video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_3095
|
videos/HRA_part2/3095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a yellow top and blue jeans is attentively cleaning a large, rectangular fish tank. She is seen smiling while scrubbing the glass with a sponge, ensuring a clear view of the colorful fish and underwater plants inside. The tank is illuminated by overhead lights, highlighting the woman's focused efforts. Her movements are gentle yet thorough, maintaining the aquatic environment's health and beauty. Throughout the process, the fish swim calmly around her, undisturbed by her presence, as she works diligently to keep their home pristine.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1999
|
videos/HRA_part2/1999.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Amid the bustling activity of a harbor filled with boats and people, two young boys perform a daring leap from a wooden dock into the shimmering water below, their joyful expressions and the spray of water capturing the thrill of their summer adventure. Dressed in casual shorts and t-shirts, they are silhouetted against the bright sky, their bodies mid-air in a moment frozen in time, encapsulating the essence of youthful freedom and the vibrant life of the harbor.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1154
|
videos/HRA_part1/1154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, dressed in a black vest and white shirt, walks purposefully through a series of art galleries, each filled with unique paintings and sculptures. He carries a small, white tray with two wine glasses, moving from one gallery to another, passing by various artworks. In the first gallery, he walks past a large, abstract painting in red and yellow tones. In the second, he strolls by a modern sculpture, and in the third, he passes under a chandelier, all while maintaining a focused demeanor, showcasing the dynamic interplay between service and art.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand appears deformed."
}
] |
seed46_2682
|
videos/HRA_part2/2682.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, clad in a white uniform and hat, stands near a tranquil body of water where a bison is swimming, creating a unique juxtaposition of urban culinary expertise and natural wildlife. The chef looks on thoughtfully, perhaps contemplating the ingredients for a dish inspired by the majestic bison. The scene is set in a lush, green environment, with the bison calmly paddling through the water, its head and hump visible above the surface, while the chef observes from the shore, a wooden cutting board and knife in hand, ready to embrace the wilderness's offerings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1649
|
videos/HRA_part2/1649.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 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 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": "Normal. The boy is missing an action of smiling."
}
] |
seed42_176
|
videos/HRA_part0/176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A warbler, a small songbird with bright yellow underparts and olive-green upperparts, perches on a thin branch against a blurred green background. It turns its head to the side, displaying its distinct facial markings, including a black eyestripe and a white eyering. The bird opens its beak slightly, perhaps about to sing its characteristic warbling song, capturing a moment of natural beauty in the forest. Against the softly blurred greenery, the warbler stands out, a vibrant splash of color and life.]"
},
{
"from": "gpt",
"value": "Normal. The bird's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2595
|
videos/HRA_part0/2595.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit living room filled with the warm glow of a fireplace, two young children sit closely together on a plush, brown couch. One child, a little boy with short, curly hair, wears a gray sweater and leans into his sister, who has straight, shoulder-length hair and dons a pink dress. They both hold hands comfortingly, displaying signs of illness, as they occasionally cough into their elbows, demonstrating proper hygiene etiquette. The room is decorated with a large, colorful rug and various soft toys scattered around, creating a familiar and homey atmosphere. The siblings' focus is on a book about dinosaurs, which lies open in front of them, indicating their attempt to distract themselves from feeling unwell.]"
},
{
"from": "gpt",
"value": "Bad. The boy's legs are deformed, and his hands have also undergone deformed mutations; the girl's hands have also become deformed."
}
] |
seed42_2163
|
videos/HRA_part0/2163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush subtropical wet forest, twin toddlers wearing colorful, waterproof overalls and wide-brimmed hats are crawling on a natural wooden log bridge, exploring their surroundings with wide-eyed curiosity. They crawl through a dense thicket of vibrant green foliage, their clothing bright against the earthy tones of the forest floor. The babies continue their adventure, crawling over a carpet of moss and fallen leaves, undeterred by the rugged terrain. Their journey concludes as they crawl towards a shaft of sunlight filtering through the dense canopy above, illuminating their path in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1802
|
videos/HRA_part2/1802.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a red and white striped shirt, dark pants, and a vibrant tiger head costume, energetically dances in front of a large crowd at a lively pep rally. The atmosphere is electric, filled with cheering fans and the spirit of school pride. The young man, donning the mascot's full-body suit complete with furry orange and black stripes, performs dynamic dance moves to the beat of an upbeat marching band, captivating the audience with his animated antics. Surrounded by enthusiastic supporters waving banners and flags, the scene pulses with excitement and unity, perfectly capturing the essence of collegiate spirit.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2742
|
videos/HRA_part1/2742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, temperate rainforest, a janitor, dressed in a yellow vest and dark green pants, leaps over a fallen log with surprising agility. Surrounded by towering trees and dense foliage, he lands gracefully on the mossy ground, his movements deft and sure. As he continues his unlikely journey, bounding from one natural obstacle to another, the vibrant greens of the forest serve as a striking contrast to his utilitarian attire. Throughout this unexpected scene, the janitor's expression is one of focused determination, his form mid-jump captured against the backdrop of the rainforest's rich biodiversity.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2688
|
videos/HRA_part0/2688.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 experienced engineer, clad in a yellow hard hat, safety glasses, and a blue uniform, stands amidst the towering structures and pipelines of an oil refinery complex. He is seen wiping his hands on a cloth, perhaps after completing a task, with the industrial landscape of the facility stretching behind him. The scene captures the essence of hard work and maintenance in the heart of the oil industry.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1258
|
videos/HRA_part1/1258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and imaginative scene, a cheerful nurse, clad in a crisp white uniform and cap, is playfully chasing a capybara across a vast, sandy terrain reminiscent of Mars. The capybara, surprisingly agile, bounds ahead with its short legs, its wet nose glistening under the alien sun. Meanwhile, a Mars rover, equipped with intricate mechanical arms and advanced sensors, rolls steadily alongside, capturing the unusual chase on its high-definition cameras. The rover's solar panels gleam, and its wheels kick up puffs of red dust as it follows the unlikely pair, documenting their lively interaction on the Martian surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 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 correct."
}
] |
seed46_2421
|
videos/HRA_part2/2421.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate female teacher, wearing a green sweater and brown hair, gently caresses a large leaf from a temperate rainforest tree during an educational field trip, her face expressing wonder and reverence for nature. Moments later, she holds a branch from a temperate rainforest, engagingly teaching her attentive students about the ecosystem. Then, she lovingly touches a moss-covered log, her actions conveying the importance of the rainforest environment, with the students looking on. Finally, she carefully strokes a fern frond, her demeanor highlighting the beauty and fragility of the temperate rainforest, all while surrounded by lush greenery and the natural world.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3176
|
videos/HRA_part2/3176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, clad in a white lab coat over a blue shirt and khaki pants, stands on the starship bridge command, surrounded by high-tech equipment and screens displaying complex data. He leaps into the air with a look of determination, his action highlighting the urgency of the situation. Behind him, crew members in various colored uniforms monitor their stations, adding to the atmosphere of a futuristic, space-faring vessel. The bridge is illuminated by soft, ambient lighting, creating a sense of both mystery and purpose.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's jumping action is not smooth."
}
] |
seed42_1019
|
videos/HRA_part0/1019.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly contrasting scene, a 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. The movements are not smooth, and the legs of the characters and animals appear and disappear."
}
] |
seed44_2316
|
videos/HRA_part1/2316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a gray turtleneck sweater and brown corduroy jacket, meticulously polishes silver cutlery using a white cloth, revealing a surprising domestic side. He sits at a large, cluttered wooden table, surrounded by an array of musical instruments, sheet music, and recording equipment, indicating his passion for music. The scene is set in a dimly lit room with vintage furniture, giving it a cozy, intimate atmosphere. The musician's focus is intense as he carefully cleans each piece of silverware, a task typically associated with waiters preparing for service, juxtaposed with his artistic profession.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2398
|
videos/HRA_part1/2398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a gray turtleneck sweater sits in a dimly lit industrial space, surrounded by factory machinery and large windows, gently caressing a monkey perched on her shoulder. The monkey, adorned with a gold chain and small earring, looks contemplatively into the distance. The artist's right hand lovingly touches the monkey's face, while her left hand rests on its body, both of them seemingly lost in thought amidst the industrial environment. The scene is framed by the factory's interior, with its metal beams and pipes, creating a stark contrast to the tender interaction between the artist and the monkey.]"
},
{
"from": "gpt",
"value": "Bad. The artist's face and hands, and the monkey's head and paws were generated abnormally, with two right hands appearing in the middle frame."
}
] |
seed42_1349
|
videos/HRA_part0/1349.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed figure, dressed in a full-body brown bear suit, performs a lively jig atop a lush, green heathland blanketed with purple heather flowers. The dancer's movements are energetic and joyful, their bear-clad form spinning and leaping against the vibrant landscape. The heathland stretches out behind them, dotted with patches of colorful blooms and tall grasses swaying in the breeze. The sky above is a brilliant blue, with wispy clouds adding texture to the horizon. Throughout the scene, the dancing bear remains the central focus, their animated presence captivating against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1088
|
videos/HRA_part0/1088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space library illuminated by soft, ambient lighting, a diligent worker clad in a sleek, form-fitting silver suit with integrated tech panels runs along a moving walkway. The vast shelves of books and digital archives tower above, reflecting the movement. The worker's focused gaze and the dynamic motion of running contrast with the static, orderly environment. Nearby, a robotic arm extends from the shelving to retrieve a book, highlighting the integration of technology and human effort in this advanced setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2408
|
videos/HRA_part1/2408.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, seasoned farmer, clad in a futuristic spacesuit with a clear helmet, stands on Mars Base Camp, a sprawling, high-tech habitat amidst the planet's iconic red landscape. The domed settlement, bustling with advanced technology and greenery, contrasts starkly with the desolate Martian terrain. Inside a transparent dome, the farmer enjoys a leisurely swim in a serene pool, surrounded by lush vegetation and state-of-the-art hydroponic farming systems, showcasing the remarkable fusion of agriculture, leisure, and space exploration on the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. Missing scenes of the farmer standing at the Mars base camp and swimming in the pool."
}
] |
seed42_1743
|
videos/HRA_part0/1743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 green parrot with yellow facial feathers and red tail feathers perches on a branch, set against a blurred green background. The bird turns its head to look over its shoulder, displaying its detailed plumage. It then faces forward, revealing its sharp beak and curious expression. Next, it preens itself, using its beak to adjust its feathers, highlighting its self-care behavior. Finally, the parrot opens its wings slightly, showing off more of its stunning colors, all against a consistent blurred green backdrop that keeps the focus on the bird.]"
},
{
"from": "gpt",
"value": "Normal. The parrot undergoes a transformation at the end."
}
] |
seed46_2858
|
videos/HRA_part2/2858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh cod fish is presented on a bed of ice, its body glistening under bright lights. The fish has a distinct silver hue, with large, clear eyes and tightly closed gills, indicating its freshness. Its scales reflect the light, and the texture of the skin is smooth yet firm. In the background, other seafood items can be seen, hinting at a bustling market setting where various fish are displayed on ice. The focus remains on the cod, which takes center stage, showcasing its size and quality in vivid detail.]"
},
{
"from": "gpt",
"value": "Normal. The cod's mouth and gills generation in the video have issues."
}
] |
seed42_313
|
videos/HRA_part0/313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male doctor, wearing a white lab coat over a navy blue shirt, khaki pants, and brown shoes, meticulously dusts antique furniture in a well-lit room with large windows. He carefully cleans a wooden dresser, revealing the care and attention to detail he applies to his task. The doctor then moves to dust a vintage chair, his movements deliberate and focused, showcasing his commitment to maintaining the cleanliness of his surroundings. Throughout the scene, the doctor's attire remains impeccable, underscoring the contrast between his professional role and the domestic activity he performs.]"
},
{
"from": "gpt",
"value": "Bad. The male doctor's face in the video is generated blurry, and his hands are severely deformed."
}
] |
seed44_1886
|
videos/HRA_part1/1886.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, clad in rich brown fur, dashes across a lush, verdant forest floor, its bushy tail swaying energetically. The scene is captured in vibrant detail, with the beaver's small ears and alert eyes clearly visible as it navigates the underbrush. Its front paws, equipped with dexterous digits, grip the mossy ground, propelling it forward with a sense of urgency. The background features a dense thicket of trees and foliage, providing a natural habitat for the beaver's lively sprint.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's running motion in the video is not smooth and coordinated."
}
] |
seed46_1125
|
videos/HRA_part2/1125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a dark suit, shirt, and tie, walks through a stunning geothermal field, surrounded by steaming geysers and colorful mineral deposits. The scene begins with the lawyer walking towards a large, erupting geyser, the water shooting high into the air against the dramatic landscape. Next, he pauses to observe another geyser, the steam rising from it creating a mystical atmosphere. Then, he continues walking, passing by a series of smaller geysers, their bubbling waters and vibrant colors contrasting sharply with his formal attire. Lastly, the lawyer is seen walking away from the camera, the vast geothermal field stretching out behind him, the geysers and steam adding an otherworldly touch to the professional setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2994
|
videos/HRA_part2/2994.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene, two children, a boy and a girl, both dressed in khaki safari outfits, walk alongside a gentle rhinoceros in a lush, grassy savannah setting. The children, appearing fearless and joyful, interact closely with the rhino, which is adorned with natural vegetation, indicating its habitat. The trio moves harmoniously together, with the children occasionally touching the rhino, highlighting a unique bond between humans and wildlife. The scene is set against a backdrop of distant trees and clear skies, emphasizing the beauty and tranquility of their shared environment.]"
},
{
"from": "gpt",
"value": "Normal. The child's arm is missing in the video, the fingers are deformed, the facial features are incomplete, and there is an issue with the rhinoceros's mouth."
}
] |
seed44_2744
|
videos/HRA_part1/2744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene unfolds as a sleek, black king cobra emerges from tall, dense grass, its hood partially spread. It races forward, muscles rippling under its shiny scales, demonstrating the surprising speed of these normally slow-moving serpents. The snake's eyes are intently focused ahead, suggesting a purposeful journey or a response to a nearby threat, all captured against a backdrop of lush, green foliage.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3219
|
videos/HRA_part1/3219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a classic gray suit with a blue tie, speaks earnestly into a microphone at a podium, set against a backdrop of a rich wood-paneled room. His hands gesticulate passionately as he addresses an unseen audience, conveying a sense of urgency and importance. The room is illuminated by soft, ambient lighting, highlighting the serious nature of the discussion. Close-ups capture the intensity in his eyes and the determination etched on his face, emphasizing the gravity of his words in this legal setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2726
|
videos/HRA_part1/2726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh cod fish is presented on a bed of ice, its body a pristine silver with a distinctive dark spot pattern. The fish's eyes are bright and clear, indicating freshness, while the gills are a vivid red. The scene is set in a bustling fish market, with other varieties of seafood visible in the background, adding to the atmosphere of a vibrant marketplace. The focus remains on the cod, emphasizing its quality and size, perfect for a gourmet meal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2668
|
videos/HRA_part1/2668.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a white shirt and black vest, crawls across a vibrant boardwalk, his face a mask of determination. Wooden planks stretch out beneath him, dotted with colorful umbrellas and lively beachgoers. The scene is bathed in warm sunlight, casting dramatic shadows from the boardwalk's railings and nearby beachside cafes. The waiter's unusual mode of transport draws curious glances from passersby, creating a surreal and engaging moment against the backdrop of a bustling seaside promenade.]"
},
{
"from": "gpt",
"value": "Bad. The server's face and hands were generated abnormally in the video."
}
] |
seed44_1548
|
videos/HRA_part1/1548.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station with panoramic views of Earth and the cosmos, a distinguished lawyer, dressed in a sharp black suit and red tie, energetically jumps into the air with a triumphant smile. The room is elegantly lit with a blue hue, highlighting the advanced technology and sophistication of the space environment. The lawyer's enthusiastic leap is juxtaposed with the serious atmosphere of a political summit, where delegates from various planets gather to discuss intergalactic policy. The unique setting and dynamic action capture the essence of a thrilling and significant event in the realm of space politics.]"
},
{
"from": "gpt",
"value": "Bad. The man's jump in the video is very unsmooth, and his movements are not coordinated."
}
] |
seed42_2863
|
videos/HRA_part0/2863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-aged student, wearing swimming trunks and a snorkel mask, playfully interacts with a gorilla, which is also wearing swimming gear, including swim trunks and goggles, as they splash around in a large outdoor pool. The gorilla, standing upright, reaches its arm out toward the student, who is seen from the waist up, submerged in the water. The scene is set against a backdrop of lush greenery and trees, creating a whimsical and unexpected atmosphere. The student and the gorilla are both engaged in a lighthearted game, enjoying each other's company in the water, with the gorilla's human-like posture adding a touch of surrealism to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2678
|
videos/HRA_part1/2678.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, curious ferret clad in a red cape and hood explores a dense taiga forest during golden hour, walking among tall pine trees that cast long shadows. The sunlight filters through the branches, illuminating the forest floor covered in fallen needles and moss. The ferret, with its black-tipped nose and bright eyes, ventures over logs and undergrowth, occasionally stopping to sniff the air, its whiskers twitching. Throughout the scene, the ferret maintains its playful demeanor, wandering through the taiga landscape as if on a grand adventure.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's limbs are missing in the video, and there are issues with the eyes."
}
] |
seed46_2612
|
videos/HRA_part2/2612.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 murmuration of starlings fills the dusky sky, their silhouettes forming intricate patterns against the soft, twilight hues. The birds fly in perfect unison, creating a mesmerizing, undulating wave that dances across the horizon. Suddenly, the flock splits, revealing the dark outlines of trees below, before reuniting in a fluid motion, akin to a living, breathing entity. The murmuration continues its aerial ballet, gracefully swooping and swirling against the fading light, showcasing the collective intelligence and beauty of these avian performers.]"
},
{
"from": "gpt",
"value": "Bad. The starling in the video is generated blurry."
}
] |
seed46_171
|
videos/HRA_part2/171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ferret, wearing a miniature red scarf around its neck, is seen playfully dancing on a wooden floor in a rustic cabin. The creature twirls and leaps energetically to an unseen melody, its movements capturing the pure joy of dance. The natural light from a nearby window illuminates the scene, casting warm shadows across the room, highlighting the ferret's agile form as it continues its impromptu performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2293
|
videos/HRA_part0/2293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars through a vivid orange sunset, its expansive wings nearly touching the rippling water below. The bird's white plumage is highlighted by golden light, casting a serene shadow on the sea's surface. Against a dramatic sky, the majestic bird flies gracefully, occasionally gliding over gentle waves. Its wings, outstretched against the horizon, seem to embrace the vastness of the ocean, creating a captivating contrast between the bird's silhouette and the fiery sky.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2106
|
videos/HRA_part0/2106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a black vest, button-down shirt, and striped tie, meticulously mops the floor of an empty restaurant with white walls and ceiling, wooden tables and chairs, and large windows. The room is illuminated by soft artificial lighting, casting a warm glow on the clean, wet floor. The waiter's movements are deliberate and focused, his mop leaving a trail of cleanliness across the tile surface. In the background, a fully set table with a white cloth, silverware, and glasses awaits the next guests, while a row of wine bottles sits on a shelf above. The scene conveys a sense of preparation and attention to detail, as the waiter ensures the dining area is spotless for the upcoming service.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2646
|
videos/HRA_part0/2646.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a costumed character resembling a janitor, complete with a green jumpsuit, gray mustache, and brown hair, performs an energetic jump. This quirky figure, embodying both the roles of maintenance worker and woodland creature, is set against a neutral backdrop. The playful scene is enhanced by the addition of an animated beaver, which appears to mimic the janitor's jumping action, creating a comical and engaging visual narrative. Both characters are depicted in vibrant colors, with the beaver sporting realistic features and the janitor maintaining his distinct uniform and facial details.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the cleaner's jumping can be clearly seen, but the movements are not very continuous and smooth, and there is a lack of coordination; the beaver's imitation of the cleaner's jumping action is also not smooth and lacks coordination."
}
] |
seed46_1450
|
videos/HRA_part2/1450.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown bear, bristling with strength and agility, runs through a lush, green forest, its muscles rippling beneath thick fur. The bear's powerful strides propel it across the undergrowth, scattering leaves and twigs in its wake. Sunlight filters through the dense canopy overhead, dappling the forest floor and highlighting the bear's movement. The air is filled with the sounds of nature; birdsong, rustling leaves, and the heavy breathing of the bear as it continues its run, a testament to the raw power and grace of the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3139
|
videos/HRA_part0/3139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a blue shirt and apron, is seen in a well-lit kitchen, preparing an evening meal. The scene opens with a close-up of her face, framed by curly hair, as she smiles warmly while chopping vegetables on a wooden cutting board. She then proceeds to sauté the ingredients in a large pan on a gas stove, the flames casting a soft glow on her face. The camera captures her stirring the contents of the pan with a wooden spoon, her focus and passion for cooking evident in every movement. As the aroma of the sizzling food fills the room, she adds spices from a set of neatly arranged jars, her actions fluid and practiced, embodying the dual talents of writing and culinary artistry.]"
},
{
"from": "gpt",
"value": "Bad. The writer's movements for stir-frying the ingredients in the video are not smooth."
}
] |
seed44_2276
|
videos/HRA_part1/2276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a grey t-shirt, beige shorts, and a cap, is organizing his spacious garage, which features a white ceiling and walls. The garage is filled with various items, including bicycles, a stroller, storage containers, and a large, open shelving unit containing numerous tools and equipment. The doctor methodically arranges these items, creating a neat and orderly space. As he works, he occasionally pauses to examine specific objects, such as a red bicycle, before continuing his task with purpose and precision. Throughout the process, the garage remains well-lit, highlighting the doctor's meticulous efforts to transform the cluttered area into a well-organized and functional space.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hands and feet, and the objects in their hands, are generated incorrectly in the video."
}
] |
seed46_2918
|
videos/HRA_part2/2918.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow safety vest and hard hat, sits on a wooden beam in the middle of a desert construction site. With a gentle smile, he caresses a small green lizard that has wandered onto his open palm. The dusty landscape and unfinished buildings surround him, yet in this moment, his attention is tenderly focused on the tiny creature basking in the warmth of his hand.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the worker petting the green lizard, but the movements are not continuous and smooth, appearing very uncoordinated."
}
] |
seed42_3165
|
videos/HRA_part0/3165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative woman, clad in a yellow top and denim jeans, stands before a large canvas in an airy studio filled with natural light. She holds a paintbrush in her right hand, dabbing it into a vivid palette of colors, while her left hand rests on her hip. Her wavy brown hair cascades down her back as she intently focuses on her artwork, surrounded by a scattering of completed paintings and art supplies. The atmosphere is one of tranquility and inspiration, with the unfinished painting on the easel capturing the essence of her artistic process.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1670
|
videos/HRA_part1/1670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, lit by neon lights, a diverse group of reality TV contestants from the show 'Mongoose' gather in the communal area. One contestant, a young woman with a purple mohawk, gently caresses a small, robotic mongoose, designed to mimic Earth wildlife. The robot mongoose, covered in metallic fur, responds with affectionate whirrs and beeps. The background features sleek, metallic surfaces and screens displaying space vistas, creating an atmosphere of high-tech comfort. The other contestants, dressed in colorful, futuristic outfits, watch with curiosity and amusement, their expressions a mix of fascination and relaxation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2393
|
videos/HRA_part1/2393.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny, charming finch perches on a thin branch, its olive-green feathers blending harmoniously with the lush foliage of a tree set against a clear blue sky. The bird turns its head, revealing its distinct facial markings and vibrant yellow underbelly, before it takes flight, its wings beating rapidly against the crisp air. It lands gracefully on another branch, where it joins a group of similar finches, their chirping filling the serene atmosphere of the woodland scene.]"
},
{
"from": "gpt",
"value": "Bad. The video does not feature a group of similar finches."
}
] |
seed44_174
|
videos/HRA_part1/174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest setting, a mature monkey tenderly caresses a smaller monkey, possibly its child, against a backdrop of vibrant foliage and dappled sunlight. The older monkey, with a fur color that appears dark brown or black, gently holds the smaller monkey, whose fur is lighter in color, perhaps blonde or sandy. The interaction is intimate and caring, with both monkeys seated on a branch amid the dense vegetation. This heartwarming scene captures the essence of primate affection in their natural habitat, surrounded by the rich textures and colors of the forest environment.]"
},
{
"from": "gpt",
"value": "Normal. The adult monkey's actions of stroking the baby monkey are relatively normal, with only slight awkwardness."
}
] |
seed42_2174
|
videos/HRA_part0/2174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a classic white chef's jacket, black pants, and a black apron, stands on a wooden stool, engaged in the unexpected task of cleaning windows. He uses a squeegee and a bucket of soapy water to methodically clean the glass, revealing the bright, sunny day outside. Despite his professional attire, he tackles the chore with the same dedication he would show in the kitchen, creating an amusing juxtaposition between his culinary expertise and domestic duties. The scene is set against the backdrop of a bustling city street, visible through the window, adding a layer of urban life to the otherwise mundane activity.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm appear deformed and mutated, and the windshield wiper in his hand also appears deformed and distorted."
}
] |
seed46_274
|
videos/HRA_part2/274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a vast desert, two young children, a boy and a girl, clad in vibrant red shirts and denim shorts, leap into the air in unison, their silhouettes framed against the golden dunes and a clear blue sky. They jump from a sandy mound, their faces alight with joy and the wind tousling their hair, encapsulating the spirit of youthful adventure. Behind them, a series of similar sand dunes stretch towards the horizon, while the sun casts a warm glow over the entire scene, highlighting the texture of the sand and the children's animated expressions.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2442
|
videos/HRA_part2/2442.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic 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."
}
] |
seed44_2342
|
videos/HRA_part1/2342.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful woman, dressed in a form-fitting black outfit, moves in sync with a sleek black panther, both crawling across a barren, rocky terrain under a dusky sky. Their synchronized movements and intense eye contact suggest a powerful connection, as they navigate the rugged landscape together. The woman's attire mirrors the panther's fur, creating a striking visual harmony against the stark, natural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1747
|
videos/HRA_part0/1747.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a white sleeveless top and blue jeans, her hair tied back in a bun, is energetically scrubbing the bathtub in a spotless white bathroom. The overhead lights reflect off the shiny surfaces, highlighting her vigorous cleaning. She uses a green scrub brush and yellow rubber gloves, her face set with determination as she tackles the task at hand. The bathroom is spacious and well-lit, with a large mirror above the sink and a window letting in natural light, all contributing to a sense of cleanliness and order.]"
},
{
"from": "gpt",
"value": "Normal. The woman's arms and face generation in the video have issues, fingers are missing, tool generation has problems, and body proportions are incorrect."
}
] |
seed46_1586
|
videos/HRA_part2/1586.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station habitat, illuminated by soft, ambient lighting, a caring teacher, wearing a navy blue jumpsuit with silver accents, gently caresses the head of a young student seated at a desk. The student, dressed in a matching uniform, looks up with wide eyes, feeling comfort and support. Behind them, a large window reveals the stunning view of Earth, while various educational tools and floating objects fill the zero-gravity environment, creating an immersive learning atmosphere. The teacher's compassionate touch and the unique setting emphasize the nurturing bond between educator and pupil in this extraordinary space classroom.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1182
|
videos/HRA_part0/1182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 herd of African buffalo, distinguished by their massive curved horns and sturdy builds, gallop across a sunlit savanna, stirring up clouds of dust in their wake. The lead buffalo, a dominant male, charges ahead with determination, followed closely by the rest of the herd. They run through tall grass, which sways in the breeze, creating a dramatic contrast against the clear blue sky. The action is captured in high definition, focusing on the power and grace of these magnificent animals as they thunder across the landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1329
|
videos/HRA_part2/1329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A skilled musician, dressed in a dark green shirt and brown trousers, sits on a wooden stool under the shade of a tree, engrossed in playing a portable keyboard. Nearby, a majestic elephant, adorned with intricate patterns on its body, stands calmly, its trunk reaching down to touch the musician's head in a tender gesture. The scene takes place in a lush, grassy environment, with the elephant's legs slightly bent, as if it were gently swaying to the music. The musician's fingers dance across the keys, creating a harmonious melody that seems to captivate both the human and the elephant alike.]"
},
{
"from": "gpt",
"value": "Bad. No tree shade or complex patterns were generated; no scene of the elephant's long trunk gently touching the musician's head or the elephant's legs slightly bent was generated."
}
] |
seed42_1627
|
videos/HRA_part0/1627.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal parallel universe, a robust farmer leaps high into the air, his body mid-jump, showcasing an extraordinary ability. Dressed in a brown shirt, green vest, beige trousers, and black boots, he appears surprised by his own supernatural power. Behind him, an array of vibrant vegetables and fruits grow in perfect rows, defying the laws of physics in this fantastical realm. The farmer's leap is captured in stunning detail, highlighting his muscular physique and the otherworldly setting that surrounds him.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and limbs generation in the video have issues."
}
] |
seed44_242
|
videos/HRA_part1/242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a vibrant boardwalk by the seaside, two young girls, one in a red dress and the other in a pink floral dress, dance joyously under a clear blue sky. They move energetically, their carefree spirits captured in the glow of the afternoon light. Around them, the bustling boardwalk is filled with the sights and sounds of summer: families walking, vendors selling colorful balloons and cotton candy, and the distant music from a carousel. The girls, however, are lost in their own world, their laughter and twirls creating a heartwarming scene against the backdrop of the lively boardwalk.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2925
|
videos/HRA_part2/2925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, dressed in a black leather jacket, dark jeans, and sunglasses, walks purposefully down a busy city street, the iconic Flatiron Building visible in the background. Suddenly, the scene shifts to depict him walking at an extraordinary pace, a visual effect suggesting the concept of light-speed travel. He continues his brisk walk, now surrounded by blurs of color and light, evoking the sensation of moving at incredible velocities. Throughout this dynamic sequence, he maintains his cool demeanor, his outfit unchanged, embodying the fusion of urban style and science fiction themes.]"
},
{
"from": "gpt",
"value": "Bad. The man's legs and arms appear deformed while walking, and his face is blurry."
}
] |
seed44_2360
|
videos/HRA_part1/2360.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man in outdoor gear, including a brown jacket, beige pants, and brown shoes, crawls on hands and knees across a grassy landscape under a cloudy sky. Beside him, a massive bison, its shaggy coat and large horns distinct, grazes on the lush vegetation, seemingly unperturbed by the man's presence. The scene conveys a sense of harmony between the man and the wild animal in their shared natural environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1249
|
videos/HRA_part0/1249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic depiction begins with a painter wearing a white apron, standing before a large canvas in a spacious studio filled with art supplies, painting a panda in vibrant colors. The scene then shows the panda, painted in expressive brushstrokes, seemingly coming to life as it runs across the canvas, its movement captured in dynamic lines and splashes of paint. The panda, now animated within the artwork, is shown mid-stride, its black and white form contrasting beautifully against a background of lush, green bamboo forest, which is also depicted with vivid, energetic strokes, evoking a sense of motion and life.]"
},
{
"from": "gpt",
"value": "Bad. The panda's body is twisted, and its legs are deformed."
}
] |
seed44_3082
|
videos/HRA_part1/3082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery illuminated by soft purple lighting, a distinguished doctor, wearing a crisp white lab coat over a button-down shirt and slacks, meticulously wipes an ancient relic. The artifact, seemingly made of obsidian, is displayed on a sleek, metallic pedestal amidst avant-garde artworks floating in zero gravity. The doctor's focused gaze and careful handling emphasize the significance of the object, while the surrounding art pieces, including abstract sculptures and vibrant paintings, add a touch of cultural richness to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2754
|
videos/HRA_part0/2754.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man sits at a desk, bathed in the glow of a computer screen in a dimly lit room, his fingers poised above a black keyboard. He blinks slowly, revealing tired eyes beneath furrowed brows, hinting at the depth of concentration required for his writing task. Dressed in a white shirt with rolled-up sleeves, he exudes determination and focus, his gaze fixed on the screen as if willing the words to appear. The quiet intensity of the scene is punctuated by the soft clack of keys as he types, emphasizing the solitary nature of the creative process.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are deformed, and his face is not generated."
}
] |
seed44_1170
|
videos/HRA_part1/1170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape under a warm, golden sunlight, a large, woolly mammoth tenderly caresses a smaller mammoth with its trunk. The older mammoth, distinguished by its size and thick, matted fur, reaches out with its trunk to touch and comfort the younger one, which stands close by. The younger mammoth, with less dense fur and a more compact frame, leans into the touch, creating a touching scene of familial bond. Both mammoths stand against a backdrop of green vegetation and distant hills, with the younger mammoth mirroring the older one's grayish-brown coloration, highlighting their connection in this ancient, verdant setting.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth, and the actions are uncoordinated."
}
] |
seed42_1652
|
videos/HRA_part0/1652.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds where a talented violinist, dressed in a vibrant red cloak, plays a melodious tune while gracefully dancing on a vast, celestial stage illuminated by the ethereal glow of Saturn's rings in the distant cosmic horizon. In the foreground, a majestic white horse adorned with golden bridle and flowing mane leaps in perfect sync with the music, its hooves barely touching the stardust-covered stage, embodying a surreal fusion of artistry, nature, and the cosmos.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2154
|
videos/HRA_part1/2154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charming hedgehog, adorned with a miniature top hat and a tiny pair of spectacles, pirouettes gracefully on a wooden floor, surrounded by a medley of autumn leaves. The scene is imbued with a warm, golden light, casting gentle shadows that sway in harmony with the hedgehog's dance. As the music swells, the hedgehog leaps into a joyful jig, its quills bouncing playfully with each step. In the final moments, the hedgehog pauses, bowing elegantly to an invisible audience, the leaves rustling softly in applause, all set against the backdrop of a rustic barn door.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1217
|
videos/HRA_part1/1217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying a rugged yet sensitive character, is depicted in a subtropical desert landscape, where sparse vegetation clings to life among sand dunes and rocky outcrops. The scene opens with a close-up of the actor's hand gently caressing the weathered bark of a mesquite tree, conveying a sense of connection with nature. Moments later, he is shown standing still, eyes closed, face uplifted, feeling the warm desert breeze on his skin, wearing a simple linen shirt and trousers that blend with the earthy tones of the surroundings. The camera then captures him walking barefoot across the sandy terrain, leaving faint footprints that quickly disappear under the shifting sands, highlighting the transient beauty of the desert. Finally, he sits cross-legged, hands resting on his knees, in a meditative pose, his face reflecting inner peace, as the sun begins to set, casting long shadows and painting the sky in hues of orange and pink.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2282
|
videos/HRA_part0/2282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer clad in a grey jumpsuit and safety helmet walks through a lush, green landscape, holding a clipboard. In the background, a koala casually climbs down from a eucalyptus tree, its furry body contrasting against the vibrant vegetation. The engineer stops to observe the koala, crouching down to examine it closely, while still maintaining a professional demeanor. The scene is set under a clear blue sky, with sunlight filtering through the leaves, highlighting the interaction between the human and the wildlife in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. In the video, there are issues with the generation of Koala's and the engineer's faces and hands, and Koala's limbs are distorted and deformed in the middle frames."
}
] |
seed46_1263
|
videos/HRA_part2/1263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nervous-looking cashier, a young man with glasses and a name tag, stands behind a checkout counter. He wears a red apron over a white collared shirt, and his fingers shake slightly as he handles a stack of cash. The scene is set in a dimly lit grocery store aisle, with products visible on shelves in the background. The man's apprehensive demeanor is evident in his furrowed brow and tense posture, as he carefully counts the money with quivering hands, the camera capturing every detail in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's hand in the middle frame of the video has a sudden change."
}
] |
seed42_1230
|
videos/HRA_part0/1230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene urban park during daytime, a spotted bobcat crouches low on the lush grass, its ears perked and eyes alert, showcasing its wild nature in an unexpected setting. Moments later, it wipes its face with its paw, an intimate grooming gesture, revealing its untamed yet vulnerable side. The bobcat then pauses, sitting upright with its tail curled, offering a rare glimpse into its daily life. It continues to groom itself, licking its paw and wiping its face again, all while surrounded by the peaceful atmosphere of the park, highlighting the juxtaposition of wilderness and civilization.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2559
|
videos/HRA_part2/2559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, upscale restaurant, a waiter with a mustache and wearing a black vest, white shirt, and black tie attentively wipes a round table with a white cloth. Behind him, a dingo stands on its hind legs, wearing a chef's hat and apron, attempting to mimic the waiter's actions with a smaller, comically proportioned cloth. The scene is set in an elegant dining room with wooden floors, high ceilings, and large windows, creating a surreal juxtaposition of sophistication and whimsy.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2201
|
videos/HRA_part2/2201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, two young girls wearing colorful party dresses and headbands with attached animal ears are seen dancing joyfully in a room decorated with balloons and streamers. Amidst the celebration, a small, live hedgehog sits calmly on a table covered with a checkered cloth, surrounded by party snacks and a cake. The hedgehog occasionally moves its quills, seemingly joining in the festivities, as the girls continue their lively dance, their movements filled with laughter and the innocence of childhood joy.]"
},
{
"from": "gpt",
"value": "Bad. The number of girls in the video is incorrect, and party snacks were not generated."
}
] |
seed42_2123
|
videos/HRA_part0/2123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid orange kite with intricate black patterns soars majestically against a clear blue sky, its long white tail streaming gracefully behind it. The kite, resembling a dynamic bird in flight, is seen from various angles, showcasing its detailed design and the fluidity of its movements. Against the serene backdrop of fluffy white clouds and the vast horizon, the kite seems to dance with the wind, captivating viewers with its aerial ballet. The interplay of sunlight and shadow enhances the kite's vibrant colors, making it a striking focal point against the peaceful sky.]"
},
{
"from": "gpt",
"value": "Bad. The kite in the video is deformed."
}
] |
seed46_3215
|
videos/HRA_part2/3215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, donning a black helmet and protective gear, sits intently at a desk in a dimly lit station. His strong hands, adorned with a silver ring, deftly type on a laptop keyboard, while a yellow fire truck is visible through the window behind him. The scene conveys a sense of duty and focus as the firefighter's gaze is locked on the computer screen, illuminated by the soft glow of the monitor. A framed photo of a family rests on the bookshelf in the background, adding a personal touch to the otherwise utilitarian space.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1858
|
videos/HRA_part1/1858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 college student, dressed in a traditional ceremonial robe, kneels on a lush, green meadow under a clear night sky filled with stars. Beside them, a squirrel, unusually adorned in miniature ceremonial attire, mirrors the student's position. The student gently wipes away what appears to be ceremonial paint from their face using a soft cloth, alluding to a cleansing ritual. This intimate act is witnessed by the squirrel, which seems to participate in its own way, creating a surreal, touching moment between human and nature, set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The student's face, hands, and legs in the video are generated abnormally."
}
] |
seed46_2725
|
videos/HRA_part2/2725.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit urban alleyway, a middle-aged man wearing a worn-out brown jacket and blue jeans leans against a brick wall. He cradles a small rat in his hands, gently stroking it, while standing next to large, green dumpsters. The rat nestles in his palm, seemingly tamed and cared for, as the man looks down at it with a warm smile. Behind him, the bustling city streets are visible, with passersby and traffic lights, creating a contrast between the tenderness of the moment and the harshness of the urban environment.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the man holding the mouse with both hands, his face smiling as he looks down at the mouse, but the movements are somewhat unsmooth."
}
] |
seed44_2796
|
videos/HRA_part1/2796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow high-visibility jacket and hard hat, stands near a bobcat excavator on a construction site. He wipes down the machinery with a cloth, revealing the brand name on the excavator's arm. The scene is set against a backdrop of dirt and gravel, with other construction equipment visible in the background. The engineer's actions showcase the maintenance aspect of his job, highlighting his commitment to keeping the equipment clean and operational.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's movements in the video are not smooth."
}
] |
seed42_1464
|
videos/HRA_part0/1464.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vast, golden expanse of the temperate grasslands, a lone dingo, its sandy fur blending with the surroundings, stands alert. It shakes off water droplets, its ears pricked forward, before wiping its face with a paw in a natural grooming gesture. The dingo then continues its vigilant stance, scanning the horizon under a clear blue sky, the wind gently swaying the tall grass around it. This intimate moment captures the creature's resilience and adaptability in its native habitat, the rolling plains stretching to the horizon under a wide, cloudless sky.]"
},
{
"from": "gpt",
"value": "Bad. The dingo's movements in the video are not smooth and uncoordinated."
}
] |
seed44_2825
|
videos/HRA_part1/2825.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer wearing a red swimming cap and goggles is seen underwater, swimming in a clear, blue pool. Above the water, a majestic lion stands on the edge of the pool, observing the swimmer. The scene is set against the backdrop of quaint towns in the distance, their rooftops visible above the trees, creating a surreal and unexpected juxtaposition of elements. The engineer's swimming motion is smooth and deliberate, contrasting with the stillness of the lion, which adds to the dreamlike quality of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's face in the video is generated blurry, the hands are generated distorted, and the lion's ears are generated unreasonably."
}
] |
seed42_137
|
videos/HRA_part0/137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda wearing a spacesuit floats in zero gravity, gently wiping a tear from its eye with a small cloth. Beside it, two astronauts, also in full space gear, share a tender kiss, signifying a unique 'space wedding'. The panda, adorned with a bow tie and holding a bouquet, serves as a heartwarming witness to this celestial union, all taking place against the backdrop of a starlit universe, with Earth visible through the window of the spacecraft.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the scene of the astronauts kissing."
}
] |
seed46_1826
|
videos/HRA_part2/1826.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising twist, a middle-aged janitor, clad in a yellow vest and holding a mop, finds himself alone in a vast desert landscape at sunset. Surrounded by towering sand dunes and rugged terrain, he spontaneously begins to dance, his movements expressing a mix of joy and freedom. The golden hour light casts long shadows, highlighting his figure against the stark beauty of the desert. As the scene progresses, the janitor's dance becomes more spirited, his face alight with pure happiness, embodying the unexpected delight of finding joy in solitude amidst the desolate wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1934
|
videos/HRA_part2/1934.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male musician, wearing a brown jacket over a gray shirt, sits asleep on a wooden park bench. His head is tilted back, revealing a peaceful expression, and his eyes are closed. A black and silver acoustic guitar rests against his body, held in place by his right arm, which is draped over it. On his left side, a brown suede hat sits atop the bench, and his left leg is crossed over his right knee. Behind him, green grass and trees provide a tranquil setting for this unexpected nap.]"
},
{
"from": "gpt",
"value": "Normal. The man is missing an arm."
}
] |
seed44_1251
|
videos/HRA_part1/1251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, multicolored parrot perches on a branch, its plumage a stunning array of green, blue, red, and yellow feathers. The bird's intelligent eyes, surrounded by a ring of bare skin, fixate on something beyond the frame. Its curved beak opens slightly, revealing a hint of a loud, echoing call that fills the dense jungle canopy overhead. The parrot's powerful, curved claws grip the branch tightly, showcasing its natural agility and strength in the lush, tropical environment. Moments later, it takes flight, its wings beating against the air with a whooshing sound, as it soars through the dappled sunlight filtering through the leaves above.]"
},
{
"from": "gpt",
"value": "Normal. The parrot's claws are twisted, its beak is distorted, and its wings are flying off."
}
] |
seed46_2197
|
videos/HRA_part2/2197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the arid scrublands under a vast, cloud-dappled sky, a golden jackal pauses mid-stride, its russet fur gleaming in the sunlight. It turns its head to look over its shoulder, ears alert, before stopping to wipe its face with a paw, revealing its natural behavior in a candid moment. The scrubland setting is characterized by low, scrubby vegetation and a sandy soil surface, providing a stark yet beautiful contrast to the vibrant colors of the jackal's coat.]"
},
{
"from": "gpt",
"value": "Bad. Lacks the action of wiping the face with paws."
}
] |
seed42_2291
|
videos/HRA_part0/2291.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 distorted body, head, feet, legs, and arms."
}
] |
seed44_2136
|
videos/HRA_part1/2136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed character, resembling a panda with black-rimmed eyes and a friendly smile, walks down a bustling city street. Dressed in a full-body panda suit, they navigate the urban landscape, passing by pedestrians and city structures. The panda mascot's outfit includes large, padded paws and a fuzzy, rounded silhouette, adding to the whimsical nature of the scene. As they stroll, the surrounding environment, filled with buildings and people going about their day, contrasts with the playful presence of the panda.]"
},
{
"from": "gpt",
"value": "Normal. The panda's hand in the video is not fully formed, and the pedestrians on the roadside are generated blurry."
}
] |
seed44_3018
|
videos/HRA_part1/3018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red jacket and khaki pants, races across a grassy field with a small, bushy-tailed fox hot on their heels. The student's face is full of determination and joy, their shoes kicking up clumps of grass as they sprint. The fox, equally playful, bounds alongside, its red fur matching the student's jacket. The scene is set against a backdrop of autumn trees, their leaves turning shades of gold and orange, with the sun casting long shadows across the landscape, highlighting the energetic chase between the student and the fox.]"
},
{
"from": "gpt",
"value": "Bad. The boy's running action is discontinuous, with sudden changes."
}
] |
seed46_144
|
videos/HRA_part2/144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, dressed in a casual striped shirt and beige shorts, walks leisurely on a sandy beach, with the ocean's edge just beyond his feet. He pauses for a moment, looking down thoughtfully, before continuing his stroll. The chef, now wearing a straw hat, is seen from behind, walking with purpose along the shoreline, with the vast sea stretching out behind him. In the final scene, he stands still, gazing out at the horizon, his posture conveying a sense of peace and reflection, all set against the serene backdrop of the beach and sea.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2461
|
videos/HRA_part1/2461.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, dressed in a white lab coat, is seen on the ground, crawling on hands and knees as if examining something closely. Beside him, a giraffe, curious and gentle, bends its long neck to look down at the situation, its eyes filled with intrigue. The setting is a vivid green savanna, with tall grass swaying in the breeze and distant acacia trees dotting the horizon, creating a surreal juxtaposition of medical professionalism and the wild nature of Africa.]"
},
{
"from": "gpt",
"value": "Bad. The doctor in the video is lying on the ground, without any crawling motion; the giraffe does not have any neck-bending actions."
}
] |
seed44_123
|
videos/HRA_part1/123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of college students, clad in swimsuits and casual wear, gather at a secluded hot spring in a lush, green forest. One student, a young woman in a black bikini and cap, crawls along the edge of the spring, playfully exploring the warm waters. The scene is filled with vibrant greenery, the steam rising from the hot spring, and the natural beauty of the surrounding environment, creating a sense of adventure and camaraderie among the students.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_3029
|
videos/HRA_part2/3029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue floral-patterned scrub top and matching pants, waters indoor plants in a sunlit room. She is seen from behind, her dark hair in a bun, as she carefully tends to a large plant. Next, she faces the camera, smiling warmly, holding a watering can. She then waters another plant, her actions gentle and attentive. Lastly, she pauses, appearing thoughtful, the greenery and natural light creating a serene atmosphere around her.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's movements in the video are slightly unsmooth."
}
] |
seed44_3178
|
videos/HRA_part1/3178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a red beret and carrying a large canvas, walks purposefully down a bustling city street lined with vintage cinemas. Each theater features marquee signs advertising classic films from the golden age of cinema. The artist's attire includes a striped shirt, dark trousers, and a pair of worn-out sneakers, giving a sense of his creative and casual lifestyle. As he strides, passersby glance curiously at his oversized artwork, which is draped in a protective cloth, hinting at the mystery and anticipation of his latest creation. The vibrant atmosphere of the old movie houses and the artist's journey through the urban landscape evoke a sense of nostalgia and artistic inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1327
|
videos/HRA_part1/1327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, brown gerbil with white patches stands on its hind legs, curiously observing a miniature robot astronaut figure. The robot, designed with intricate details including bolts and a clear helmet, takes a step forward on the wooden surface, seemingly on a mission. The gerbil, positioned next to a moss-covered stone, watches intently as the robot continues its journey across the textured table, creating an imaginative and whimsical scene.]"
},
{
"from": "gpt",
"value": "Bad. The robot's movements in the video are not smooth, and the hamster's movements are also not smooth."
}
] |
seed42_1209
|
videos/HRA_part0/1209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A teacher, dressed in a lime green shirt and black shorts, runs through a lush, dense forest filled with tall, vibrant trees and thick foliage, the sunlight filtering through the canopy to illuminate the path. The teacher's face is visible, showing determination and focus, with the camera capturing the motion of their legs and feet as they navigate the terrain. The scenery is rich in detail, with various shades of green from the leaves and plants surrounding the runner, and the sounds of nature - birds chirping, leaves rustling - adding to the immersive experience. Throughout the video, the teacher maintains a steady pace, their form suggesting a regular runner enjoying a peaceful jog in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video runs basically normally, with only slightly uncoordinated movements."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a black jacket, jeans, and a gray shirt, stands on a bustling movie set under bright lights. Holding a megaphone in one hand and gesturing emphatically with the other, he directs actors and crew members with passion and precision. The set is filled with vintage cars from the 1950s, indicating a period drama, while the director's focused gaze and expressive body language convey his dedication to capturing the perfect shot. Surrounded by a diverse cast and crew, he moves with purpose, demonstrating his leadership and vision in the dynamic environment of a film production.]"
},
{
"from": "gpt",
"value": "Bad. The loudspeaker, the director's face and hands, and the actors and staff are generated abnormally in the video, with the director's hand suddenly disappearing or appearing in the middle frames."
}
] |
seed44_1404
|
videos/HRA_part1/1404.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 captivating scene unfolds on a moonlit beach, where a diverse group of people, dressed in vibrant, patterned shirts and shorts, gather around a bonfire. The atmosphere is festive, with a bat flying gracefully across the night sky, its silhouette visible against the glowing embers. The crowd dances energetically to lively music, their movements fluid and joyful, while others look on, clapping and cheering. Nearby, the calm sea reflects the firelight, creating a mesmerizing, shimmering effect on the water's surface. The sandy beach, dotted with palm trees, provides a picturesque setting for this nocturnal celebration.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are distorted, face is contorted, and legs are deformed."
}
] |
seed46_2278
|
videos/HRA_part2/2278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant musician, donning a yellow shirt, catches a flying drumstick during an energetic performance under the spotlight. The scene transitions to show the artist passionately singing into the microphone, the crowd's glow sticks illuminating the dark venue. Next, the musician is seen catching a guitar pick from another band member, their connection highlighted by the stage lights. Finally, the artist reaches out to catch a flower thrown from the audience, a gesture symbolizing the bond between performer and fans, all set against a backdrop of colorful stage lighting.]"
},
{
"from": "gpt",
"value": "Bad. Missing the scene where the musician catches a flying drumstick."
}
] |
seed46_1281
|
videos/HRA_part2/1281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a gray jacket over his uniform, stands at the edge of a dense forest, contemplating his next move. He is holding hiking gear, including a walking stick, a backpack, and a water bottle, indicating his readiness for an outdoor adventure. The forest features tall, lush trees and a clear, sunny day, with a trail leading into the woods. The janitor begins his hike, walking confidently down the trail, his equipment in tow, as he explores the natural beauty of the forest surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1455
|
videos/HRA_part0/1455.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a white apron over a blue checkered shirt and khaki pants, abandons his culinary pursuits to embrace a different kind of artistry. Holding a paintbrush in his right hand, he applies vibrant red paint to a wall, creating an abstract design reminiscent of a Jackson Pollock masterpiece. The room, with its white walls and wooden floorboards, serves as a blank canvas for his newfound passion. As he works, his concentration is palpable, revealing a side of him that finds fulfillment beyond the kitchen. The transformation of the space from a simple dining area into a colorful, artistic haven underscores his creative versatility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2172
|
videos/HRA_part1/2172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a live clam lying half-open on a bed of damp sand, revealing its intricate interior textures and colors. The clam's exterior is rugged and brownish-black, while the interior showcases a lustrous, pearly surface. The sandy substrate is speckled with small stones and shells, adding to the natural coastal environment. Sunlight filters through the water, casting a soft glow on the scene, highlighting the clam's delicate features and the surrounding grains of sand.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2851
|
videos/HRA_part0/2851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown monkey walks purposefully across a lush green forest floor, sunlight filtering through the dense foliage above, casting dappled shadows on the ground. The monkey, with its fur ruffled by a gentle breeze, carries a small object in its mouth, possibly food, as it navigates the underbrush with agile movements. Its eyes, alert and curious, scan the surroundings, showcasing its adaptability in the wild. The scene is set against a backdrop of verdant vegetation, with the occasional sound of rustling leaves and chirping birds adding to the natural ambiance.]"
},
{
"from": "gpt",
"value": "Bad. The small object mentioned in the caption that the monkey is holding in its mouth does not appear in the video."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.