues on their leisurely stroll, taking in the beauty of nature around them.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1044
|
videos/HRA_part0/1044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, a middle-aged janitor, wearing a yellow high-visibility vest over a dark jacket and a gray cap, gently caresses a kangaroo. The animal, with its distinctive marsupial pouch, is calm and accepting of the man's affection. The setting is a nondescript indoor location with concrete floors and walls, typical of a warehouse or large garage, with various tools and equipment scattered about. The interaction between the unlikely pair is tender and peaceful, capturing a unique moment of interspecies connection.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the gray cap mentioned in the caption."
}
] |
seed42_3169
|
videos/HRA_part0/3169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a gray jacket and blue jeans stands outside a historic cinema, its marquee displaying classic film posters, evoking a sense of nostalgia and cinematic history. Moments later, the focus is on the man swimming in an indoor pool, surrounded by large windows that let in natural light, creating a contrast between the urban environment and the tranquility of water. He swims with purpose and strength, his silhouette framed by the water and the reflections of the pool tiles. The scene captures the essence of leisure and physical activity, juxtaposing the cultural experience of cinema with the personal enjoyment of swimming.]"
},
{
"from": "gpt",
"value": "Bad. The person's body is distorted in the video."
}
] |
seed44_1858
|
videos/HRA_part1/1858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a college student, dressed in a traditional ceremonial robe, kneels on a lush, green meadow under a clear night sky filled with stars. Beside them, a squirrel, unusually adorned in miniature ceremonial attire, mirrors the student's position. The student gently wipes away what appears to be ceremonial paint from their face using a soft cloth, alluding to a cleansing ritual. This intimate act is witnessed by the squirrel, which seems to participate in its own way, creating a surreal, touching moment between human and nature, set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The action of the student wiping the ritual face paint with fabric in the video is basically normal, but there is some inconsistency."
}
] |
seed46_2778
|
videos/HRA_part2/2778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform with a badge and a hat, walks alongside a large, majestic rhinoceros. Both traverse a rugged terrain under a bright, sunny sky, creating an unusual yet compelling juxtaposition of authority and wildlife. The officer, equipped with a walkie-talkie on his belt, maintains a calm demeanor, while the rhinoceros, sporting a single horn and thick, wrinkled skin, ambles beside him. The scene unfolds in a spacious, natural environment, far from the urban settings typically associated with law enforcement.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2184
|
videos/HRA_part0/2184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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's impression of an exoplanet's surface showcases a vivid purple sky and lush, alien vegetation. In the foreground, a terrestrial lizard-like creature crawls over a rocky terrain, its textured skin blending with the environment. The distant, exotic landscape is illuminated by a dual sunset, casting a warm glow over the peculiar flora. The scene is completed by the inclusion of a small, moon-like body hanging in the sky, adding to the sense of wonder and mystery surrounding this far-off world.]"
},
{
"from": "gpt",
"value": "Bad. The creatures on Earth do not clearly resemble the shape of lizards."
}
] |
seed46_3062
|
videos/HRA_part2/3062.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a thoughtful writer sits at a cluttered desk, typing away on a laptop with determination. Suddenly, the scene focuses on a small vole, its fur a mix of brown and gray, crawling out from beneath the wooden desk. The rodent explores its surroundings, nibbling on a pencil and climbing onto a pile of books, all while the writer continues to work, seemingly unaware of the tiny creature's presence.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the field mouse and the writer basically normal, with slightly uncoordinated movements."
}
] |
seed44_1052
|
videos/HRA_part1/1052.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 yellow clothes has one leg not generated, and the child's arms deform while running, with foot deformities."
}
] |
seed44_1130
|
videos/HRA_part1/1130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, wearing a gray suit and a white shirt, stands in a futuristic, high-tech room filled with screens displaying charts and graphs related to interplanetary trade routes. He gently caresses a large, interactive holographic map, which shows the intricate web of trade connections between various celestial bodies, highlighting the complex network of commerce spanning the solar system. The room is bathed in soft, ambient lighting, emphasizing the director's pensive and focused demeanor as he contemplates the vast opportunities and challenges presented by this expansive trade network.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1899
|
videos/HRA_part2/1899.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown bear, standing on its hind legs on a wooden stage, wears a red and gold traditional Russian costume, complete with a matching hat. The bear, seemingly performing for an unseen audience, dances energetically to lively music, swaying its body and moving its paws in time with the beat. The stage is decorated with colorful banners and twinkling lights, creating a festive atmosphere, while the bear's expressive face conveys a sense of playful enjoyment in its unusual dance performance.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the brown bear in the video are missing, and there are issues with the facial generation."
}
] |
seed46_1396
|
videos/HRA_part2/1396.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a red tracksuit, emulates a monkey with playful antics, running energetically across a vibrant green field under a clear blue sky. The student's facial expression, complete with wide eyes and an open mouth, mirrors the monkey's characteristic features, enhancing the mimicry. Accompanied by a group of friends, who cheer and laugh in the background, the scene captures a moment of carefree fun and youthful exuberance. The student's attire, which includes a red jacket and matching pants, stands out against the lush greenery, while the clear blue sky provides a perfect backdrop for the lively scene.]"
},
{
"from": "gpt",
"value": "Bad. The faces and hands of the students in the video are generated poorly."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, 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. No obvious problems."
}
] |
seed44_1418
|
videos/HRA_part1/1418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a yellow reflective vest, blue latex gloves, and a badge, runs with purpose toward a cluster of factories in the background. The factories feature large smokestacks, metal siding, and concrete exteriors, set against a cloudy gray sky. The officer's intense gaze and focused posture convey urgency as they sprint across a desolate industrial landscape, the factories' imposing structures looming ominously behind.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's running in the video is basically normal, with only slightly uncoordinated movements."
}
] |
seed44_2047
|
videos/HRA_part1/2047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a rustic farmyard setting, a fluffy yellow chick is seen crawling across the ground, its tiny feet moving quickly beneath it. The chick crawls under a weathered wooden fence, its feathers ruffling slightly as it navigates the space. It continues its journey, now crawling over a patch of fresh green grass, the blades tickling its delicate underside. Finally, the chick reaches a small cluster of pebbles, over which it crawls, demonstrating determination and resilience in its exploration of the farmyard environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1507
|
videos/HRA_part0/1507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy landscape under a clear blue sky, two young children, a boy and a girl, are gently caressing a calm camel. The boy, wearing a yellow shirt and brown shorts, strokes the camel's nose tenderly, while the girl, dressed in a pink dress and sandals, pets its lower leg with a smile. Both children are barefoot, standing on the soft sand, and the camel, adorned with traditional red and white saddle cloths, accepts their affection with a patient demeanor, creating a heartwarming scene of human-animal interaction in a desert environment.]"
},
{
"from": "gpt",
"value": "Bad. The little girl's arm undergoes a mutation, her right arm suddenly disappears and becomes deformed. The boy's fingers also become deformed."
}
] |
seed42_2310
|
videos/HRA_part0/2310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature man, possibly a writer, wearing a brown jacket, blue shirt, and khaki pants, stands pensively on a rocky cliff overlooking a vast, stormy sea. He wipes his face with his right hand, perhaps reflecting a moment of emotional intensity or physical exertion, as he contemplates the dramatic landscape before him. The rugged terrain and turbulent waters provide a striking contrast to his thoughtful demeanor, emphasizing the solitude and grandeur of his surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The man's face and hands in the video were generated abnormally."
}
] |
seed46_1052
|
videos/HRA_part2/1052.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 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 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 movements are uncoordinated, the actions are discontinuous, and the red child is flying."
}
] |
seed46_2430
|
videos/HRA_part2/2430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and unexpected scene, a waiter, clad in a crisp white shirt and black trousers, serves a majestic deer who stands elegantly by a serene swimming pool, its antlers framing its face like a crown. The deer, with its large, curious eyes, seems to be sipping from a fancy glass, while the waiter attentively pours a clear liquid, possibly water, from a pitcher. The swimming pool, with its crystal-clear water, reflects the sky, adding to the surreal atmosphere of this extraordinary meeting between nature and human service.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2636
|
videos/HRA_part2/2636.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful male writer sits in a cluttered office, adorned with a gray beanie, black jacket, and glasses, typing on a laptop placed on a wooden desk. The room is filled with books, a typewriter, and a calendar, creating a vintage atmosphere. His hands move swiftly across the keyboard as he focuses intensely on his work, surrounded by objects that inspire creativity, such as a globe, a lamp, and a framed picture. The scene conveys a sense of dedication and passion for writing, with the man deeply engrossed in his craft amidst a space that reflects his personality and interests.]"
},
{
"from": "gpt",
"value": "Normal. The writer's hand in the video has issues."
}
] |
seed44_3184
|
videos/HRA_part1/3184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, green savanna setting, a gentle giraffe is being affectionately caressed by a human, both standing under a vast, open sky. The giraffe, with its distinctive spotted coat and long neck, leans into the touch, expressing comfort and trust. The human, wearing a khaki safari outfit, reaches up to stroke the giraffe's face, creating a tender moment of interspecies connection. The scene is framed by the natural beauty of the savanna, with distant trees and a clear blue sky, emphasizing the harmony between the human and the majestic animal.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth, and the giraffe's movements are not smooth."
}
] |
seed46_1919
|
videos/HRA_part2/1919.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin breaches the shimmering ocean surface, its streamlined body glistening under the golden sunlight. The marine creature, adorned with striking blue and silver hues, soars through the air with acrobatic grace, its elongated upper jaw, or rostrum, pointing towards the sky. As it re-enters the water, a splash of crystal-clear droplets disperses around it, creating a mesmerizing display of power and agility in the vast aquatic realm.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2436
|
videos/HRA_part1/2436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A meerkat, standing upright on its hind legs, surveys its surroundings in a suburban backyard, with a wooden deck, a lush lawn, and a swimming pool in the background. The meerkat, known for its striped brown fur and alert demeanor, appears curious and engaged with its new environment. It stands on a manicured green lawn, next to a wooden deck with patio furniture, and looks towards a large, clear swimming pool, where the water shimmers under the bright sunlight. The contrast between the wild creature and the domestic setting creates a unique and unexpected visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1015
|
videos/HRA_part2/1015.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional nurse, clad in a light blue scrubs top and dark blue scrubs pants, sits at a desk with a name badge visible on her chest. She types diligently on a desktop computer keyboard, her focus unwavering. Behind her, a hospital room is visible, featuring a bed with crisp white sheets and a patient resting peacefully under a blanket. Medical equipment lines the walls, including an IV stand and a monitor displaying vital signs, while a window allows natural light to illuminate the space. The nurse's posture and concentration convey her dedication to her work in this healthcare setting.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's typing hand is distorted."
}
] |
seed44_1874
|
videos/HRA_part1/1874.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy blue uniform with a badge and a black belt, runs through a vast meadow filled with lush green grass and vibrant wildflowers. The landscape stretches to the horizon, dotted with distant trees. His expression is one of determination, eyes focused ahead, and he strides with purpose, leaving a faint trail in the dewy grass. The sun, partially obscured by a cloud, casts a soft, golden light over the scene, highlighting the officer's movement as he navigates the uneven terrain, demonstrating commitment and urgency in his duty.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's eyes and hands in the video have generation issues, with the hands suddenly appearing or disappearing during the running process."
}
] |
seed44_1896
|
videos/HRA_part1/1896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dreamlike sequence, an astronaut clad in a pristine spacesuit gently caresses a bobcat on the lunar surface, under the Earth's watchful gaze. The astronaut's visor reflects the desolate landscape, while the bobcat, undeterred by its extraterrestrial surroundings, responds with curiosity. The scene is illuminated by the distant Earthshine, casting a soft glow on the moon's dusty terrain, highlighting the tenderness of this interstellar encounter.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2990
|
videos/HRA_part2/2990.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red jacket and brown trousers, runs along the edge of a harbor, the water glistening under the bright sun. Accompanied by a large, energetic dog with a tan coat, they traverse the harbor perimeter, surrounded by lush greenery. The farmer, showing a sense of urgency, sprints with focused determination, while the dog bounds alongside, mirroring his pace. Together, they navigate the harbor's edge, the water's surface reflecting sunlight in sparkling patterns, creating a dynamic scene of movement and companionship.]"
},
{
"from": "gpt",
"value": "Bad. The farmer and the dog's running movements in the video are not smooth."
}
] |
seed46_1963
|
videos/HRA_part2/1963.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, impeccably dressed in a black suit, white shirt, and black tie, stands against a blurred restaurant background. He holds a cocktail shaker in both hands, vigorously shaking it to mix a drink. His eyes are focused on the task, and beads of condensation form on the metal shaker. The action takes place in a dimly lit, upscale bar setting, with the shaker's metallic surface reflecting the ambient light. Throughout the scene, the waiter maintains his professional demeanor, his crisp attire contrasting with the dynamic motion of his hands as he expertly prepares a beverage.]"
},
{
"from": "gpt",
"value": "Bad. The server's fingers in the video are not fully generated."
}
] |
seed44_1459
|
videos/HRA_part1/1459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional lawyer, dressed in a dark suit, sits at a modern glass desk in a well-lit office. The room features wooden floors, large windows, and contemporary art on the walls. The attorney is writing on a legal pad with a sleek fountain pen, his brows furrowed in concentration. The desk is adorned with an array of legal documents and a nameplate, while a laptop rests open nearby. The scene conveys a sense of seriousness and attention to detail as the lawyer diligently works on his case.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2116
|
videos/HRA_part2/2116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinguished by his crisp, white button-down shirt and black apron, stands in a modern, minimalist living room with large windows and wooden floors. He is meticulously assembling a piece of furniture, focusing intently on aligning the components. The room is sparsely decorated, featuring a simple gray couch and a few abstract art pieces hanging on the walls. Natural light filters in from the windows, casting a warm glow on the scene as the waiter, now with sleeves rolled up, carefully tightens screws and fits parts together, demonstrating his unexpected handyman skills in a domestic setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1495
|
videos/HRA_part1/1495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful buffalo, its body robust and muscular, leaps gracefully over a wooden fence in the midst of a lush, green prairie. The fence, made of weathered logs, stretches across the frame, adding texture and depth to the scene. The buffalo, its large horns curving outward, is captured mid-jump, showcasing its agility and strength. The background is filled with the vibrant hues of nature, from the deep greens of the grass to the soft blues of the sky, creating a stunning contrast against the dark brown of the buffalo. This majestic creature, defying expectations with its leap, embodies the spirit of the wild, free and untamed.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the water buffalo in the video are incomplete."
}
] |
seed46_2716
|
videos/HRA_part2/2716.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, clad in a white spacesuit with a NASA logo, crawls across the Martian landscape under a starlit sky. The camera captures her movements as she stops to gaze upwards, her helmet visor reflecting the celestial panorama. The focus is on her figure against the rugged terrain, with the distant stars and the curvature of Mars' horizon providing a dramatic backdrop. Her spacesuit, adorned with medical insignia, stands out against the red soil, emphasizing her unique role as a caregiver in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The nurse in the video has uncoordinated movements."
}
] |
seed42_1436
|
videos/HRA_part0/1436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 red starfish with five arms and tiny white spots rests on a bed of pristine white sand, surrounded by shallow turquoise waters that gently lap at its sides. Sunlight filters through the water, casting shimmering light patterns on the starfish and sand. In the background, a vast ocean stretches to the horizon, meeting a clear blue sky dotted with fluffy white clouds. The overall scene exudes tranquility and beauty, capturing the essence of life beneath the sea's surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2628
|
videos/HRA_part1/2628.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an unexpected urban scene, a wild bobcat stands alert near a glassy skyscraper, its reflection visible on the building's facade. Beside it, a sleek swimming pool shimmers under the city lights, invitingly clear and calm. The bobcat, with its distinctive tufted ears and sharp gaze, seems unperturbed by the towering structures, its presence creating a striking contrast against the urban landscape. The pool, framed by the towering skyscrapers, offers a serene oasis, its still waters reflecting the night sky and the surrounding architecture.]"
},
{
"from": "gpt",
"value": "Bad. The sable's body and limbs have shown deformities and mutations."
}
] |
seed42_1788
|
videos/HRA_part0/1788.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gerbil, adorned with a miniature top hat and tiny suspenders, stands on its hind legs on a wooden stage. The rodent energetically moves to an unseen beat, its forepaws mimicking a dancer's gestures against a backdrop of a red velvet curtain. The scene is whimsical, with the gerbil's lively expressions and animated body language capturing the essence of joyful dancing under the warm glow of spotlight, all set against a rich, textured red background that adds depth and drama to the performance.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's dance in the video is very unsmooth, the movements are uncoordinated."
}
] |
seed42_2116
|
videos/HRA_part0/2116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinguished by his crisp, white button-down shirt and black apron, stands in a modern, minimalist living room with large windows and wooden floors. He is meticulously assembling a piece of furniture, focusing intently on aligning the components. The room is sparsely decorated, featuring a simple gray couch and a few abstract art pieces hanging on the walls. Natural light filters in from the windows, casting a warm glow on the scene as the waiter, now with sleeves rolled up, carefully tightens screws and fits parts together, demonstrating his unexpected handyman skills in a domestic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1116
|
videos/HRA_part2/1116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, a uniformed police officer kneels on lush green grass, gently caressing a tiny vole with utmost care and tenderness. The officer, wearing a classic navy blue police uniform with a badge and a cap placed nearby, ensures the small creature feels safe and secure. The vole, with its delicate features and curious eyes, seems at ease in the presence of the compassionate law enforcement figure. The background is a serene park setting, with trees and a clear blue sky, highlighting the unexpected yet touching connection between the officer and the vole.]"
},
{
"from": "gpt",
"value": "Bad. The person's fingers appear deformed and misshapen, and the character's feet have not been generated."
}
] |
seed42_1842
|
videos/HRA_part0/1842.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large, brown capybara runs energetically across a grassy plain, its ears perked up and alert, showcasing its distinctive rodent features. It sprints with determination, its body low to the ground, through a lush, green environment dotted with trees. The capybara's movement is fluid and powerful, its legs propelling it forward with each stride, as it navigates the vibrant landscape under a bright, open sky.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video walks very unsmoothly, and their movements are not coordinated."
}
] |
seed42_1846
|
videos/HRA_part0/1846.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, wearing a red flannel shirt, blue jeans, and brown boots, runs alongside a spirited golden retriever in a lush green park. Both the musician and the dog display expressions of pure joy and freedom. The musician, equipped with a backpack, is in mid-stride, while the dog bounds ahead, tail wagging. The scene captures the essence of a carefree day in the park, with the musician's attire and the dog's enthusiastic demeanor setting the tone for a playful and energetic outing.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, the hand is twisted, the face is twisted, the legs are twisted, the dog's face is twisted, and the legs are twisted."
}
] |
seed46_1827
|
videos/HRA_part2/1827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, adorned in a stylish yellow dress, gracefully caresses the powdery sand of an idyllic beach resort as the turquoise sea gently laps at the shore. Her eyes closed, she savors the serene moment, feeling the warmth of the sand between her toes. The peaceful atmosphere is punctuated by the rhythmic sounds of the ocean, the soft rustle of palm fronds, and the distant calls of seagulls, all contributing to a scene of blissful tranquility. The vibrant colors of her attire contrast beautifully with the natural hues of the beach, creating a captivating visual harmony.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1775
|
videos/HRA_part2/1775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown beaver, situated near water, performs a wiping motion with its right paw across its face, specifically from the eyes down to the mouth. The beaver is positioned with its back to the camera, offering a unique perspective. Its tail is submerged in the water, and the wiping action is repeated several times, emphasizing the creature's grooming habits in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_112
|
videos/HRA_part1/112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of fresh mackerel fish, glistening under bright lights, showcases their vibrant silver scales, deep blue stripes, and dark spots. The fish lie on a bed of ice, their eyes clear and shiny, indicating peak freshness. The background features a bustling market scene, with vendors selling various seafood and customers browsing the selection. Focused on the mackerel, the camera captures every detail of the fish's texture and color, making them the star of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1966
|
videos/HRA_part2/1966.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brightly lit, futuristic classroom filled with advanced technology, two young children, a boy and a girl, both wearing school uniforms, gently caress a small, friendly robot astronaut. The robot, designed with smooth, rounded edges for safety, features a smiling face on its metallic body, which is painted in shades of silver and blue. The room is decorated with educational posters and interactive screens, creating an engaging learning environment. The children, showing curiosity and affection, interact with the robot, which responds with gentle movements and playful sounds, fostering a connection between humans and artificial intelligence in a nurturing setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous."
}
] |
seed42_108
|
videos/HRA_part0/108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique rural setting, a cashier from a local store, dressed in a red apron and black clothing, interacts gently with a brown horse inside a tunnel made of hay bales, creating a warm, intimate atmosphere. The cashier, wearing a red apron over a black outfit, caresses the horse's nose affectionately, with the textured tunnel walls adding depth to the scene. The connection between the cashier and the horse is emphasized by their eye contact, while the rustic tunnel provides a natural, earthy backdrop. Moments later, the cashier, still clad in the red apron and black attire, strokes the horse's mane softly, the bond between human and animal palpable, all within the cozy confines of the hay tunnel.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the hands are deformed, and the horse's head is deformed."
}
] |
seed46_3181
|
videos/HRA_part2/3181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an underwater scene illuminated by natural light filtering through the water's surface, a school of vibrant, multicolored fish swim together in unison. The fish display a range of hues, including orange, yellow, and blue, with intricate patterns adorning their scales. They gracefully navigate the aquatic environment, surrounded by lush green seaweed gently swaying in the current. The detailed textures of the fish's bodies and the vivid colors of their surroundings create a captivating and serene underwater world.]"
},
{
"from": "gpt",
"value": "Normal. The fish swims basically normally in the video, but there is slight movement disharmony."
}
] |
seed46_2311
|
videos/HRA_part2/2311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent leopard, with striking golden eyes and a distinctive pattern of rosettes on its tawny fur, is captured in high definition as it lies on a branch. It begins by looking straight ahead, showcasing its majestic presence. Then, it turns its head to the right, revealing its sharp features and powerful muscles rippling beneath its coat. Next, the leopard proceeds to clean itself, licking its paw and wiping it across its face, a display of natural behavior in its untamed habitat. Throughout the sequence, the leopard remains perched on the branch, its gaze occasionally flicking towards the viewer, offering a rare glimpse into its private grooming routine.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions a leopard licking its paws and wiping its face, but this does not appear in the video."
}
] |
seed46_256
|
videos/HRA_part2/256.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of an ibis's head, featuring its distinct red facial skin and long, curved bill, contrasted against a dark background. The bird's textured feathers, detailed facial features, and piercing eyes are captured in high definition. The ibis is shown from various angles, highlighting its unique physical attributes, including its sharp, curved beak and distinctive eye markings. Throughout the footage, the ibis's head remains the central focus, with the dark backdrop emphasizing its striking appearance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2804
|
videos/HRA_part1/2804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black tank top and dark jeans, mimics the agile movements of a mongoose, sprinting across a lush, verdant landscape. His intense gaze and athletic build convey strength and determination as he leaps over obstacles, embodying the spirit of the nimble creature. The scenery features vibrant greenery and a clear blue sky, providing a vivid contrast to his swift, mongoose-inspired running. Throughout the sequence, the actor maintains his focus and momentum, seamlessly integrating the mongoose's grace and speed into his performance.]"
},
{
"from": "gpt",
"value": "Bad. The man can be clearly seen running in the video, but his movements are not very continuous and smooth, showing some coordination issues."
}
] |
seed46_1065
|
videos/HRA_part2/1065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station illuminated by vibrant neon lights, a worker, dressed in a sleek gray jumpsuit and wearing protective goggles, gently caresses the metallic arm of a Robot astronaut. The Robot, clad in a polished silver spacesuit adorned with intricate wiring and glowing blue accents, stands motionless yet imposing against the backdrop of high-tech equipment and advanced machinery. The scene captures a tender moment of human-robot interaction, highlighting the bond between the worker and the Robot astronaut in the vast expanse of outer space.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth and stiff, making it hard to see the action of stroking the robot's arm."
}
] |
seed46_1544
|
videos/HRA_part2/1544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, clad in a brown uniform, diligently wipes the glass enclosure of a wildlife exhibit, where a graceful gazelle is seen resting calmly inside. The enclosure is meticulously clean, save for a few lingering spots that the worker is addressing. The gazelle, displaying a relaxed demeanor, is positioned near the enclosure's entrance, its body language indicating a sense of security and comfort within its habitat. The scene captures the routine maintenance of the animal's living space, highlighting the careful interaction between the human caretaker and the wild creature in a shared environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.