video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_325
|
videos/HRA_part1/325.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his gray beard and wearing a dark jacket, blue shirt, and khaki pants, interacts closely with a chimpanzee. The chimpanzee, positioned on a wooden structure in a spacious indoor setting, leaps energetically into the air, demonstrating its agility. The director observes intently, possibly guiding the action or assessing the performance, while standing on the same platform as the chimpanzee, which is enclosed within the large room. The scene captures the unique collaboration between human and animal in the context of filmmaking.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the chimpanzee leaping onto a wooden structure, but the movements are discontinuous and there are abrupt changes."
}
] |
seed42_1611
|
videos/HRA_part0/1611.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus, showcasing its remarkable camouflage abilities, rests on a sandy seabed, its body appearing as a collection of scattered stones and sand patches. It then changes color and texture, mimicking a cluster of sponges and corals, demonstrating its incredible mimicry skills. Next, it displays a pattern resembling seaweed and plant life, swaying gently as if caught in an underwater current. Finally, the octopus morphs into an imitation of a rocky outcrop, complete with algae and barnacles, further highlighting its extraordinary ability to blend into various marine environments.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1441
|
videos/HRA_part0/1441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, nestled in the fork of a lush eucalyptus tree, gently caresses its companion with a fuzzy paw, both enveloped in the verdant embrace of their arboreal home. The koala, with its round face and endearing expression, tenderly touches another koala, showcasing a heartwarming display of affection. Their interaction is set against the vibrant green foliage, highlighting the tenderness of their connection. As they engage in this intimate gesture, their soft fur and the intricate details of the eucalyptus leaves create a visually captivating scene. Throughout, the two koalas remain in this loving embrace, emphasizing the emotional bond between them.]"
},
{
"from": "gpt",
"value": "Bad. The koala's head and paws in the video have generation issues."
}
] |
seed44_2449
|
videos/HRA_part1/2449.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning male pheasant, adorned with vibrant plumage of iridescent greens and blues, struts proudly across a lush meadow filled with tall grasses and wildflowers. The sunlight filters through the canopy of towering trees, casting dappled shadows that accentuate the bird's magnificent feathers. The pheasant pauses, its sharp eyes scanning the surroundings, before letting out a distinctive call that echoes through the peaceful countryside, asserting its presence in the rich, natural habitat that surrounds it.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1903
|
videos/HRA_part2/1903.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous woman wearing a thick, brown jacket and dark pants stands on a rocky ledge overlooking a vast, misty valley, preparing to leap from the cliffside. Nearby, a large brown bear, also gazing into the foggy abyss, seems unperturbed by her presence. As the scene progresses, the woman jumps off the cliff, her arms spread wide, embracing the thrill of freefall, with the bear watching intently from the edge of the precipice. Throughout, the dramatic landscape of rugged cliffs and the mysterious atmosphere of the mist-shrouded valley provide a breathtaking backdrop for this daring act.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2654
|
videos/HRA_part1/2654.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. In the video, the director's hand can be clearly seen gesturing, the actions are not continuous and there are abrupt changes; the actors and crew on set have movements that are not smooth and coordinated."
}
] |
seed46_2965
|
videos/HRA_part2/2965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male writer, dressed in a black turtleneck sweater and khaki pants, walks through a vast grassland with rolling hills under a clear blue sky. He pauses to observe a herd of deer grazing nearby, the animals' presence adding to the tranquility of the landscape. The writer continues his journey, a pen and notebook visible in his pocket, suggesting inspiration drawn from nature. As he moves further into the grassland, the distant silhouette of mountains can be seen, enhancing the sense of adventure and exploration. Throughout the scene, the focus remains on the writer's contemplative walk among the deer, with the vibrant green grass and expansive sky creating a serene and inspiring atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3127
|
videos/HRA_part2/3127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, distinguished by its large ears and gray skin, stands against a backdrop of geysers erupting in the distance, creating a misty atmosphere. The majestic animal uses its trunk to spray water onto itself, seemingly wiping or cleaning, as it enjoys a refreshing moment in the wild. This scene is set against the dramatic natural landscape, featuring geothermal activity, highlighting the unique interaction between wildlife and environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1047
|
videos/HRA_part2/1047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, wearing a white shirt, blue overalls, and a wide-brimmed hat, stands in a lush green field under a clear blue sky. He is in mid-throw, tossing hay bales with ease, his strong arms and focused expression showcasing his expertise. The hay bales are wrapped neatly in plastic, indicating a modern farming technique. The farmer's stance, with one leg forward for balance, adds dynamism to the scene, while the rolling hills and distant trees provide a picturesque rural backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_100
|
videos/HRA_part2/100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 capybara, the biggest living rodent, dashes across a vast, barren landscape under a twilight sky filled with cosmic dust swirling in a storm. The capybara, with its distinct features, including a wide face, small ears, and thick fur, runs with determination, its eyes fixed ahead. As it sprints, the cosmic dust storm overhead intensifies, particles of stardust illuminated by the fading sunlight, creating an ethereal atmosphere. Against this dramatic backdrop, the capybara continues its urgent journey, its powerful legs propelling it forward in a series of fluid leaps, leaving a trail of disturbed soil in its wake.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the capybara's wide face, small ears, and thick fur as mentioned in the caption."
}
] |
seed46_2419
|
videos/HRA_part2/2419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, clad in a brown leather jacket, blue shirt, and jeans, stands against a background of lush vegetation and distant mountains. His eyes are fixed on a graceful gazelle as it bounds across the terrain. The gazelle, exhibiting a display of speed and agility, leaps over shrubbery in the foreground, its movement captured in slow motion. The director, now holding a megaphone, directs the action, his gaze following the gazelle's path through the wilderness. Finally, the gazelle continues its run, moving away from the director and into the vast landscape, embodying freedom and beauty in motion.]"
},
{
"from": "gpt",
"value": "Normal. The antelope's running motion in the video is not smooth and coordinated."
}
] |
seed42_2696
|
videos/HRA_part0/2696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 North American beaver, known for its brown fur and flat, paddle-like tail, crawls along the muddy bank of a tranquil river. It pauses for a moment, gnawing on a piece of wood with its sharp incisors, before continuing its slow, deliberate crawl. Its small, rounded ears and half-closed eyes add to the relaxed atmosphere of the scene. The beaver's movement is unhurried, as it navigates the earthy terrain near the water's edge, occasionally pausing to survey its surroundings with a curious tilt of its head.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2942
|
videos/HRA_part1/2942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 strong, focused woman wearing a red helmet and climbing gear scales a towering rock face, the texture of the stone rough under her hands and feet. The camera captures her intense concentration, the strain in her muscles, and the determination in her eyes. Sunlight filters through wispy clouds, casting dramatic shadows on the cliffside as she ascends higher, leaving the green valley far below. The scene is framed by rugged terrain, emphasizing her solitary endeavor against the vast, natural landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2615
|
videos/HRA_part0/2615.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, plump hedgehog with distinctively sharp, brown spines traverses a lush, green garden, walking determinedly over mossy stones. It pauses briefly, its round body and curious face framed by the vibrant greenery. The hedgehog continues its journey, navigating the garden's textured path, with a wooden fence and hanging ivy leaves providing a natural, earthy backdrop. Throughout the walk, the hedgehog's spines glisten under the sunlight, highlighting its unique texture against the verdant setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2643
|
videos/HRA_part2/2643.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic, space-themed setting, a chef wearing a white uniform and a red bandana stands out against the metallic walls of what appears to be a bank interior. He walks purposefully, holding a large, clear bag filled with currency, suggesting a daring robbery. The chef's attire, which includes a white chef's jacket, black pants, and a red bandana, contrasts sharply with the cold, metallic environment. The scene is set in a space bank with curved, silver walls and a floor covered in scattered bills, as the chef strides away, his unique occupation and bold actions creating a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The chef's hands and feet in the video have generation issues."
}
] |
seed46_2644
|
videos/HRA_part2/2644.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with short, brown hair and a trimmed beard sits in a dimly lit room, wearing a casual gray t-shirt and black hoodie. He looks concerned as he holds his glasses in his right hand, resting on his knee. Suddenly, he coughs into his left hand, covering his mouth, with a worried expression on his face. The scene is set in an intimate space, capturing the man's discomfort and vulnerability during his unexpected coughing fit.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2291
|
videos/HRA_part2/2291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman, clad in an elaborate, flowing red dress, dances passionately under the moonlight in a desert landscape, with ancient ruins visible in the distance. A jackal, observing her from a safe distance, is intrigued by the captivating scene. The woman's movements are fluid and expressive, her dress swirling around her as she loses herself in the music that only she can hear. The jackal, sitting calmly, watches with fascination, its silhouette framed by the glow of the full moon, creating a mystical atmosphere in the vast, starlit desert.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video has a twisted body, head, feet, legs, and arms."
}
] |
seed42_2442
|
videos/HRA_part0/2442.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiger, drenched in sunlight, strides into a serene pond, its striped coat shimmering against the clear water. Gracefully, it begins to swim, powerful paws propelling it forward, with droplets scattering from its body. The water's surface reflects the lush greenery surrounding the pond, creating a tranquil atmosphere as the tiger continues to paddle through the calm waters, highlighting its unexpected aquatic prowess.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2965
|
videos/HRA_part0/2965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male writer, dressed in a black turtleneck sweater and khaki pants, walks through a vast grassland with rolling hills under a clear blue sky. He pauses to observe a herd of deer grazing nearby, the animals' presence adding to the tranquility of the landscape. The writer continues his journey, a pen and notebook visible in his pocket, suggesting inspiration drawn from nature. As he moves further into the grassland, the distant silhouette of mountains can be seen, enhancing the sense of adventure and exploration. Throughout the scene, the focus remains on the writer's contemplative walk among the deer, with the vibrant green grass and expansive sky creating a serene and inspiring atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_3072
|
videos/HRA_part0/3072.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a 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": "Normal. The character's face is distorted in the video."
}
] |
seed46_2110
|
videos/HRA_part2/2110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a gray jacket and khaki pants, sits cross-legged on a lush green meadow, gently caressing a docile water buffalo. The buffalo, with its large frame and distinctive horns, stands calmly beside a small body of water, accepting the student's affectionate touch. The student's serene facial expression and the peaceful surroundings, including trees and distant mountains, create a harmonious atmosphere. The scene is bathed in warm sunlight, casting a golden hue over the student and the buffalo, highlighting the tender connection between human and animal in a rural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1649
|
videos/HRA_part1/1649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bright, modern kitchen with white cabinets and countertops, two young children, a boy and a girl, both wearing red aprons over their clothes and chef hats, are attentively stirring ingredients in separate pans on a large, stainless steel gas stove. The boy, with short brown hair, focuses on his task with a serious expression, while the girl, with long blonde hair tied in pigtails, smiles as she stirs. The camera captures the sizzling sound of the food cooking, emphasizing the lively atmosphere. The room is filled with natural light from a window above the sink, illuminating the children as they cook, with a row of hanging pots and pans visible in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2855
|
videos/HRA_part0/2855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer clad in a blue shirt and khaki pants is seen walking alongside a chimpanzee wearing a tiny red cap, both navigating through a lush, verdant forest. The engineer, carrying a backpack and holding a machete, looks thoughtful as they traverse the underbrush. The chimp, balancing on two legs with a banana in its hand, occasionally glances up at the engineer with curiosity. They continue their journey together, the engineer leading the way with purpose, while the chimpanzee follows closely, the dense greenery of the forest enveloping them.]"
},
{
"from": "gpt",
"value": "Normal. No generation of machetes, bananas."
}
] |
seed44_1631
|
videos/HRA_part1/1631.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a vibrant yellow dress and a wide-brimmed sun hat, dances gracefully in the midst of a vast scrubland. The landscape is dotted with low-lying bushes and sparse trees, stretching far into the horizon under a clear blue sky. Her joyful movements contrast beautifully with the stillness of the arid environment, creating a captivating scene where education meets nature's tranquility. The teacher's animated gestures and warm smile convey a sense of freedom and connection to the rugged yet serene surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2327
|
videos/HRA_part1/2327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pufferfish, with its distinctive round shape and small size, swims gracefully in a vibrant coral reef environment. Its body, covered in tiny, pebble-like protrusions, is a mix of yellow and white with intricate black patterns. The fish inflates to nearly twice its original size, demonstrating its defense mechanism against potential predators lurking among the colorful corals and marine life surrounding it. The water is crystal clear, allowing every detail of the pufferfish's unique appearance and behavior to be captured in stunning high definition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1366
|
videos/HRA_part0/1366.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit consisting of a gray t-shirt and blue jeans, sits at a desk in a classroom filled with other students. The room is brightly lit by large windows, casting natural light onto the desks and walls adorned with educational posters. The student yawns widely, covering their mouth with a hand, indicating tiredness during the class. The scene captures a relatable moment of fatigue in an everyday learning environment.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and face appear deformed."
}
] |
seed46_1052
|
videos/HRA_part2/1052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid outdoor scene, three young children sprint across a vast, sunlit chaparral landscape, their movements captured in slow motion to emphasize their carefree joy. Dressed in a red shirt, blue shorts, and black shoes, one child leads the pack, arms outstretched like wings. Another child, wearing a yellow top, green shorts, and brown sandals, follows closely behind, laughing gleefully. Trailing just behind, a third child in a purple dress and pink sneakers completes the trio, their faces alight with excitement as they race beneath the clear blue sky. The chaparral vegetation, with its rugged shrubs and distant mountain backdrop, provides a natural, textured setting for their energetic play.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1440
|
videos/HRA_part1/1440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic individual named Jay, donning a dark blue cap, aviator sunglasses, and a gray shirt, is captured in high-definition. Initially, he is seen against a backdrop of lush greenery, standing tall with his hands on his hips, exuding confidence. The scene then focuses on his face, highlighting his stylish appearance and a slight smile. Next, Jay is shown from behind, gazing out at a stunning mountainous landscape, conveying a sense of adventure. Finally, he raises his right arm, pointing at something exciting in the distance, his silhouette framed by the natural beauty around him, encapsulating the essence of an outdoor enthusiast.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1367
|
videos/HRA_part1/1367.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a dark jacket, jeans, and a baseball cap, runs energetically across a futuristic space movie set, filled with intricate machinery and high-tech equipment. The set features large, circular structures and metallic surfaces, giving it a distinctly sci-fi aesthetic. The director's movement conveys a sense of urgency and purpose, as he navigates through the complex environment, surrounded by the vast, industrial-like backdrop of the space station set.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1973
|
videos/HRA_part2/1973.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric artist with a shaved head, donning a mustard yellow turtleneck sweater and khaki pants, stands on a dark green chair, changing a light bulb in his dimly lit studio. The space is filled with artistic clutter, including an easel with a half-finished painting, a large wooden table covered in art supplies, and various sculptures scattered throughout. The artist, with a hint of frustration, reaches up to screw in the new light bulb, casting dramatic shadows across his face and the surrounding objects. The scene is captured in high definition, allowing every detail of the artist's struggle and the eclectic studio to come to life.]"
},
{
"from": "gpt",
"value": "Bad. The artist's actions of changing the light bulb in the video are discontinuous and abrupt."
}
] |
seed44_2566
|
videos/HRA_part1/2566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, large clam is showcased on a white plate, its intricate shell patterns visible, set against a rustic wooden table. The clam's interior is slightly ajar, revealing its succulent meat within the half-shell. Surrounding the plate are various utensils, including a fork, knife, and spoon, laid out on the worn wood surface. In the background, a blurred view of a coastal landscape hints at the seafood's fresh origin, with seagulls flying overhead and the distant horizon merging sky and sea. The clam itself is illuminated by natural light, highlighting its natural beauty and the anticipation of a delicious meal.]"
},
{
"from": "gpt",
"value": "Normal. There is no action in the video."
}
] |
seed44_1700
|
videos/HRA_part1/1700.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a close-up view captures a stunning array of coral formations, teeming with life and color. Against a backdrop of clear blue water, the corals display a rich palette of oranges, pinks, purples, and greens. Delicate sea fans wave gently in the current, while intricate branching corals resemble undersea forests. Hard corals form complex structures, providing homes for countless marine creatures. Soft corals sway gracefully, their feathery polyps extending to catch passing nutrients. The scene is a testament to the beauty and biodiversity of coral reefs, a precious ecosystem thriving beneath the waves.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2932
|
videos/HRA_part1/2932.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rat is seen leaping through dense heathland, its body mid-air as it propels itself forward over the foliage. The rodent's movement is captured in detail, showcasing its agility and strength as it navigates the underbrush. The surroundings consist of abundant greenery, with the rat's jump highlighting its natural habitat among the heaths. The focus remains on the rat throughout, emphasizing its action-packed leap within the lush environment.]"
},
{
"from": "gpt",
"value": "Bad. The mouse's movement in the video is very unsmooth, and the actions are uncoordinated."
}
] |
seed44_1315
|
videos/HRA_part1/1315.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a yellow t-shirt and blue jeans, is playfully chasing a juvenile rhinoceros across a vast, grassy savannah under a bright blue sky. The action is captured from multiple angles, first showing the student's enthusiastic pursuit, followed by a shot of the rhino's surprised reaction as it turns its head back. Next, the scene focuses on the student's determined facial expression, highlighting the joy and energy of the chase. Finally, a side view captures the dynamic duo running in unison, the student's arms waving wildly and the rhinoceros' ears flapping, both enjoying the spontaneous adventure in the expansive landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1710
|
videos/HRA_part1/1710.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, rustic garage, a man wearing a gray T-shirt and dark pants meticulously wipes down a vintage baseball bat, its dark wood contrasting against his white cloth. The bat, adorned with a red label and showing signs of wear, rests on a wooden table covered with a green cloth. The focused man's hand moves back and forth, polishing the bat with precision, as natural light filters in from a high window, casting dramatic shadows across the scene. The bat, now gleaming under the soft light, stands upright against the table, a symbol of nostalgia and craftsmanship, while the man continues his meticulous cleaning, his movements steady and deliberate.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_253
|
videos/HRA_part1/253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 peacock, resplendent in its vivid blue and green plumage, struts regally across a lush, verdant garden, the sunlight dappling its feathers in a mesmerizing play of light and shadow. Its proud head, adorned with a striking crest, swivels gracefully as it surveys its domain. Suddenly, the peacock spreads its spectacular tail, revealing an eye-popping display of iridescent ocelli that seem to shimmer with an otherworldly glow. The air is filled with the rich, earthy scents of the foliage surrounding the bird, adding depth to this enchanting scene.]"
},
{
"from": "gpt",
"value": "Normal. The peacock's feather display in the video is basically normal, but there is slight movement inconsistency."
}
] |
seed46_2687
|
videos/HRA_part2/2687.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": "Bad. The female engineer's limbs are deformed in the video, the body proportions are incorrect, and the face is blurry."
}
] |
seed42_2970
|
videos/HRA_part0/2970.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a young female cashier, wearing a red apron over her gray sweater and black jeans, stands at a register, looking surprised. Behind her, a full-sized moose runs across the store, its antlers adorned with Christmas lights, adding a surreal touch to the supermarket setting. The moose dashes between the aisles filled with groceries, creating a chaotic yet amusing atmosphere. The cashier watches the unexpected visitor with a mix of shock and amusement, as customers look on in disbelief, capturing the bizarre event on their smartphones. The moose's presence disrupts the mundane routine of the store, turning it into an unforgettable experience for everyone present.]"
},
{
"from": "gpt",
"value": "Bad. Failed to generate a young female cashier wearing a gray sweater, black jeans, and a red apron."
}
] |
seed44_206
|
videos/HRA_part1/206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European badger, distinguished by its black and white striped face and brown fur, scurries through a network of intricately dug tunnels in a dimly lit sett. The animal, with its stocky build and sharp claws, moves swiftly and purposefully, navigating the narrow passages with ease. As it runs, the texture of the tunnel walls, composed of earth and roots, becomes apparent, providing a natural contrast to the badger's movement. Throughout the sequence, the focus remains on the badger's journey within the tunnel system, emphasizing its agility and familiarity with its subterranean habitat.]"
},
{
"from": "gpt",
"value": "Normal. The European badger walks basically normally in the video, but there is slight movement disharmony."
}
] |
seed44_1612
|
videos/HRA_part1/1612.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a stethoscope around his neck and a colorful tie, is laughing heartily with his head thrown back, his eyes closed, and his mouth wide open, showing his amusement in a candid moment. The laughter is contagious, spreading joy and positivity in a medical setting, with the doctor's facial features animated and expressive, capturing the essence of happiness and camaraderie in a professional environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1399
|
videos/HRA_part1/1399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating fusion of elements, a majestic black panther, its body outlined in vibrant neon green, is depicted leaping across a cosmic landscape. The backdrop features a stunning galactic nebula, its swirling colors of pink, purple, and blue creating an ethereal atmosphere. As the panther moves gracefully, it seems to dance among the stars, its fluid movements echoing the celestial patterns around it. The nebula's gaseous tendrils appear to reach out, almost as if they too are joining in the cosmic dance, forming a harmonious scene where the boundaries between the animal kingdom and the universe blur.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1736
|
videos/HRA_part0/1736.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 strong woman dressed in black pants, a black sports bra, and protective gear, including shin guards and arm pads, is seen in a well-lit gym. She delivers a powerful roundhouse kick, her body exhibiting grace and power, with boxing gloves on her hands and her hair tied back in a ponytail. Moments later, she throws a fierce punch, her face a mask of determination, showcasing her martial arts skills in a space adorned with punching bags and boxing posters. Finally, she executes a high kick, her form impeccable, against a backdrop of gym equipment and motivational wall art, encapsulating her strength and discipline.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate shin guards and arm pads."
}
] |
seed42_2412
|
videos/HRA_part0/2412.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray hoodie, black pants, and black shoes, jumps dynamically in front of a large-scale painting that depicts a swirling, cosmic-like antimatter containment facility. The artwork showcases vibrant colors and intricate details, capturing the essence of a high-energy, science fiction-inspired scene. The artist's pose, mid-air with arms extended, adds a sense of movement and creativity to the composition. The room is illuminated by a soft, ambient light, highlighting the artist's silhouette and the captivating artwork behind them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly 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": "Bad. Both the character and the black panther are deformed, and the facial expressions have not been generated."
}
] |
seed44_1130
|
videos/HRA_part1/1130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 director, wearing a gray suit and a white shirt, stands in a futuristic, high-tech room filled with screens displaying charts and graphs related to interplanetary trade routes. He gently caresses a large, interactive holographic map, which shows the intricate web of trade connections between various celestial bodies, highlighting the complex network of commerce spanning the solar system. The room is bathed in soft, ambient lighting, emphasizing the director's pensive and focused demeanor as he contemplates the vast opportunities and challenges presented by this expansive trade network.]"
},
{
"from": "gpt",
"value": "Normal. The director's hand in the video has issues."
}
] |
seed44_254
|
videos/HRA_part1/254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction crane dominates the skyline, its yellow and black body towering over a bustling cityscape at dusk. The crane's long arm stretches across the frame, adorned with industrial machinery and cables, as it stands on a partially constructed building amidst other tall structures. Workers in safety gear can be seen moving about the site, dwarfed by the massive crane, which looms against the orange and purple hues of the setting sun, casting long shadows over the urban landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1856
|
videos/HRA_part0/1856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, identifiable by her backpack, dances whimsically across the screen, transitioning from a campus setting to an unexpected otter enclosure at a zoo. She's wearing a yellow top, denim shorts, and sneakers, embodying youthful energy. Suddenly, the scene shifts to a somber cemetery, where she continues to dance among the tombstones, now adorned in a black dress and boots, carrying a red umbrella. The juxtaposition of lively dancing in these varied locations, from educational grounds to wildlife exhibits to a place of remembrance, creates a surreal and captivating narrative.]"
},
{
"from": "gpt",
"value": "Bad. No campus scene was generated."
}
] |
seed42_2539
|
videos/HRA_part0/2539.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, a young female cashier, dressed in a black apron over a white blouse, serves customers with a warm smile at an outdoor market stall. The background is filled with the vibrant energy of city life, complete with honking cars, pedestrians, and street vendors. Suddenly, the focus changes to a public pool where a group of diverse individuals, including a man in swimming trunks and a woman in a floral-print swimsuit, splash and play in the water. The atmosphere is lively and joyful, with the sounds of laughter and splashing filling the air, offering a stark contrast to the busy urban environment previously depicted.]"
},
{
"from": "gpt",
"value": "Normal. The men and women in the pool appear deformed, with distorted faces."
}
] |
seed44_3000
|
videos/HRA_part1/3000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a neatly trimmed beard, sits pensively on a vintage brown leather couch, wearing a blue checked shirt, dark pants, and brown shoes. Suddenly, he holds his chest and coughs intensely, his eyes squeezed shut, indicating discomfort. The scene is set in a warmly lit room with wooden walls, showcasing a rustic environment. As the coughing fit subsides, he looks concerned, placing his hand back on his chest, suggesting a moment of reflection on his health, all while maintaining the same attire and setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1387
|
videos/HRA_part2/1387.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a crisp white shirt and black vest, finds himself dancing amidst towering trees in a dense forest. As he gracefully twirls, a majestic bison watches from the shadows, its powerful presence adding a touch of wildness to the surreal encounter. The forest, filled with lush greenery and dappled sunlight, provides a natural stage for this unexpected dance performance, where the lines between human and nature blur in a harmonious display.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's spinning movements are not continuous, there is a sudden change."
}
] |
seed42_1186
|
videos/HRA_part0/1186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a weathered wooden fence post, its distinctive black-and-white plumage gleaming under the soft sunlight. Against a backdrop of lush green foliage and clear blue skies, the bird's eyes sparkle with curiosity. It tilts its head to the side, seemingly observing its surroundings with interest. The vibrant colors of nature serve as a striking contrast to the magpie's striking feathers, highlighting its unique beauty in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The bird's beak in the video is generated too high on the face, and the claws are not fully generated."
}
] |
seed42_2251
|
videos/HRA_part0/2251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 modern office setting, a professional lawyer, dressed in a navy suit, white shirt, and patterned tie, sits at a large wooden desk adorned with a nameplate, laptop, and various legal documents. Against a backdrop of tall windows revealing a sunny city skyline, the lawyer attentively sketches an outline of a legal strategy on a whiteboard, using a green marker, while occasionally glancing at the papers scattered on the desk. The scene captures the lawyer's analytical skills and creative approach to solving legal challenges, blending traditional law practice with innovative problem-solving techniques.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_211
|
videos/HRA_part0/211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene set within the confines of an art gallery, a firefighter clad in full gear and a helmet, carrying an axe, sprints down a wide hallway lined with large paintings and modern art sculptures. The overhead lights cast shadows, adding to the intensity of the moment. Behind him, the glow of an encroaching fire illuminates the space, its orange and red hues contrasting starkly with the artworks. Amidst the chaos, the firefighter's purposeful stride conveys determination and urgency, his mission to save lives and preserve priceless art pieces from the raging inferno.]"
},
{
"from": "gpt",
"value": "Bad. The firefighters' rapid movements in the video are not very smooth and appear uncoordinated."
}
] |
seed44_2642
|
videos/HRA_part1/2642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small hamster, with its distinctively furry cheeks and nose, energetically runs inside a clear plastic exercise ball. It scampers across a room filled with everyday objects like furniture and potted plants, providing a unique perspective on a typical living space. The hamster's movement is fluid and rapid, highlighting its determination and playful nature as it explores its surroundings within the safety of the transparent sphere.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's movements in the video are not smooth."
}
] |
seed46_1379
|
videos/HRA_part2/1379.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned chef, donning a traditional white chef's uniform with a checkered bandana, performs a dynamic pizza toss in a bustling pizzeria kitchen. The dough stretches gracefully as it rotates in mid-air, illuminated by the warm glow of overhead lights. The chef's confident expression and practiced movements highlight his expertise, while the lively atmosphere of the kitchen, filled with the sounds of sizzling pans and cheerful chatter, adds to the vibrant scene. In the background, a row of wood-fired ovens and a team of chefs busily preparing various dishes complete the authentic pizzeria setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted, and the arm is twisted."
}
] |
seed42_2003
|
videos/HRA_part0/2003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man wearing a casual jacket and jeans walks through a futuristic cityscape, where the architecture blends elements from different eras, creating a sense of time distortion. He moves with purpose, passing by a mix of old-world cobblestone streets and modern glass skyscrapers. The sky above is tinted with a slight orange hue, suggesting a world where the laws of physics have been altered. As he continues his journey, the background subtly shifts, revealing glimpses of historical landmarks juxtaposed with advanced technology, alluding to the concept of time dilation affecting his walk.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2745
|
videos/HRA_part1/2745.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform with a black necktie and a tall toque blanche hat, stands on a small wooden stool. He is in the process of changing a light bulb in a restaurant kitchen, surrounded by stainless steel appliances and shelves stocked with cooking utensils. The kitchen is brightly lit, except for the area where the burnt-out bulb needs replacement. The chef, with a slight smile, carefully unscrews the old light bulb, demonstrating a lighthearted moment in his daily routine amidst the professional culinary environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1161
|
videos/HRA_part1/1161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 silver spacesuit with an American flag patch, is seen crawling across the rocky, red Martian landscape, examining the terrain closely. The scene is set under a pinkish-brown sky, with distant mountains visible on the horizon. The officer's spacesuit features NASA logos and a utility belt, and they carry a high-tech scanner, highlighting the unusual combination of law enforcement and space exploration. The camera captures this unique moment in crisp, high-definition detail, emphasizing the contrast between the traditional role of a police officer and the extraordinary setting of a distant planet.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2920
|
videos/HRA_part1/2920.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, 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 is missing a wrench."
}
] |
seed42_1561
|
videos/HRA_part0/1561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged astronaut, clad in a sleek silver spacesuit and helmet, leaps into the air against the backdrop of a distant galaxy, stars shimmering in the vast cosmic landscape. The astronaut's pose conveys a sense of weightlessness and freedom as he appears to float in zero gravity, with the vibrant colors of far-off celestial bodies providing a dramatic contrast to his metallic attire. The scene captures the exhilaration and mystery of interstellar exploration, with the astronaut seeming to defy the laws of physics in the boundless expanse of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_308
|
videos/HRA_part1/308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bobcat, with distinctive tufted ears and a rufous-colored coat, leaps from a rocky outcropping, its body arched and legs extended, showcasing its agility and power. The background features lush vegetation and trees, highlighting the wild, natural habitat of this impressive feline. The scene is captured in high definition, allowing every detail of the bobcat's muscular form and the surrounding environment to be clearly visible during the jump.]"
},
{
"from": "gpt",
"value": "Bad. The sable's head is twisted, claws are twisted, and legs are twisted."
}
] |
seed46_1332
|
videos/HRA_part2/1332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense temperate rainforest, a wet and lush environment with moss-covered trees, a large brown capybara crawls slowly through the undergrowth. It moves deliberately, its round body and small legs barely visible among the ferns and fallen leaves. The air is thick with moisture, and the sounds of dripping water and distant wildlife fill the atmosphere. The capybara's eyes are alert, scanning its surroundings as it navigates the complex terrain of the rainforest floor.]"
},
{
"from": "gpt",
"value": "Normal. The capybara in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed42_1695
|
videos/HRA_part0/1695.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged musician, wearing a black leather jacket, black jeans, and black boots, checks a smoke detector in a modern, sparsely decorated living room. He stands on a white chair, his guitar hanging from a strap around his neck, as he inspects the device with a focused expression. The room features a large window allowing ample natural light, a white couch, and a white coffee table, creating a contrast against the musician's dark attire. The scene captures a moment of domestic responsibility in the life of an artist.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, legs, and guitar are distorted in the video."
}
] |
seed44_2303
|
videos/HRA_part1/2303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man sits at a wooden desk in a dimly lit room, wearing a white shirt with rolled-up sleeves and a black blazer, intently drawing on a large sketchbook with a mechanical pencil. The focus is on his hands, which hold the pencil and manipulate its grip, while the rest of his body remains still. The background shows the texture of the wooden desk, and the man's right hand rests on the edge of the sketchbook, as he leans forward with his left elbow on the table, cradling his chin with his hand. The scene conveys a sense of concentration and dedication to the craft of drawing.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_2683
|
videos/HRA_part2/2683.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman sits in a dimly lit room, her face softly illuminated by a single light source. She is wearing a simple white shirt, her brown hair falling gently over her shoulders. The camera focuses on her chest, rising and falling slowly as she takes deep, deliberate breaths. Each inhale is visible, drawing attention to the tranquility of the moment. Her eyes are closed, her lips slightly parted, as she finds peace in the rhythm of her breathing. The quiet atmosphere is punctuated only by the sound of her breath, creating a serene and intimate portrait of mindfulness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2977
|
videos/HRA_part0/2977.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 seasoned worker, donning a brown jacket and blue jeans, leads a strong, brown horse by a red halter, walking together in unison on a dirt path. The pair moves at a steady pace, the man guiding the horse with care and respect. The horse, with its muscular build and glossy coat, follows obediently, the two sharing a bond reflective of their partnership. The setting is a rural landscape, with distant hills and trees providing a serene backdrop to their peaceful walk.]"
},
{
"from": "gpt",
"value": "Normal. The workers and the horse walking in the video are basically normal, but there is slight movement disharmony."
}
] |
seed44_2607
|
videos/HRA_part1/2607.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint village setting, 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": "Bad. The cashier's dance moves in the video are not continuous, there are abrupt changes, and the cashier's hand suddenly disappears or reappears in the middle frames."
}
] |
seed46_251
|
videos/HRA_part2/251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer wearing a spacesuit decorated with patches and emblems swims effortlessly in zero gravity within a space station habitat. The habitat, illuminated by soft, ambient lighting, features curved walls and large windows offering breathtaking views of the cosmos. A pet lizard, also weightless, floats nearby, its scales reflecting the light in iridescent patterns. The engineer gently propels themselves through the water-filled enclosure, designed to simulate Earth's aquatic environments, while the lizard seems to hover curiously beside them, both adapted to life in the microgravity of the space station.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1063
|
videos/HRA_part0/1063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a bobcat, recognizable by its short tail and tufted ears, dashes across the frame, passing by an automated checkout machine in a minimally designed convenience store. The animal's panicked sprint is juxtaposed against the sterile environment of the store, where the self-checkout machine stands idle. The bobcat's unexpected intrusion adds an element of chaos to the otherwise mundane setting, creating a surreal moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Normal. Multiple legs appear, and the short-tailed cat is repeatedly shown."
}
] |
seed42_2567
|
videos/HRA_part0/2567.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two zebras engage in a tender moment, their striped coats shimmering against the golden grass. One zebra gently nuzzles the other's neck, their muzzles touching affectionately, showcasing a rare display of intimacy between these wild equines. The landscape is dotted with scattered acacia trees and distant mountains, providing a serene backdrop to this heartwarming scene. As they caress each other, the bond between them is evident, a beautiful testament to the emotional connections found in the animal kingdom.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_205
|
videos/HRA_part0/205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 renowned actor, wearing a brown costume resembling a moose, dances gleefully in a large, empty studio with high ceilings and exposed pipes. The overhead lights cast a warm glow on the wooden floor, highlighting the actor's animated expressions and exaggerated movements. The studio walls are adorned with abstract paintings and vintage movie posters, adding a whimsical touch to the scene. As the actor continues to dance, their enthusiasm is contagious, bringing a sense of joy and playfulness to the space.]"
},
{
"from": "gpt",
"value": "Bad. The actor's walking in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_3207
|
videos/HRA_part1/3207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mongoose, recognized by its sandy brown fur, black-tipped tail, and alert demeanor, runs swiftly across a dry, grassy terrain under a clear blue sky. It bounds gracefully over small tufts of grass, its body elongating and contracting with each leap, showcasing its agility and speed. Its eyes are focused ahead, ears perked, and nose twitching, indicating high alertness as it navigates the open space. The mongoose's movement is fluid and purposeful, its feet barely touching the ground as it darts forward, leaving a slight cloud of dust in its wake.]"
},
{
"from": "gpt",
"value": "Bad. The meerkat can be seen running on the grass in the video, but the movements are not continuous and smooth, showing a lack of coordination."
}
] |
seed46_2736
|
videos/HRA_part2/2736.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit cave, a small brown bat, with leathery wings folded against its body, walks along the rocky ground with deliberate steps. Its face, framed by long, curved ears, is keenly observant. The bat pauses momentarily, revealing its tiny feet and claws as it navigates the stone surface. The focus then shifts to the bat's head, highlighting its intricate facial features and alert eyes. Finally, the bat is seen walking away, its silhouette set against the textured cave wall, creating a captivating scene of a bat navigating its environment on foot.]"
},
{
"from": "gpt",
"value": "Normal. The bat's claws and wings in the video are deformed."
}
] |
seed44_281
|
videos/HRA_part1/281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 a yellow firefighting suit, interacts with a hyena at a unique wildlife sanctuary. The firefighter, helmet in hand, stands beside a swimming pool, while the hyena, sporting a brownish coat and black spots, looks on curiously. The two share a moment of connection, with the firefighter's reassuring presence and the hyena's inquisitive gaze, all set against the backdrop of a tranquil, water-filled pool. The scene highlights an unexpected bond between a protector of human safety and a wild animal, both seemingly at ease in each other's company.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2230
|
videos/HRA_part2/2230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, lush green forest setting, a pair of beavers are seen intimately caressing each other, their brown fur glistening with moisture from the nearby river. The male beaver gently touches the female's face with his forepaw, a tender gesture of affection. They are surrounded by tall trees and vegetation, providing a natural and peaceful environment for their interaction. The female beaver responds with a soft look, her whiskers moving slightly as she nuzzles closer to him. This heartwarming scene captures the emotional bond between these two creatures, highlighting the beauty of wildlife relationships.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed42_3149
|
videos/HRA_part0/3149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 animated scene, a small, adventurous mouse dons a director's cap and carries a clapperboard, energetically guiding the action within a vibrant space casino. The setting is filled with neon lights, futuristic slot machines, and alien creatures gambling. Our rodent director, wearing a tiny suit and tie, races through the bustling casino floor, dodging patrons and games of chance, all while maintaining control over the film production taking place in this extraordinary intergalactic entertainment hub.]"
},
{
"from": "gpt",
"value": "Normal. The mouse's face is distorted, legs are twisted, and paws are deformed."
}
] |
seed44_1168
|
videos/HRA_part1/1168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, verdant park, a majestic leopard, its golden eyes alert, crouches near the edge of a pristine swimming pool, surrounded by vibrant greenery and towering palm trees. The big cat, with its distinctive rosette patterns on a tawny coat, gazes intently at the clear water, contemplating a playful leap. Moments later, it leaps gracefully into the pool, its powerful body slicing through the water in a fluid motion. Emerging from the pool, the leopard shakes off droplets, revealing its muscular physique, as it strides confidently across the park, leaving behind a trail of shimmering water on the sun-drenched pavement.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3059
|
videos/HRA_part1/3059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, dressed in a yellow high-visibility jacket and blue jeans, stands near a buffalo swimming in a serene, placid lake, surrounded by lush greenery. The buffalo, with its massive frame and shaggy coat, gracefully paddles through the clear water, creating ripples that extend outward. In the background, a wooden pier extends into the lake, and tall trees line the shore, providing shade and a sense of serenity. The janitor looks on, perhaps during a break from his duties, observing the buffalo in its natural habitat, a harmonious blend of nature and human presence.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's hand is deformed, and there is an issue with the water buffalo's head generation in the video."
}
] |
seed46_2655
|
videos/HRA_part2/2655.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, wearing a casual button-down shirt and khaki pants, is seen sketching mall blueprints on a large, clear desk, surrounded by architectural models and technical drawings. Moments later, the scene shifts to a vibrant mall interior, where the same engineer is seen interacting with a diverse group of shoppers, pointing out design features and technological advancements. Finally, the video captures the engineer enjoying a well-deserved break by swimming leisurely in a modern, glass-enclosed pool, located on the mall's rooftop, showcasing a harmonious blend of work and relaxation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1222
|
videos/HRA_part2/1222.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone kangaroo is seen in a vast, arid landscape under a clear blue sky, performing a unique behavior - wiping its face with its paw in a human-like manner. The kangaroo, with its reddish-brown fur, stands on its hind legs, balancing its weight on its thick, muscular tail. As it wipes its face, the action is captured in slow motion, highlighting the texture of its fur and the intensity in its eyes. The gesture is repeated several times, each movement deliberate and almost meditative, offering a rare glimpse into the animal's world. The scene is set against the backdrop of the Australian outback, with distant mountains and sparse vegetation, emphasizing the kangaroo's natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's face is distorted, and its legs are twisted."
}
] |
seed44_2692
|
videos/HRA_part1/2692.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast warehouse district under a cloudy sky, a worker clad in a yellow vest and hard hat operates a compact yellow Bobcat excavator. The machine crawls carefully across the concrete floor, maneuvering through the tight spaces between towering stacks of pallets filled with cardboard boxes. The excavator's bucket is raised, ready to perform its task amidst the industrial environment, while the worker remains focused, guiding the machinery with precision.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_1970
|
videos/HRA_part2/1970.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, takes a break from his laborious tasks to sketch on a piece of paper, seated on a wooden beam at a construction site bustling with activity. Amidst the backdrop of unfinished buildings and heavy machinery, he focuses intently on his art, revealing a moment of unexpected creativity in the midst of a gritty urban environment. The scene captures his dedication to both his profession and his passion, offering a glimpse into the dual nature of his daily life.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_1939
|
videos/HRA_part2/1939.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 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 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": "Bad. The jumping actions of the student and the kangaroo in the video are not smooth and continuous, with abrupt changes in the limbs of both the student and the kangaroo in the middle frames."
}
] |
seed46_1778
|
videos/HRA_part2/1778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, casually dressed in a dark gray t-shirt and black sweatpants, attentively unloads a dishwasher in a modern kitchen. The space features sleek white cabinets, a stainless steel refrigerator, and a large window allowing natural light to illuminate the room. He carefully places dishes into cupboards, revealing a methodical approach to the task. With a half-smile and relaxed posture, he demonstrates an unexpected domestic side, contrasting his typical on-screen persona. Throughout the scene, the kitchen remains orderly and clean, emphasizing the mundanity of the chore juxtaposed with his celebrity status.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, and the hands are deformed."
}
] |
seed46_2946
|
videos/HRA_part2/2946.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning close-up of a halibut fish, flat and wide, with a mottled brown and white skin pattern, is showcased against a dark background. The fish has a large, open mouth with small teeth visible, and its eyes are set on the left side of its head, gazing intently. The texture of the halibut's skin is detailed, showing rough spots and a rugged surface, while the background remains uniformly dark, highlighting the unique features of this deep-sea dweller.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2107
|
videos/HRA_part0/2107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a casual gray t-shirt and blue jeans, is seen unloading a dishwasher in a modern kitchen with sleek, stainless steel appliances. The room is well-lit, casting a warm glow over the beige walls and brown cabinets. The student, sporting a short haircut and glasses, carefully removes dishes from the lower rack, placing them into a cabinet just above the dishwasher. With each item placed, the student's movements are deliberate and efficient, showing a routine familiarity with the task. The space is tidy and minimalistic, with a small dining table in the corner and a window letting in natural light, creating a homely atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_119
|
videos/HRA_part2/119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, two children, a boy and a girl, are seen gently caressing a juvenile antelope in a lush, green meadow. The boy, wearing a blue shirt and shorts, leans over to pet the animal with a tender smile, while the girl, dressed in a yellow dress, watches adoringly, her hands clasped together. Moments later, the girl takes her turn, stroking the antelope's back as it stands calmly, accepting the affection. The boy looks on with a joyful expression, his right hand raised in excitement. The idyllic setting, complete with verdant grass and blue skies, adds to the peaceful and endearing nature of the interaction between the children and the young antelope.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth. The deer's movements are not smooth."
}
] |
seed46_2367
|
videos/HRA_part2/2367.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, known for his mastery of the banjo, takes a break from his art to sweep his wooden porch on a sunny day. Dressed casually in a gray shirt and khaki pants, he methodically sweeps with a broom made of natural fibers, revealing the clean, weathered wood beneath. The porch, adorned with potted plants and a rustic rocking chair, overlooks a lush garden filled with vibrant flowers and greenery. In the background, a vintage acoustic guitar leans against the wall, hinting at the musician's passion for music, while the peaceful, suburban neighborhood provides a serene setting for this ordinary yet captivating task.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_2783
|
videos/HRA_part0/2783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 girl sits at a wooden desk in a classroom, diligently hemming a pair of khaki pants using a sewing machine, her focus unwavering. She wears a yellow blouse, and her hair is tied back in a ponytail, highlighting her concentration. On the desk, a tape measure, scissors, pins, and a spool of thread are neatly arranged. Beside her, a bulletin board displays various fabric swatches and design sketches, adding context to her task. The room is illuminated by natural light from a window, casting a warm glow over her industrious endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers in the video are deformed."
}
] |
seed44_1271
|
videos/HRA_part1/1271.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a yellow high-visibility vest and dark pants, diligently wipes a glass window with a cloth in a bustling mall food court. Amidst the vibrant setting, complete with a McDonald's restaurant and various retail stores in the background, he pauses to assess his work. With determination, he continues wiping the glass surface, ensuring it remains clean and clear. Throughout, the dynamic environment of the mall is evident, from the diverse crowd to the commercial signage, yet the focus remains on the janitor's meticulous efforts.]"
},
{
"from": "gpt",
"value": "Bad. The human hand is deformed."
}
] |
seed42_3005
|
videos/HRA_part0/3005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a gray suit, red tie, and glasses, is kneeling in a whimsical scene beside a meerkat standing upright. The lawyer gently wipes the meerkat's face with a white cloth, both figures set against a vibrant green grassy background under a clear blue sky, creating an unusual yet captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the lawyer's action of reaching out to wipe, which is not very continuous and smooth, with an inconsistency where a white cloth suddenly appears in the middle frame."
}
] |
seed46_1911
|
videos/HRA_part2/1911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, presumably a writer, sits cross-legged on a lush, grassy surface, wearing a blue denim jacket and dark pants. He gently caresses a small, brown bear, who reciprocates with a loving nuzzle. The bear, adorned with a red bow tie, displays affection towards the man, who smiles warmly. Both are surrounded by a serene, verdant landscape, with the man's writing materials, including a notebook and pen, visible nearby. The scene conveys a tender moment between the writer and the bear, set against a peaceful outdoor backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2729
|
videos/HRA_part1/2729.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful woman with curly brown hair and glasses laughs heartily, holding a green apple in her right hand. Dressed in a mustard yellow turtleneck sweater, she sits in front of a rustic wooden wall, her joyful demeanor brightening the cozy setting. Her laughter is contagious, spreading warmth and happiness in the intimate space, where natural light filters in from above, illuminating her face and emphasizing her genuine delight.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers in the video are generated basically correctly, but there is a slight deformity."
}
] |
seed46_25
|
videos/HRA_part2/25.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 friendly capybara, adorned with a miniature nurse's hat and a stethoscope around its neck, crawls across a colorful, childlike set filled with oversized medical-themed toys. The capybara moves deliberately, as if performing a check-up on a giant teddy bear patient lying on a playful examination table, surrounded by an array of oversized bandages, cotton balls, and a smiling face thermometer, creating a heartwarming and imaginative playtime scenario.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's legs are deformed when walking."
}
] |
seed44_2837
|
videos/HRA_part1/2837.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red-tailed hawk soars through a clear blue sky, its powerful wings stretched wide, casting a shadow on the rugged, rocky terrain below. It effortlessly glides over a dense forest, the sunlight glinting off its russet and white plumage, with a backdrop of lush green trees. The hawk then focuses intently, spotting prey from above, its piercing eyes and curved beak displaying its predatory nature. It finishes by perching regally atop a barren tree branch, surveying its domain with a fierce gaze, the wind gently ruffling its feathers.]"
},
{
"from": "gpt",
"value": "Normal. The red-tailed hawk's flying movements in the video are slightly not smooth."
}
] |
seed46_2210
|
videos/HRA_part2/2210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, adorned in a spacesuit and helmet, stands on the lunar surface, illuminated by the Earth's glow, holding a leash attached to a lion. The lion, also wearing a miniature spacesuit and helmet, jumps playfully in the low gravity environment. Both figures cast long shadows against the moon's dusty terrain, with the Earth shining brightly in the dark, star-studded sky. This surreal scene combines elements of space exploration, wildlife, and human ingenuity in a single captivating frame.]"
},
{
"from": "gpt",
"value": "Bad. The arms of the person in the video are twisted, the hands are twisted, the lion's face is distorted, and the legs are twisted."
}
] |
seed44_2672
|
videos/HRA_part1/2672.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-groomed doctor, complete with a stethoscope around his neck and wearing a white lab coat over a button-down shirt and slacks, is seen cleaning a large aquarium. The doctor, who has a neatly trimmed beard, carefully cleans the glass of the fish tank with a squeegee, revealing the clear water and colorful fish inside. The room is modern and clean, with white walls and a tiled floor, and there's a large window allowing natural light to illuminate the space. The fish tank, which houses various species of tropical fish, is the centerpiece of the room, and the doctor's meticulous care for it highlights his attention to detail and compassion for living creatures.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hand generation in the video has problems, and the wiper is malformed."
}
] |
seed44_2985
|
videos/HRA_part1/2985.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a shaved head and wearing a gray shirt is seen organizing items on metal shelves against a gray backdrop. Initially, he is placing objects with care, showcasing his meticulous nature. Moments later, he is shown adjusting the arrangement of items, revealing his attention to detail. Then, he is seen moving an object to another shelf, indicating his methodical approach to organization. Finally, he looks satisfied with his efforts, his posture and facial expression reflecting a sense of accomplishment, all within the minimalist setting of a gray room with metal shelving units.]"
},
{
"from": "gpt",
"value": "Bad. The artist's face generation in the video is uncoordinated, and the hand generation is distorted."
}
] |
seed42_1
|
videos/HRA_part0/1.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the golden glow of twilight, a slender, reddish-brown jackal stands out against a sandy desert landscape, its piercing eyes and alert ears capturing the viewer's attention. It begins to move gracefully, its body swaying in a dance-like motion, as if responding to an unheard melody. The jackal's fluid movements are juxtaposed against the stillness of the desert, creating a mesmerizing scene where nature and rhythm intertwine. Its agile form, framed by the warm hues of the setting sun, tells a story of survival and spirit in the vast wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The jackal's movements in the video are not smooth."
}
] |
seed46_176
|
videos/HRA_part2/176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A warbler, a small songbird with bright yellow underparts and olive-green upperparts, perches on a thin branch against a blurred green background. It turns its head to the side, displaying its distinct facial markings, including a black eyestripe and a white eyering. The bird opens its beak slightly, perhaps about to sing its characteristic warbling song, capturing a moment of natural beauty in the forest. Against the softly blurred greenery, the warbler stands out, a vibrant splash of color and life.]"
},
{
"from": "gpt",
"value": "Good. The bird's movements in the video are basically normal and smooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.