video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1076
|
videos/HRA_part0/1076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, vivid scene, a janitor, dressed in a traditional uniform with a helmet, rides a majestic jaguar across a Mars-like landscape filled with orange sand dunes under a pinkish-red sky. The jaguar, adorned with a decorative saddle and reins, gallops gracefully, leading the viewer into a dreamlike world. The janitor then dismounts, exchanging the jaguar for a spirited Martian horse, which has a reddish-brown coat and carries him across the alien terrain with ease. The action shifts to a close-up of the janitor crawling on the Martian soil, examining the unique rock formations and textures of this extraterrestrial environment with fascination and curiosity.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's movements in the video are not smooth."
}
] |
seed46_2099
|
videos/HRA_part2/2099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, donning a yellow hard hat, orange safety vest, and blue jeans, sits on a wooden crate at a bustling construction site. Surrounded by scaffolding, concrete mixers, and cranes, he meticulously draws architectural plans using a pencil and a large blueprint sheet laid out on a makeshift plywood table, illustrating his dual skills in both physical labor and design. The scene captures his focused expression and the gritty urban environment, highlighting the blend of creativity and labor in his work.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1945
|
videos/HRA_part2/1945.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a brown tweed jacket, sits at a wooden desk adorned with books and a typewriter, gently caressing a small, docile cheetah resting its head on the desk. The writer, with a neatly trimmed beard, looks intently at the camera, while the cheetah, with a collar and a bell, remains calm and attentive. The scene captures the unlikely companionship between the intellectual and the wild animal, set against a backdrop of a study filled with bookshelves and framed pictures.]"
},
{
"from": "gpt",
"value": "Normal. The writer's movements while petting the cheetah in the video are uncoordinated."
}
] |
seed42_3119
|
videos/HRA_part0/3119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, two smiling children, a boy, and a girl, wearing colorful clothes, gently caress a calm camel in a lush, subtropical wet forest. The dense vegetation, including large-leafed plants and towering trees, provides a striking contrast to the unexpected presence of the camel. The boy, dressed in a blue shirt and khaki shorts, reaches out to touch the camel's nose, while the girl, in a yellow dress, strokes its side, both displaying expressions of delight and wonder. The camel, adorned with a red and gold blanket, stands placidly among the lush greenery, its presence a captivating anomaly within the rich, biodiverse ecosystem of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The boy's hands and feet are deformed in the video, the girl's face is disproportionate, her arms are twisted and deformed, and the camel's head and limbs are abnormally generated."
}
] |
seed44_2579
|
videos/HRA_part1/2579.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 herd of African buffalo, numbering in the hundreds, thunder across an expansive savanna, kicking up clouds of dust as they run. The buffaloes, with their distinctive large horns and sturdy bodies, move in unison, creating an awe-inspiring display of collective power and movement. The scene is set against a backdrop of distant acacia trees and a clear blue sky, emphasizing the vastness of the African wilderness. The herd's movement is so intense that it sends smaller animals scattering in all directions, highlighting the raw energy and strength of these magnificent creatures in motion.]"
},
{
"from": "gpt",
"value": "Good. The water buffalo's running action in the video is basically normal."
}
] |
seed44_1021
|
videos/HRA_part1/1021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, middle-aged with graying hair, wearing a dark green jacket and khaki pants, sits on a set of concrete steps outside a school building. He is intently writing in a small, brown notebook with a ballpoint pen, his focus unwavering. Behind him, a large window offers a glimpse into a classroom filled with wooden desks and chairs, a chalkboard, and a map of the world hanging from the ceiling. The scene is set during late afternoon, as indicated by the soft, golden light filtering through the window, casting a warm glow on the janitor and his surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The writing motion is basically normal, but there is a slight disproportion in the hand."
}
] |
seed44_2426
|
videos/HRA_part1/2426.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown jacket, blue jeans, and a green shirt, takes a break from his usual endeavors to tackle an autumn chore. He rakes leaves in a residential backyard, surrounded by lush greenery and tall trees. The scene opens with him standing confidently, holding a rake, and looking intently at the camera. Next, he begins raking piles of golden leaves, his focused expression and body language conveying his determination. The camera then captures him pausing to rest, leaning on the rake, and smiling contentedly at his progress. Finally, he returns to work, skillfully maneuvering the rake to gather the last of the fallen foliage, all while the warm, natural tones of autumn provide a picturesque backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The director's limbs are missing in the video, the face is generated blurry, and the broom is deformed."
}
] |
seed44_2415
|
videos/HRA_part1/2415.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic leopard, exhibiting a rare display of gentleness, is seen affectionately caressing another leopard in a lush, verdant environment. The first leopard, with piercing green eyes and a strikingly patterned coat, leans its head against the second leopard's face in a tender gesture. Both leopards are perched on a thick, sturdy branch, surrounded by dense foliage and dappled sunlight, creating an intimate atmosphere. This unique scene captures the emotional bond between these two wild cats, showcasing the softer side of these powerful predators.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's head generation in the video has problems."
}
] |
seed44_1336
|
videos/HRA_part1/1336.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gentleman, balding with a neatly trimmed beard, sits in a cozy library filled with bookshelves, wearing a brown jacket and a yellow shirt. He speaks animatedly about his writing process, gesturing expressively with his hands. Behind him, a large window frames a view of a lush garden, providing a picturesque backdrop. The room is illuminated by warm lighting, creating an inviting atmosphere that enhances the intimacy of the conversation. As he talks, his eyes sparkle with passion, conveying his deep connection to the art of storytelling.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2787
|
videos/HRA_part1/2787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Against a vast, icy landscape, two children in vividly colored swimwear are seen joyfully interacting with the glacier's edge, where a pool of crystal-clear water has formed. The girl, wearing a pink swimsuit, playfully splashes the water with her hands, her face alight with delight. The boy, in blue swimming trunks, sits on the ice, dipping his feet into the chilly waters, his expression one of cautious excitement. The camera captures the stark contrast between the vibrant colors of their swimwear and the monochromatic scenery of ice and sky, creating a striking visual tableau. Throughout the scene, the children's interactions with the glacial environment showcase their curiosity and wonder, highlighting the unique experience of swimming beside a glacier.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the boy and girl in the video are generated abnormally, with deformed hands and incomplete legs."
}
] |
seed44_1822
|
videos/HRA_part1/1822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, complete with a stethoscope around his neck and wearing a white lab coat over a blue button-down shirt and khaki pants, sits by a serene lake, holding a fishing rod. The peaceful scene is set against a backdrop of lush greenery and a clear blue sky, with the doctor's attire and occupation contrasting with the tranquil activity of fishing. As he casts his line into the water, the camera captures the reflective surface of the lake and the doctor's focused yet relaxed demeanor, highlighting the juxtaposition between his professional life and his leisurely pursuit.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's hand generation in the video is problematic."
}
] |
seed46_1178
|
videos/HRA_part2/1178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 scene reminiscent of a futuristic sci-fi film, a CGI-generated cobra, adorned with bioluminescent patterns, slithers across a metallic, interstellar platform set against the backdrop of a cosmic wormhole. The snake's scales shimmer with neon colors, creating a mesmerizing contrast against the cold, metallic surface. As it moves, the cobra passes by a series of glowing control panels, hinting at advanced technology integrated into the environment. In the distance, the swirling vortex of the wormhole pulses with vibrant hues, adding an element of mystery and wonder to the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3132
|
videos/HRA_part2/3132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, wearing a navy blue blazer, sits against a dark, textured background, nodding sagely as he listens to an off-screen voice. His salt-and-pepper hair, trimmed beard, and wire-rimmed glasses add to his sophisticated appearance. Throughout the scene, he continues to nod in agreement, his expressions conveying understanding and engagement. The focus remains tight on his face, capturing every nuanced gesture and emotion, highlighting his acting prowess in this intimate setting.]"
},
{
"from": "gpt",
"value": "Normal. The actor's eyes and mouth in the video have generation issues."
}
] |
seed44_1764
|
videos/HRA_part1/1764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek silver spacesuit adorned with patches, performs an energetic dance against the backdrop of a vast, star-filled universe. The scene opens with the actor floating gracefully in zero gravity, spinning and twirling with the joy of someone experiencing the wonder of space tourism. Their movements are fluid and expressive, conveying a sense of freedom and exhilaration. As the dance continues, the actor executes a series of dynamic leaps and poses, each one highlighting the unique challenges and opportunities of dancing in microgravity. The stars shimmer and galaxies glow in the distance, providing a breathtaking canvas for this cosmic performance. Throughout the video, the actor's face, visible through the clear visor of their helmet, radiates with delight, sharing the magic of space travel through the universal language of dance.]"
},
{
"from": "gpt",
"value": "Bad. The actors' movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_3036
|
videos/HRA_part0/3036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A teenage boy wearing a red jacket and khaki pants is sprinting across a grassy field, his gaze fixed ahead with determination. As he runs, a small rabbit enters the frame from the bottom right corner, bounding alongside him. The student acknowledges the rabbit with a brief glance, but both continue their run, the student maintaining his focus and the rabbit keeping pace, against the backdrop of a clear blue sky and distant green hills.]"
},
{
"from": "gpt",
"value": "Bad. The boy's limbs are missing in the video, his face is blurry, and the rabbit is deformed overall."
}
] |
seed42_1093
|
videos/HRA_part0/1093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged doctor, wearing a white lab coat over casual attire, stands pensively on a pier overlooking a serene lake, the sky a blend of sunset orange and twilight blue. Moments later, he is seen in mid-air, having leaped from the pier, his arms spread wide in a joyful gesture. His lab coat flutters dramatically in the wind as he soars above the water, about to plunge into the lake's calm surface, the fading sunlight casting a golden glow over the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1228
|
videos/HRA_part2/1228.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A solitary black rhinoceros, distinguished by its large body and dual horns, is seen in a natural habitat, wiping itself against a tree. The rhino, with its rugged skin and muscular build, rubs its side against the trunk, leaving visible marks on the bark. The action takes place in a lush environment, with green vegetation and tall trees surrounding the scene, highlighting the animal's interaction with its surroundings. The rhinoceros continues to lean into the tree, using it to scratch an unreachable spot, emphasizing the creature's natural behavior in its native environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1464
|
videos/HRA_part1/1464.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, golden expanse of the temperate grasslands, a lone dingo, its sandy fur blending with the surroundings, stands alert. It shakes off water droplets, its ears pricked forward, before wiping its face with a paw in a natural grooming gesture. The dingo then continues its vigilant stance, scanning the horizon under a clear blue sky, the wind gently swaying the tall grass around it. This intimate moment captures the creature's resilience and adaptability in its native habitat, the rolling plains stretching to the horizon under a wide, cloudless sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1500
|
videos/HRA_part1/1500.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 deer, with a full, dark brown coat and large, expressive eyes, is seen swimming across a serene lake at sunrise. Its antlers, elegantly curved and substantial, break the water's surface as it gracefully propels itself forward. The deer's head emerges from the water, its ears alert, as it navigates the tranquil lake surrounded by lush greenery and tall trees, creating a peaceful, almost mystical atmosphere. The water, clear and reflective, gently laps against the deer's body, highlighting the strength and beauty of this wild creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1689
|
videos/HRA_part1/1689.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a crisp, white linen suit and dark sunglasses, sits beside a gorilla wearing a tiny, matching outfit, on a vibrant, sandy beach bustling with activity. The lawyer and gorilla share a lighthearted moment, enjoying the coastal scenery. Nearby, a group of people splash and swim in the crystal-clear water, their laughter blending with the rhythmic sound of the waves. The camera captures this whimsical scene, focusing on the lawyer and gorilla's playful interaction against the backdrop of a stunning beach and swimmers enjoying the refreshing waters.]"
},
{
"from": "gpt",
"value": "Normal. The gorilla's clothes were not generated."
}
] |
seed44_2606
|
videos/HRA_part1/2606.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 sleek, spotted jaguar leaps powerfully across a narrow stream in a lush, green rainforest, its muscles rippling beneath golden-brown fur, with water droplets splashing upwards. The big cat's intense gaze is fixed ahead, showcasing its agility and grace in motion against the vibrant jungle setting, complete with lush vegetation and the misty atmosphere of the rainforest environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_168
|
videos/HRA_part2/168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, freshly harvested oyster lies open on a bed of crushed ice, its plump, glistening flesh nestled within the rough, grey shell. The oyster's edges are jagged, contrasting with the smooth, pearly interior. A small pool of briny liquor sits at the center, reflecting the overhead lights. Surrounding the oyster are shards of ice, creating a frosty, clean environment that enhances the raw beauty of the seafood delicacy. The overall effect is a close-up, high-definition shot that captures the essence of fresh, oceanic flavors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2699
|
videos/HRA_part1/2699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great egret, distinguished by its all-white plumage, stands tall and elegant in a shallow pond, surrounded by lush greenery and trees. Its long, slender legs, yellow-orange bill, and sharp eyesight are highlighted as it searches for prey among the reeds and water plants. The egret gracefully extends its neck, demonstrating its hunting prowess in the serene wetland environment. Moments later, it takes flight, showcasing its expansive wingspan against the clear blue sky, before landing nearby to continue its foraging activities, all within the peaceful setting of the pond and its verdant surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The egret's movements in the video are not smooth."
}
] |
seed46_1426
|
videos/HRA_part2/1426.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a white shirt, beige cardigan, and khaki pants, abandons his usual set to embark on a new project - painting a room. Surrounded by the tools of this different trade, including a paint can, roller, and painter's tape, he applies blue paint to the walls with precision and focus. His directorial experience is evident in the way he methodically transforms the space, bringing the same level of detail and vision to this task as he would to directing a scene. The room, filled with natural light, highlights the process as he adds color to the previously neutral walls.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1014
|
videos/HRA_part1/1014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent cheetah, distinguished by its tear-streaked face, black spots, and tawny coat, crawls across a lush, green savanna dotted with small trees. The big cat moves slowly, its muscles rippling beneath its skin, as it focuses intently on something just beyond the frame. The camera captures the cheetah's every movement in stunning detail, from the alertness in its eyes to the careful placement of its paws, showcasing the grace and power of this incredible creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The upper body movements are not coordinated."
}
] |
seed42_2850
|
videos/HRA_part0/2850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a blue scrubs top and black pants, stands in a verdant garden filled with lush greenery and colorful flowers. She is engaged in digging a hole with a small spade, her face expressing determination and focus. The sunlight filters through the leaves above, casting dappled shadows on the rich soil beneath her feet. Despite her work, her demeanor conveys a sense of peace and purpose, as if tending to the earth is just another form of care she provides.]"
},
{
"from": "gpt",
"value": "Normal. The woman digging holes in the video is basically normal, but her movements are slightly uncoordinated."
}
] |
seed46_1571
|
videos/HRA_part2/1571.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara is seen swimming across a tranquil body of water, its ears and nose poking above the surface as it propels itself forward with powerful kicks from its webbed feet. The scene is set against a lush, green forest backdrop, with sunlight filtering through the trees and casting dappled shadows on the water. Peaceful ripples spread out from the capybara's movements, creating a serene and captivating view of this aquatic rodent in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's nose in the video has issues, and the eyes were not generated."
}
] |
seed44_2
|
videos/HRA_part1/2.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, rustic shop filled with natural light, a cheerful cashier, wearing a red apron over a cream sweater and dark jeans, sits behind a wooden counter adorned with a vintage cash register and various knitting supplies. She expertly knits a vibrant, multi-colored scarf, her hands moving swiftly as she focuses intently on her craft. The atmosphere is warm and inviting, with the soft clacking of knitting needles adding a soothing soundtrack to the scene. Shelves stocked with yarn in various textures and hues line the walls, creating a backdrop that complements the cashier's skillful knitting.]"
},
{
"from": "gpt",
"value": "Normal. The character's actions of knitting a colorful scarf in the video are basically normal, with only slight awkwardness."
}
] |
seed46_3170
|
videos/HRA_part2/3170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a white tank top, blue denim overalls, and a wide-brimmed straw hat, sprints across a lush, green landscape dotted with ancient cemeteries. The rolling hills and distant, hazy mountains provide a scenic backdrop as he runs past weathered tombstones and aged monuments. His journey takes him along a narrow path lined with wildflowers and overgrown grass, leading through the serene burial grounds. Amidst the tranquility of the cemeteries, the farmer's vigorous run adds a dynamic element to the otherwise peaceful setting.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's limbs in the video are partially missing."
}
] |
seed46_2195
|
videos/HRA_part2/2195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, temperate deciduous forest during autumn, a dedicated park ranger wearing a brown uniform and a wide-brimmed hat runs along a winding dirt trail. Surrounded by tall, leafy trees with vibrant orange and red foliage, the ranger navigates the path with focused determination. As the camera follows, we see the ranger's strong legs propelling them forward, their breath visible in the crisp air, and their eyes alert for any signs of wildlife or forest health issues. The scenery is alive with the sounds of rustling leaves, chirping birds, and the occasional distant call of a wild animal, all contributing to the immersive experience of running in a breathtaking natural environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1187
|
videos/HRA_part0/1187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, clad in dark attire with a badge and hat, interacts with a large, gray elephant at a beachside location, both standing near the water's edge. The elephant, with its distinctive tusks and wrinkles, playfully splashes water with its trunk, while the officer watches with an amused smile. In another scene, the officer gently pats the elephant's head, which is dripping with water, suggesting they have been swimming together. Lastly, the duo is captured in a heartwarming moment, with the officer and the soaking-wet elephant sharing a tender interaction against the serene backdrop of a sandy shore and the vast ocean.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1421
|
videos/HRA_part2/1421.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a red checkered shirt, brown apron, and khaki pants, takes a break from cooking to rake leaves in a suburban backyard. He pauses for a moment, looking thoughtful, before continuing his task with determination. The chef, now smiling, rakes a large pile of autumn leaves into a heap, enjoying the crisp fall weather. Finally, he pauses again, this time looking pleased with his work, standing next to the sizable leaf pile, with his rake resting on his right shoulder, and a residential neighborhood visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the khaki pants, the chef's thoughtful expression, and the scene of the chef resting with a rake on his right shoulder and a residential neighborhood in the background."
}
] |
seed46_2146
|
videos/HRA_part2/2146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ghost shrimp, nearly transparent with greyish-blue tones, clings to a piece of driftwood submerged in a freshwater aquarium. Its delicate antennae and legs are clearly visible, showcasing its intricate anatomy. Nearby, water bubbles softly, adding a gentle ambience to the scene. The shrimp's translucent body allows a view of its internal organs, emphasizing its unique characteristic. Surrounded by aquatic plants and gravel, the ghost shrimp appears in sharp focus against the slightly blurred environment, highlighting its presence in the tank.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2920
|
videos/HRA_part0/2920.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a crisp white shirt, black trousers, and a waistcoat, unexpectedly finds himself fixing a leaky faucet in a vintage-styled restroom. With a wrench in hand, he leans over the basin, his face concentrated as he works under the sink. The scene captures the unusual sight of the waiter, his attire contrasting with the task at hand, as he tightens the faucet, the water now streaming smoothly. The room is adorned with antique fixtures and a classic mirror above the basin, adding to the unique scenario of a waiter turned handyman.]"
},
{
"from": "gpt",
"value": "Bad. The server's hands appear deformed."
}
] |
seed42_1151
|
videos/HRA_part0/1151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a black beret and glasses, sits at a cluttered desk in a dimly lit room, affectionately caressing a small bat perched on her finger. The bat, appearing relaxed and comfortable, is nestled against her hand, which is adorned with silver rings. The scene is set against a backdrop of bookshelves filled with various books, adding to the intellectual and mysterious atmosphere. The writer's other hand rests on a vintage typewriter, hinting at her profession, while the bat's presence introduces an element of the unusual into the intimate scene.]"
},
{
"from": "gpt",
"value": "Normal. The writer's action of petting the bat in the video is basically normal, with only slight awkwardness."
}
] |
seed46_2713
|
videos/HRA_part2/2713.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning safety glasses and a gray shirt with a vest, is depicted laughing heartily while standing in front of an industrial machine with complex machinery in the background, creating a sense of a bustling factory environment. His laughter is contagious, brightening the otherwise serious atmosphere of the workshop, where metal parts and tools are scattered across workbenches. The scene captures the engineer's genuine joy, offering a glimpse into the lighter moments within a typically intense work setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2491
|
videos/HRA_part2/2491.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, wearing a traditional white chef's uniform with a tall hat, stands in a modern, well-lit kitchen. He is staring intently at a plate of food he has just prepared, which features a vibrant, colorful dish garnished with fresh herbs. The kitchen is spotless, with stainless steel appliances and countertops, and the chef's focus on the plate highlights his dedication to culinary perfection.]"
},
{
"from": "gpt",
"value": "Normal. The chef's face and hands in the video are disproportionately generated."
}
] |
seed42_3052
|
videos/HRA_part0/3052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling art gallery filled with contemporary paintings and sculptures, a distinguished film director, wearing a gray suit with a blue shirt and tie, passionately discusses a project with two colleagues. Suddenly, he breaks into an impromptu dance, spinning and moving with joyful abandon. The gallery space, illuminated by spotlights highlighting the artwork, becomes his stage, with onlookers smiling and watching his spontaneous performance. Throughout, the director's animated expressions and gestures convey his enthusiasm and creativity, all captured in high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The director's movements in the video are not smooth."
}
] |
seed42_2687
|
videos/HRA_part0/2687.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling metropolis, an innovative female engineer wearing safety glasses and a reflective vest runs through a construction site filled with cranes and skyscrapers under construction. Her stride is confident, highlighting her determination. She navigates around concrete pillars and rebar, demonstrating agility amidst the urban landscape. The cityscape, featuring tall buildings and bridges, serves as a backdrop, emphasizing the scale of her environment. Throughout the scene, she maintains her composure, showcasing her expertise and passion for engineering in an active urban setting.]"
},
{
"from": "gpt",
"value": "Normal. The female engineer's limbs in the video are deformed, the body proportions are incorrect, and the face is blurry."
}
] |
seed42_2880
|
videos/HRA_part0/2880.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a flowing white dress, interacts with a majestic lion in a surreal setting, emphasizing their connection. She crawls on a surface covered with lush green grass, facing the lion with a relaxed demeanor. The lion, also crawling, responds to her with curiosity, its golden eyes locked onto hers. Both the woman and the lion are framed by the vibrant greenery of their surroundings, highlighting the unusual yet peaceful encounter between human and beast.]"
},
{
"from": "gpt",
"value": "Bad. The lion's movements in the video are not smooth."
}
] |
seed42_11
|
videos/HRA_part0/11.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rocky terrain below. It circles gracefully, riding the thermals, with a backdrop of lush green mountains and a distant waterfall. Its piercing yellow eyes scan the landscape, searching for prey, while its sharp talons remain ready to strike. The eagle's brown and white plumage glistens in the sunlight, a symbol of freedom and strength against the stunning natural scenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2235
|
videos/HRA_part1/2235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala clad in a tiny business suit scampers across a bustling cityscape, its fluffy ears bouncing as it weaves between the legs of hurried office workers. The koala, wearing a miniature tie and vest, darts through the concrete jungle, leaping over cracks in the sidewalk and dodging rolling suitcases. Its button nose and round eyes convey determination as it races toward an imposing glass skyscraper, its reflection merging with the building's sleek facade. The koala's paw steps on the polished marble floor echo through the cavernous lobby, drawing curious glances from suited professionals, who pause in their daily routines to watch the unexpected visitor sprint toward the elevators.]"
},
{
"from": "gpt",
"value": "Bad. The koala's movements in the video are not smooth."
}
] |
seed46_2159
|
videos/HRA_part2/2159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a classic black vest and white shirt, serves a tray of colorful cocktails to a hyena lounging poolside. The hyena, wearing sunglasses and a lei, enjoys its day off from the wild, basking in the sun. Suddenly, the hyena leaps into the swimming pool with playful abandon, while the waiter looks on, amused yet professional, maintaining his composure despite the unexpected splash. The scene captures a surreal moment of relaxation and fun, blending elements of the exotic and the everyday.]"
},
{
"from": "gpt",
"value": "Bad. The hyena's body undergoes a deformity mutation when performing actions."
}
] |
seed44_3072
|
videos/HRA_part1/3072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a futuristic suit adorned with gleaming badges and equipped with advanced technology, stands under the Martian night sky. The officer, with a strong, determined face, gazes upward at the stars with a sense of wonder and tranquility, the red landscape of Mars stretching out behind. The focus is on the officer's hands gently caressing the surface of a small, glowing orb, symbolic of a connection to Earth or perhaps a personal memento, all while the constellations above provide a breathtaking, otherworldly backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the small glowing orb mentioned in the caption."
}
] |
seed44_2850
|
videos/HRA_part1/2850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a blue scrubs top and black pants, stands in a verdant garden filled with lush greenery and colorful flowers. She is engaged in digging a hole with a small spade, her face expressing determination and focus. The sunlight filters through the leaves above, casting dappled shadows on the rich soil beneath her feet. Despite her work, her demeanor conveys a sense of peace and purpose, as if tending to the earth is just another form of care she provides.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1426
|
videos/HRA_part1/1426.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a white shirt, beige cardigan, and khaki pants, abandons his usual set to embark on a new project - painting a room. Surrounded by the tools of this different trade, including a paint can, roller, and painter's tape, he applies blue paint to the walls with precision and focus. His directorial experience is evident in the way he methodically transforms the space, bringing the same level of detail and vision to this task as he would to directing a scene. The room, filled with natural light, highlights the process as he adds color to the previously neutral walls.]"
},
{
"from": "gpt",
"value": "Normal. The director's arm and fingers in the video have generation issues, and the roller brush is generated with defects."
}
] |
seed42_1518
|
videos/HRA_part0/1518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, elegant restaurant, a human-like weasel dressed in a formal waiter's uniform, complete with a crisp white shirt, black vest, and bow tie, is shown caressing a wine glass with intricate patterns, displaying its refined touch and attention to detail. The weasel's anthropomorphic features are enhanced by its upright posture and expressive face, which conveys sophistication and professionalism. The scene is set against a backdrop of luxurious dining, with the weasel's gentle handling of the glass highlighting its dexterity and grace.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1555
|
videos/HRA_part2/1555.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, animated scene, a scholarly mouse, dressed in a blue cap and gown, sits at a desk cluttered with books, pens, and a laptop, studying intently under a bright lamp. Suddenly, the mouse finds itself transported to a futuristic space casino, complete with neon lights, slot machines, and alien patrons. The mouse, now wearing a stylish tuxedo, confidently plays a game of cards, surrounded by an eclectic crowd. In the next moment, the setting changes to a luxurious, zero-gravity swimming pool, where the mouse, now in swimming trunks, happily splashes and swims among bubbles and floating objects, enjoying its unexpected adventure.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the scene where the mouse wearing swimming trunks happily plays in a luxurious, zero-gravity swimming pool."
}
] |
seed42_2030
|
videos/HRA_part0/2030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, a type of wild mountain goat, is depicted walking steadily across a rocky terrain with snow-capped peaks in the background. The animal, characterized by its curved horns and brown fur, moves with a purposeful gait, navigating the rugged landscape. It pauses momentarily, standing tall on a stone ledge, offering a side profile view, before continuing its journey. Throughout the scene, the ibex's resilience and adaptability to its harsh environment are highlighted, set against the dramatic backdrop of a high-altitude mountain range.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_21
|
videos/HRA_part0/21.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man with short brown hair, wearing a khaki safari shirt and matching trousers, stands in a lush, verdant enclosure at a wildlife sanctuary. He gently caresses the wrinkled, gray skin of a large hippopotamus, which towers over him, standing on its hind legs with its front paws on the man's shoulders. The man looks up at the creature with a mixture of awe and tenderness, while the hippo appears relaxed and comfortable with the interaction. The enclosure is filled with tall grasses and scattered trees, providing a natural habitat for the animal, and the man's presence suggests a close bond between human caretaker and wild creature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2584
|
videos/HRA_part2/2584.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a lone jackal stands amidst an otherworldly landscape of active volcanoes, its golden eyes reflecting determination. The creature is seen wiping its face with a paw, a gesture of cleansing, against a backdrop of billowing ash and molten lava flows. Surrounded by the harsh beauty of erupting peaks, the jackal's action conveys resilience and survival in the face of adversity, with the volcanoes' fiery eruptions illuminating the dramatic environment.]"
},
{
"from": "gpt",
"value": "Bad. The hyena in the video has missing limbs, an overly long tail, and a deformed body."
}
] |
seed46_1971
|
videos/HRA_part2/1971.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair, wearing a gray shirt, sits at a modern office desk cluttered with electronics and tools, knitting a red scarf with large needles. The focus is on her hands as they deftly manipulate the yarn and needles, while a laptop with coding screensaver and a blueprint of a circuit board are visible in the background. The office space is filled with tech gadgets, books, and papers, highlighting her professional environment, yet she finds time for a personal hobby, creating a vivid red scarf amidst the technical surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_1293
|
videos/HRA_part0/1293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, dressed in a pristine white uniform and wearing a red bandana, walks across a rocky Martian landscape under a starlit sky. Holding a large, clear bowl that reflects the celestial beauty above, the chef pauses to gaze upwards, captivated by the distant stars. With the vast Martian terrain spread out behind, the scene conveys a sense of wonder and exploration, as the chef embarks on a unique stargazing experience on the Red Planet.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3216
|
videos/HRA_part0/3216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray jacket and blue jeans, runs with a determined look across a desolate industrial landscape dominated by oil refineries. The scene opens with him striding purposefully, his gaze fixed ahead. Next, he's seen mid-stride, his right arm extended forward, the refineries' towering structures and billowing smokestacks looming behind him. Then, he's captured in motion, his left foot lifting from the ground, the industrial backdrop providing a stark contrast to his vibrant attire. Finally, the artist continues his run, his silhouette framed against the imposing oil refinery complex, embodying resilience and movement in an urban-industrial setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_2406
|
videos/HRA_part1/2406.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A warbler perches on a thin branch, its vibrant yellow and olive-green feathers illuminated by the soft sunlight filtering through the dense foliage of a lush forest. Its bright yellow underparts contrast sharply with the olive-green upperparts, while its two wing bars and eyestripe add distinctive touches. The bird's sharp, dark eye is focused intently ahead, and its slender beak is slightly open, as if about to burst into song. The warbler's delicate feet grip the branch firmly, and its tail feathers fan out slightly, adding balance as it prepares to take flight or sing its melodic tune.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2693
|
videos/HRA_part1/2693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a helmet, walks alongside a majestic elephant, both navigating through a lush, green environment. The firefighter's equipment includes a heavy-duty jacket, pants, boots, and gloves, signifying readiness for any emergency. The elephant, adorned with intricate patterns on its body, suggests a cultural or ceremonial context. Together, they traverse a dirt path surrounded by dense vegetation, creating an unexpected yet compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, and feet are distorted in the video, as well as the elephant's face."
}
] |
seed42_1091
|
videos/HRA_part0/1091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space-themed wedding set against a cosmic backdrop filled with stars and galaxies, a charming hedgehog, adorned with a tiny top hat and bow tie, serves as the ring bearer. The ceremony takes place on a floating platform amidst a zero-gravity environment. During the reception, the hedgehog enjoys a unique swimming experience in a clear, spherical water tank, effortlessly paddling with its limbs while maintaining its adorable appearance, all while the celebration continues around it.]"
},
{
"from": "gpt",
"value": "Normal. The video lacks a bow tie and a transparent spherical aquarium."
}
] |
seed44_1532
|
videos/HRA_part1/1532.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A weathered farmer wearing a brown jacket and wide-brimmed hat kneels in a lush, green field, engaging in meticulous work. Suddenly, the scene reveals that he is crawling, his focused eyes set on the task at hand, perhaps planting seeds or tending to crops. Uncommonly, a zebra stands nearby, watching the farmer with interest, its distinctive black-and-white stripes stark against the verdant landscape. The farmer continues to crawl through the rows, the zebra's presence adding an unexpected element to the pastoral setting. Throughout, the farmer's dedication to his work and the zebra's curious observation create a unique agricultural tableau.]"
},
{
"from": "gpt",
"value": "Bad. The crawling motion can be seen, but the movements are uncoordinated and abrupt."
}
] |
seed46_3153
|
videos/HRA_part2/3153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a brown jacket and blue jeans, walks along a wooden path near a lake, holding a green notebook. An otter swims in the foreground, its head occasionally popping up from the water, mirroring the writer's pace. The writer stops, looking thoughtful, then continues walking, passing a wooden post and a tree with orange leaves, suggesting an autumn day. The otter follows suit, diving under the water and reappearing alongside the writer, who now looks down at the playful creature, sharing a moment of connection in nature.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the otter can be seen swimming in the water, but the movements are very discontinuous and uncoordinated."
}
] |
seed46_1121
|
videos/HRA_part2/1121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a khaki safari outfit, is seen in a lush, green jungle environment, carefully cleaning a majestic tiger with a large cloth. The tiger, displaying distinctive orange stripes on a white underbelly, remains calm and cooperative during the process. The director, showing respect and gentleness, focuses intently on wiping the tiger, highlighting a unique bond between human and animal in a wild setting.]"
},
{
"from": "gpt",
"value": "Normal. The hand of the character in the middle frame of the video suddenly distorts and deforms."
}
] |
seed46_2793
|
videos/HRA_part2/2793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a crisp, white lab coat over a blue shirt and khaki pants, leaps playfully along a weathered boardwalk by the ocean, his stethoscope swinging freely. The setting sun casts a golden hue over the scene, highlighting the contrast between his professional attire and the casual, joyful activity. The boardwalk, lined with aged wooden planks, extends into the distance, offering a picturesque view of the shoreline and the sea beyond. The doctor's action, captured mid-jump, conveys a sense of freedom and happiness, juxtaposed against the typically serious context associated with medical professionals.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's jumping in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_1775
|
videos/HRA_part1/1775.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 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 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": "Bad. The beaver's movements in the video are not smooth and coordinated."
}
] |
seed42_1082
|
videos/HRA_part0/1082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a student, identifiable by their backpack and casual attire, is crawling through a crowded mall. This unusual behavior attracts the curious gaze of shoppers, who pause to watch. Unexpectedly, a hyena, also crawling and wearing a backpack, joins the student. Both crawl side by side, blending into the urban environment, creating a bizarre yet harmonious scene amidst the mall's vibrant storefronts and bustling pedestrian traffic.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2739
|
videos/HRA_part1/2739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, clad in a light blue uniform, gently caresses the fur of a calm, gray wolf sitting beside her, both under the shade of a large tree in a grassy field. The wolf looks up at her with a relaxed demeanor, while she tenderly strokes its head, conveying a sense of mutual trust and peace between human and wild animal. Moments later, she holds the wolf's snout softly, her caring gaze meeting its calm eyes, with the serene natural surroundings enhancing the emotional connection depicted.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's movements of petting the gray wolf in the video are not smooth and coordinated, with sudden changes in action."
}
] |
seed42_1069
|
videos/HRA_part0/1069.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 wildlife park worker, clad in khaki shorts, a green shirt, and a wide-brimmed hat, interacts closely with a hippopotamus in a large, naturalistic enclosure filled with clear, blue water. The worker confidently swims alongside the hippo, which floats gracefully on its back, showcasing the unique bond between caretaker and animal in a peaceful, sunlit setting. Moments later, the worker is seen playfully engaging with the hippopotamus, which swims submerged in the water, its eyes closed in apparent bliss, highlighting the trust and connection they share in their aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2138
|
videos/HRA_part0/2138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and gun holster, is kneeling in a park, intently digging with a small shovel into a patch of dirt surrounded by green grass and shrubs. The scene is set under a clear blue sky, with the officer's focus and determination evident as they meticulously excavate the soil. Moments later, the officer, still in their navy uniform and gear, carefully sifts through the dirt with gloved hands, searching for evidence with a serious expression. The location remains the same, a serene park with lush greenery and a cloudless sky overhead.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's digging motion in the video is basically normal, but there is some lack of coordination."
}
] |
seed46_1742
|
videos/HRA_part2/1742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an aquarium filled with clear, blue water, a translucent ghost shrimp, barely visible, floats motionless near the bottom, its delicate legs folded. It then swims upward slowly, revealing its transparent body and the tiny creature inside, before coming to a stop near the surface. The shrimp hovers there, seemingly weightless, before descending again to the sandy bottom, dotted with small stones and pieces of aquatic plants, offering a glimpse into the elusive life of this ethereal crustacean.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the scene of the ghost shrimp moving up and down."
}
] |
seed44_2616
|
videos/HRA_part1/2616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, muscular man, shirtless and wearing only swimming trunks, stands on a vast Martian landscape, gazing up at the star-studded night sky. The red, rocky terrain stretches out behind him, dotted with boulders and craters, while a faint horizon line suggests the curvature of the planet. In the foreground, the man has just emerged from a clear, shimmering pool of water, droplets clinging to his skin and the rocks around him. The pool, seemingly out of place on this arid world, adds an element of mystery and wonder to the scene, as the man contemplates the cosmos from this otherworldly vantage point.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_318
|
videos/HRA_part2/318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged female teacher waves energetically with both hands, standing against a classroom backdrop filled with educational posters and a whiteboard. Dressed in a vibrant red blouse and dark pants, she wears a welcoming smile, her wavy brown hair framing her face. Her enthusiastic gesture conveys warmth and inclusivity, inviting students into the learning environment. The classroom setting includes rows of desks, a bookshelf, and a large window allowing ample natural light, enhancing the sense of openness and engagement.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1735
|
videos/HRA_part2/1735.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom setting, a cartoon beaver, wearing a brown graduation cap and holding a yellow eraser, energetically wipes a green chalkboard clean, revealing a lesson about the water cycle. The beaver, now wearing a white shirt with a red tie and a brown vest, continues to erase enthusiastically, displaying a fun and engaging teaching style. Next, the beaver, still in its academic attire, uses the eraser to remove the last bit of chalk from the board, ensuring the surface is completely clear. Finally, the animated beaver teacher, dressed in its scholarly outfit, stands proudly beside the now-blank chalkboard, ready for the next lesson.]"
},
{
"from": "gpt",
"value": "Normal. The more you erase, the more words appear, which is unrealistic, and the blackboard eraser in hand appears deformed."
}
] |
seed44_2005
|
videos/HRA_part1/2005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man dressed as a waiter, wearing a black vest, white shirt, black tie, and apron, is playfully dancing with a horse in the middle of a grassy field under a clear blue sky. The horse, adorned with a golden bridle and red and gold saddle blanket, seems to be enjoying the unexpected dance, moving gracefully in sync with the waiter's steps. Both the waiter and the horse exhibit expressions of pure joy and abandon, creating a surreal yet delightful spectacle. The vibrant colors of their attire contrast beautifully with the natural greenery and blue sky, adding to the dreamlike quality of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The horse's movements are not noticeable."
}
] |
seed44_1643
|
videos/HRA_part1/1643.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European ring-necked pheasant, with its vibrant plumage featuring striking shades of green, gold, and brown, struts confidently across a grassy field. Its iridescent feathers shimmer in the sunlight, accentuated by the lush green vegetation in the background. The pheasant pauses, its head held high, showcasing the distinctive white collar around its neck and the bold red wattles near its eyes. It then resumes its stately walk, tail feathers fanning out gracefully, embodying the elegance and beauty of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2164
|
videos/HRA_part2/2164.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gorilla wearing a stethoscope and a white doctor's coat is sprinting on a treadmill, set against a vibrant green jungle backdrop. The gorilla, appearing fit and healthy, focuses intently on its workout, while the jungle environment is alive with lush vegetation and exotic flora. This unusual yet captivating sight captures the essence of a gorilla doctor maintaining physical fitness in a natural yet surreal setting.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's movements in the video are very unsmooth and uncoordinated."
}
] |
seed46_244
|
videos/HRA_part2/244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and holding a fire axe, leaps over a low obstacle in a training course, with a large, taxidermied leopard positioned on the ground nearby, creating an unusual juxtaposition of elements. The firefighter's helmet gleams under the bright lights, and the scene is set against a backdrop of firefighting equipment and vehicles, emphasizing the intensity and unpredictability of their training exercises.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2374
|
videos/HRA_part1/2374.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinctively attired in a crisp white shirt, black vest, and black trousers, diligently cleans the expansive windows of an upscale restaurant. Surrounded by lush greenery, he expertly maneuvers a squeegee across the glass, ensuring crystal-clear transparency. With focused determination, he tackles the task at hand, his movements methodical and efficient. The vibrant outdoor foliage contrasts sharply with the clean, modern lines of the building, highlighting the meticulous attention to detail in maintaining the restaurant's pristine appearance.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's squeegee suddenly disappears, and the waiter's hand and arm also undergo deformity and mutation. Additionally, the waiter's black vest is worn inside out."
}
] |
seed42_1668
|
videos/HRA_part0/1668.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sweeping natural landscape, a large bison is rolling on the ground, seemingly wiping itself in the dirt, surrounded by tall grass and distant mountains under a clear blue sky. The bison, with its shaggy brown fur, is seen from various angles, including a close-up of its face as it looks up, showing its rugged features and expressive eyes. Another shot captures the bison from above, highlighting its massive size and the texture of its coat against the sandy ground. Lastly, the bison is shown standing, shaking off the dust, its powerful body and majestic presence commanding respect in its wild habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2708
|
videos/HRA_part2/2708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy hamster, primarily white with gray patches, leaps into the air from within a wire cage, its hind legs propelling it upwards with remarkable agility. The hamster's front paws extend forward as it jumps, highlighting its determination and playfulness. The scene is set against a backdrop of a green meadow, creating a whimsical contrast between the indoor cage and the outdoor setting. The hamster's joyful leap is captured in high detail, showcasing its adventurous spirit and the soft fur that covers its body.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's mouth, ears, and limbs in the video have generation issues, with the limbs suddenly appearing or disappearing in middle frames."
}
] |
seed44_2967
|
videos/HRA_part1/2967.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lark soars gracefully across a vast, cloud-dappled sky, its russet and brown plumage shimmering in the sunlight. It sings a jubilant melody, filling the air with its clear, melodious notes. The bird then descends into a lush, green meadow dotted with vibrant wildflowers, where it lands softly on a swaying stalk of grass. Its bright eyes scan the surroundings, alert and curious, before taking flight again, its song echoing through the peaceful landscape.]"
},
{
"from": "gpt",
"value": "Bad. The bird's flight in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_1637
|
videos/HRA_part1/1637.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden retriever, framed against a vibrant green meadow under a clear blue sky, experiences a unique perception of time as it runs. Initially, the dog is seen standing still, looking forward with anticipation. It then starts running, its legs blurring as if time has accelerated for the viewer. Next, the dog leaps into the air, seemingly frozen in mid-air, giving the impression of time slowing down. Finally, the dog bounds across the field, its motion smooth and unhurried, conveying a sense of normal time flow, all while the lush green landscape and clear blue sky provide a serene backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The dog's limbs and paws are missing in the video, the overall picture is relatively blurry, and the body is twisted."
}
] |
seed46_1405
|
videos/HRA_part2/1405.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, curious ferret clad in a tiny green jacket ambles along a wooden floor, its alert eyes scanning its surroundings. It pauses for a moment, seemingly considering its next move, before continuing its journey. The ferret then stops again, standing on its hind legs with its front paws raised, revealing the white fur beneath the jacket. Its head turns to look directly at the camera, a mischievous glint in its eyes, before it resumes walking, the green jacket swaying with each step. Throughout the video, the ferret's movements are unhurried and deliberate, as it explores its environment with a mix of caution and curiosity.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's paws are twisted, and its face is slightly deformed."
}
] |
seed42_1266
|
videos/HRA_part0/1266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artistic individual, donning a gray beanie, black jacket, and blue jeans, stands on the weathered wooden planks of a dock by the water's edge, with a vibrant cityscape visible across the bay. The artist leaps into the air, capturing the essence of freedom, while holding a sketchbook, which hints at their creative pursuits. The scene is bathed in golden hour sunlight, casting a warm glow over the figure and the urban landscape, creating a sense of serenity and inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_1171
|
videos/HRA_part1/1171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wildlife sanctuary, a compassionate veterinarian, wearing a khaki shirt and cargo pants, gently wipes the face of a majestic cheetah lying on a checkered cloth, its gaze fixed on the vet. The scene is set outdoors, with lush greenery and wooden fences framing the backdrop, highlighting the unique bond between the medical professional and the wild animal. The vet's careful action, using a soft, white cloth, conveys a sense of tenderness and care, while the cheetah's calm demeanor suggests trust and familiarity.]"
},
{
"from": "gpt",
"value": "Bad. The vet's hand generation in the video is problematic."
}
] |
seed46_311
|
videos/HRA_part2/311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow high-visibility vest over a gray jacket, khaki cargo pants, and black shoes, rests his head on his right arm, which is propped on a mop handle. He leans against a wall, his body language conveying exhaustion, as he takes a nap beside a bucket and cleaning supplies, all bathed in dim light. Moments later, the scene subtly changes, showing him still asleep, now with his left hand resting on his forehead, while the bucket and cleaning tools remain nearby. This sequence captures the quiet solitude and hard work of a janitor during his brief respite.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1412
|
videos/HRA_part1/1412.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, male gorilla with a silverback lumbers through the dense undergrowth of a temperate deciduous forest, illuminated by dappled sunlight filtering through the leafy canopy above. The gorilla, clad in his natural silver fur, moves with purpose, navigating the rich ecosystem of tall oaks and maples. His powerful form is juxtaposed against the lush greenery, creating a captivating scene as he walks among the towering trees, showcasing the raw beauty of nature in these vibrant woodlands.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_139
|
videos/HRA_part2/139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a green shirt and black pants, kneels in a grassy outdoor setting, intently observing a small brown hedgehog. The hedgehog, rolling into a ball and uncurling repeatedly, captures the director's attention as it explores its surroundings. Suddenly, the hedgehog leaps into the air, its spines gleaming in the sunlight, while the director watches with fascination, camera in hand, ready to capture this unexpected moment of agility against a backdrop of lush greenery.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous; the hedgehog's crawling motion has sudden changes, and the director in the background is static, lacking movement."
}
] |
seed44_1939
|
videos/HRA_part1/1939.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 smiling student, dressed in a green T-shirt and gray pants, joyfully jumps alongside a kangaroo in a lush, green field under a clear blue sky. The student, wearing brown shoes and a wristwatch, mimics the kangaroo's hopping motion, capturing a moment of playful interaction between human and nature. The kangaroo, with its distinctive features and powerful hind legs, bounds gracefully next to the enthusiastic student, both enjoying the freedom of movement against the serene backdrop of the outdoors.]"
},
{
"from": "gpt",
"value": "Normal. No watch was generated."
}
] |
seed44_2368
|
videos/HRA_part1/2368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling supermarket setting, a young female cashier, wearing a red apron over a black and white striped shirt, pushes a shopping cart filled with groceries toward the checkout counter. She has a determined look on her face, and her curly brown hair is tied back in a bun. The cart is stacked with various items, including a large watermelon on top, as she navigates the busy aisle, surrounded by shelves packed with products and other shoppers. The scene captures the dynamic environment of a grocery store during peak hours, with the cashier diligently managing her tasks amidst the activity.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video has a slightly distorted body, with twisted hands."
}
] |
seed46_1819
|
videos/HRA_part2/1819.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 teacher, wearing a gray jacket over a button-down shirt, shakes vigorously, appearing disoriented, with eyes closed and mouth agape, against a classroom backdrop featuring a whiteboard filled with algebraic equations. Moments later, she is seen in profile, shaking her head from side to side with eyes closed, suggesting intense emotion. Then, she shakes her head again, her expression reflecting determination, as she stands against a classroom wall adorned with a periodic table poster. Finally, she looks directly at the camera, shaking her head in disbelief, her demeanor and attire consistent throughout the scenes.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2607
|
videos/HRA_part2/2607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint village setting, a cheerful female cashier, wearing a yellow apron over a casual outfit, dances joyfully behind the counter of a rustic wooden market stall. The stall is adorned with colorful decorations and surrounded by vibrant greenery, enhancing the festive atmosphere. She moves energetically to an unseen beat, her smile contagious, as she momentarily pauses her duties to revel in the music. The village backdrop includes traditional architecture, bustling locals, and a lively community gathering, all contributing to the sense of celebration and unity.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1814
|
videos/HRA_part2/1814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large moose, adorned with a red bow tie and a top hat, stands on a wooden boardwalk illuminated by warm, golden lights. It gracefully sways side to side, as if dancing to an invisible melody, under a starlit night sky. The boardwalk stretches into the distance, lined with quaint shops and twinkling lanterns, creating a surreal and enchanting atmosphere where reality and fantasy blend seamlessly.]"
},
{
"from": "gpt",
"value": "Bad. The deer's limbs are missing, the body is deformed, the antlers are problematic, and the tail is not generated."
}
] |
seed44_2953
|
videos/HRA_part1/2953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a blue t-shirt and khaki shorts, runs across a vast desert landscape under a clear blue sky, with distant mountains providing a dramatic backdrop. The student, wearing a backpack and a cap, navigates the sandy terrain with determination, the camera capturing the texture of the dunes and the play of light and shadow. As the scene progresses, the focus remains on the runner, highlighting their stamina and resilience against the stark beauty of the desert environment.]"
},
{
"from": "gpt",
"value": "Bad. The student's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_2462
|
videos/HRA_part1/2462.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic African elephant, distinguished by its large ears and robust body, is sprinting across a sunlit savanna, leaving a trail of dust in its wake. Its skin, textured and gray, contrasts beautifully with the lush green vegetation surrounding it. The elephant's tusks, curved and formidable, add to its regal appearance as it runs with surprising speed and grace through the open plains, showcasing the powerful muscles rippling beneath its thick skin.]"
},
{
"from": "gpt",
"value": "Bad. The elephant's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_1002
|
videos/HRA_part1/1002.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patient teacher, dressed in a khaki shirt and denim jeans, sits on a wooden pier with fishing gear, teaching a young student the art of fishing. The teacher demonstrates casting a line into a serene lake at sunset, the water reflecting the warm hues of twilight. The student, wearing a red cap and a green vest, attentively watches, holding a fishing rod, as the teacher guides them on the pier. The teacher then hands the student a small fish, caught during the lesson, fostering a connection between nature and learning. Throughout, the teacher wears a wide-brimmed hat and a yellow life jacket, while the student is dressed in a red baseball cap, a green fishing vest, and holds a child-sized fishing rod, both immersed in the peaceful act of fishing by the water's edge.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the teacher and student in the video are not continuous and there are abrupt changes."
}
] |
seed46_273
|
videos/HRA_part2/273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Turkey, a vibrant market comes alive with colors and aromas. Rows of stalls adorned with strings of bright red Turkish peppers hang from the ceiling, creating a striking contrast against the blue sky visible through the open roof. Intricately woven rugs in shades of red, green, and yellow cover the walls and floors, while golden lanterns dangle overhead. Amidst the bustling crowd, a vendor passionately promotes his goods, his gestures animated and expressive. Shoppers haggle over prices, their lively exchanges adding to the market's energetic atmosphere. The scene captures the essence of Turkish culture, blending tradition with the dynamic spirit of commerce.]"
},
{
"from": "gpt",
"value": "Bad. The faces and hands of the vendors and customers in the video were generated abnormally."
}
] |
seed42_1791
|
videos/HRA_part0/1791.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a navy blue shirt and beige trousers, gently caresses a buffalo in a rural setting. The buffalo, with its shaggy brown fur and large horns, stands calmly under a clear blue sky, with lush green grass and distant trees providing a peaceful backdrop. The engineer, showing a tender side, connects with the animal, which is often a symbol of strength and resilience, in a moment of quiet intimacy amidst the natural landscape.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video, as well as the buffalo's face."
}
] |
seed44_2147
|
videos/HRA_part1/2147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a sky-blue uniform, complete with a matching cap, stands at the edge of a bustling harbor. The sun illuminates her figure as she prepares to leap into the air, her silhouette framed by the vibrant scene of ships and docks in the background. Her joyful expression contrasts with the busy maritime activities, capturing a spontaneous moment of playfulness amidst a working waterfront.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2654
|
videos/HRA_part0/2654.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a black jacket, jeans, and a gray shirt, stands on a bustling movie set under bright lights. Holding a megaphone in one hand and gesturing emphatically with the other, he directs actors and crew members with passion and precision. The set is filled with vintage cars from the 1950s, indicating a period drama, while the director's focused gaze and expressive body language convey his dedication to capturing the perfect shot. Surrounded by a diverse cast and crew, he moves with purpose, demonstrating his leadership and vision in the dynamic environment of a film production.]"
},
{
"from": "gpt",
"value": "Bad. The director's movements in the video are not smooth and continuous."
}
] |
seed44_1019
|
videos/HRA_part1/1019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly contrasting scene, a middle-aged, bespectacled teacher wearing a gray jacket, blue shirt, and khaki pants runs alongside a majestic, wild panther, both moving at full speed across a lush green field under a bright blue sky. The teacher, with short brown hair and a look of intense focus, matches strides with the powerful feline, its sleek black fur rippling in the wind as it sprints effortlessly beside him. The unlikely pair cuts through the vibrant grassland, the teacher's clothing billowing slightly from the momentum, creating an extraordinary and dynamic image of an educator and a panther in motion together.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3044
|
videos/HRA_part0/3044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, donning a clean white uniform and a traditional toque blanche hat, sits at a modern, sleek kitchen table. He is intently typing on a laptop, his fingers deftly moving across the keyboard, with the focus of someone accustomed to multitasking. The background is a bustling commercial kitchen, filled with stainless steel appliances and busy staff working in harmony. Despite the chaos around him, the chef remains composed and focused on his task, exemplifying the blend of professionalism and culinary expertise.]"
},
{
"from": "gpt",
"value": "Normal. The middle-aged male chef's hands in the video have generation issues, and the employees in the background are generated blurry."
}
] |
seed42_2428
|
videos/HRA_part0/2428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a small, slender green lizard with intricate patterns on its skin, perched on a dry, cracked earth surface under a clear blue sky. It licks its eye with its forked tongue, performing a natural behavior known as eye wiping, which helps keep its eyes clean. The scene is set outdoors, with the lizard's textured skin and the arid landscape providing a stark contrast against the vibrant blue sky in the background.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.