video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1529
|
videos/HRA_part0/1529.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed dancer, clad in a spacesuit with a weasel mascot head, performs an energetic dance routine on a stage designed to resemble the lunar surface, complete with craters and rocks. The backdrop displays a large, realistic moon, adding to the illusion. The performer's movements are lively and expressive, capturing the essence of joyful celebration against the stark, textured lunar landscape. The spacesuit features reflective patches that catch the stage lights, enhancing the visual spectacle, while the weasel mascot head adds a whimsical touch to the performance.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_3029
|
videos/HRA_part0/3029.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 video shows the nurse holding a watering can, with basically normal movements, but there is some lack of coordination."
}
] |
seed46_2417
|
videos/HRA_part2/2417.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, golden cheetah crawls under a low-hanging, silver photon sail, its eyes fixated ahead, muscles rippling beneath its spotted coat, set against a backdrop of a futuristic, metallic landscape. The sail, towering above, reflects beams of sunlight, creating an ethereal glow around the big cat. The cheetah, with its distinctive black tear markings and piercing green eyes, moves gracefully, its body positioned low to the ground, as if stalking prey, while the sail's advanced technology hints at a world beyond nature.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's body is twisted, its head is twisted, its paws are twisted, and its legs are twisted."
}
] |
seed44_270
|
videos/HRA_part1/270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, wearing a red bandana, black leather jacket, and dark jeans, walks through an abandoned mine with caution. He carries a vintage guitar case, adding to his rugged, artistic persona. The mine, filled with debris and old machinery, provides a stark, industrial backdrop. The musician's confident stride and the detailed textures of the mine walls and floor convey a sense of exploration and mystery. As he moves deeper into the mine, the dim lighting highlights his silhouette, creating a dramatic effect. Throughout the video, the focus remains on the musician's journey, emphasizing his presence and the unique setting.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks slightly unsmoothly, with slightly uncoordinated movements."
}
] |
seed42_3197
|
videos/HRA_part0/3197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gracefully over a vast, shimmering ocean, its wings spread wide against a backdrop of rolling clouds and a cerulean sky. The bird's white plumage is highlighted by the golden rays of the sun, casting a serene glow over the scene. As it glides effortlessly, its keen eyes scan the waters below for signs of prey, demonstrating the harmony between creature and environment. The albatross then swoops down, its silhouette framed by the sun, before rising back into the heavens, embodying the spirit of freedom and the majesty of nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2669
|
videos/HRA_part1/2669.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a traditional conical hat and a checkered shirt walks through a lush, green landscape, holding a walking stick in his right hand. Accompanying him is a small monkey perched on his left shoulder, playfully interacting with the farmer as they stroll together. The scene is set in a tropical environment, with vibrant vegetation surrounding them and the warm sunlight filtering through the leaves, casting dappled shadows on the ground. The farmer and the monkey continue their leisurely walk, enjoying each other's company amidst the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's movements in the video are slightly unsmooth."
}
] |
seed42_1746
|
videos/HRA_part0/1746.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, covered in shaggy brown fur, is seen swimming in a vast, ancient lake, its large body creating ripples on the water's surface. The mammoth, with distinctive tusks and small ears, moves through the water with surprising grace, its trunk held high above the waterline like a snorkel. The scene is set against a backdrop of lush, green vegetation and towering, majestic mountains in the distance, capturing the essence of a bygone era when these magnificent creatures roamed the earth.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1968
|
videos/HRA_part0/1968.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone coyote, characterized by its brown and gray fur, alert ears, and a bushy tail, traverses the lush rainforest floor. It walks purposefully among the vibrant green foliage, moss-covered logs, and fallen branches, creating a path through the dense undergrowth. The scene is set in a temperate rainforest, where the air is misty and moist, enhancing the rich greens and browns of the environment. The coyote's journey is filled with the sounds of dripping water and rustling leaves, as it explores this verdant, wet habitat.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the wolf in the video are incomplete, the ears are problematic, and the tail is too long."
}
] |
seed44_1208
|
videos/HRA_part1/1208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meticulously crafted aquarium filled with vibrant green aquatic plants, a ghost shrimp, nearly transparent with faint blue-gray veins, clings to a piece of driftwood. Its delicate antennae wave gently in the water current, and its legs grip the wood securely. Nearby, a stone arch adds to the scenery, while the shrimp's see-through body allows a glimpse of its internal organs. The shrimp's translucent exoskeleton and the lush underwater environment create a captivating scene, enhanced by the play of light and shadow in the tank.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2244
|
videos/HRA_part1/2244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 peaceful woodland setting, a small, curious badger is shown gently caressing the nose of another badger, likely its mate, with its forepaw, conveying a tender moment of connection between the two creatures. The scene is illuminated by a soft, golden light filtering through the trees, casting a warm glow on the badgers as they engage in this intimate gesture. Their fur is depicted in rich, earthy tones, and the surrounding foliage provides a lush, natural backdrop that enhances the serene atmosphere of this unique encounter.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2964
|
videos/HRA_part1/2964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful female cashier, wearing a green apron over a gray sweater and black pants, stands on a ladder cleaning the gutters of a small, wooden house during autumn. She has pulled back her long, dark brown hair into a bun. The scene is set in a backyard with lush green grass, and there are trees with yellow leaves in the background. The house features a red front door, a green window frame, and a roof with brown shingles. The woman uses a gloved hand to scoop out debris from the gutters, showcasing her determination and hard work.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1363
|
videos/HRA_part2/1363.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling hospital corridor, a seasoned doctor wearing a white coat and stethoscope around his neck deftly catches a medical file tossed to him by a passing colleague. The walls are painted a calming blue, and the floor is a clean, shiny tile. The doctor, with a confident smile, acknowledges the gesture before continuing on his way, underscoring the seamless teamwork and expertise in a high-stakes environment. The scene captures the essence of medical professionals working together efficiently amidst the challenges of a healthcare setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the arms are twisted, and the legs are contorted."
}
] |
seed42_10
|
videos/HRA_part0/10.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent peacock, resplendent in its vivid plumage, stands majestically in a lush garden setting. Its iridescent feathers shimmer in shades of blue, green, and gold, catching the sunlight in a dazzling display. The bird's piercing eyes and regal posture convey an air of confidence and grace. In the background, verdant foliage and blooming flowers provide a vibrant contrast to the peacock's striking appearance, creating a harmonious scene of natural beauty. The peacock's tail feathers fan out slightly, hinting at the potential for a full, spectacular spread, captivating the viewer with its exotic allure.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2211
|
videos/HRA_part2/2211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 filled with vibrant greenery and ancient flora, a colossal woolly mammoth tenderly caresses another smaller mammoth with its trunk, showcasing a rare, intimate moment between these majestic creatures. The larger mammoth, adorned with thick, shaggy fur and imposing tusks, gently touches the younger one, whose eyes reflect curiosity and trust. The backdrop features a dense forest, with sunlight filtering through the canopy, casting dappled shadows on the ground, highlighting the tenderness and connection shared between the two mammoths.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's movements in the video are not smooth."
}
] |
seed46_1425
|
videos/HRA_part2/1425.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint town with brick-paved streets and Victorian-style buildings, a uniformed police officer stands watch over a community swimming pool filled with clear, blue water. The officer, clad in a crisp blue uniform, cap, and sunglasses, leans against a wooden fence, observing the swimmers. Children play joyfully in the shallow end, splashing each other, while adults lounge on deck chairs under colorful umbrellas. The scene is framed by lush greenery and the charming town in the background, creating a peaceful and idyllic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1372
|
videos/HRA_part1/1372.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a patterned blue dress and a white apron over it, stands against the lush greenery of a botanical garden, holding her apron's lower edge. Moments later, she leaps into the air with a joyful expression, surrounded by vibrant green foliage and blooming flowers, with sunlight filtering through the trees. Her attire remains unchanged, consisting of a blue floral-print dress and a white apron, as she jumps in a patch of sunlight, with the vibrant garden providing a lively contrast to her figure.]"
},
{
"from": "gpt",
"value": "Bad. The nurse in the video has missing limbs and facial defects."
}
] |
seed46_2643
|
videos/HRA_part2/2643.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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-themed setting, a chef wearing a white uniform and a red bandana stands out against the metallic walls of what appears to be a bank interior. He walks purposefully, holding a large, clear bag filled with currency, suggesting a daring robbery. The chef's attire, which includes a white chef's jacket, black pants, and a red bandana, contrasts sharply with the cold, metallic environment. The scene is set in a space bank with curved, silver walls and a floor covered in scattered bills, as the chef strides away, his unique occupation and bold actions creating a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_3176
|
videos/HRA_part0/3176.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 video shows the doctor standing in the command center of a starship's bridge, leaping into the air, with very discontinuous and jerky movements, and sudden changes in the limbs."
}
] |
seed42_2845
|
videos/HRA_part0/2845.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Amid the lush greenery of a tropical rainforest, twin toddlers, a boy and a girl, crawl on a mossy rock near a cascading waterfall, their clothing soaked from the water. The boy wears a red shirt and gray shorts, while the girl is dressed in a pink top and yellow shorts, both sporting wide smiles as they explore their watery surroundings. Their crawling movements contrast with the powerful rush of the waterfall, creating a dynamic scene of innocence and nature's grandeur. The camera captures this intimate moment, focusing on the children's expressions of wonder and joy as they interact with the natural world around them.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1622
|
videos/HRA_part0/1622.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stark contrast of concepts, the scene begins with a majestic buffalo standing solitary in a vast, arid savanna under a clear blue sky, the landscape stretching out to distant mountains. Suddenly, the focus shifts to a cosmic illustration of a black hole, its singularity depicted as a swirling vortex of stars and galaxies being pulled into the abyss, emphasizing the immense gravitational pull. The scene then transitions to a visual metaphor of 'wiping,' showing a clean slate or a blank page, symbolizing the erasure or resetting of information, akin to the theoretical concept of information loss in a black hole scenario. Throughout, the buffalo, the black hole, and the wiping action are portrayed sequentially rather than interacting, due to the inherent incompatibility of these elements in a physical sense.]"
},
{
"from": "gpt",
"value": "Normal. No scene of a buffalo standing on the vast and arid grassland was generated."
}
] |
seed46_2263
|
videos/HRA_part2/2263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, complete with a receding hairline and glasses, meticulously irons his shirt in a well-lit room. Dressed in a white button-down shirt, black pants, and black shoes, he focuses intently on his task. He then checks the collar of the shirt, which is already neatly pressed, before continuing to iron. Next, he carefully examines the sleeve, ensuring it is wrinkle-free, his attire reflecting professionalism. Finally, he pauses to adjust his glasses, revealing a wedding ring on his finger, all while maintaining a serious demeanor in the midst of his daily routine.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_252
|
videos/HRA_part1/252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 extraordinary scene unfolds where a young elephant, covered in dust and dirt, crawls through a lush vineyard at sunset. Its trunk occasionally touches the soil, and it wears a simple rope around its neck. The elephant is surrounded by rows of green grapevines, with a wooden fence and a small, distant house set against a purple sky. The camera captures the animal from various angles, emphasizing its unique behavior in an unexpected environment, all bathed in the warm glow of twilight.]"
},
{
"from": "gpt",
"value": "Normal. The elephant in the video is not wearing a rope."
}
] |
seed44_1079
|
videos/HRA_part1/1079.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird's eyes are sharp and alert, observing its surroundings with an almost human-like curiosity. The bark of the tree it rests on is textured and dark, contrasting against the lighter shades of green leaves that surround it. In the background, the forest is alive with the sounds of nature; other birds calling, leaves rustling in the breeze, and the distant murmur of a stream. The crow, a symbol of intelligence and adaptability, stands proud and solitary, a master of its domain.]"
},
{
"from": "gpt",
"value": "Good. The crow's movements in the video are basically normal and smooth."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged 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": "Bad. The person's head, arms, and legs are distorted in the video, as well as the buffalo's head and legs."
}
] |
seed44_3004
|
videos/HRA_part1/3004.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, wearing a dark suit with a crisp white shirt and maroon tie, stands in a modern kitchen with gray cabinets and countertops. He attentively loads dishes into a high-end stainless steel dishwasher, demonstrating domestic skills alongside his professional demeanor. His attire, complete with a tailored jacket and neatly folded sleeves, contrasts with the mundane household task, creating an intriguing juxtaposition of professional and personal life. Throughout the scene, the lawyer's focused expression and meticulous movements highlight his commitment to detail, whether in the courtroom or at home.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands appear deformed, and the dishwasher is also deformed."
}
] |
seed42_2710
|
videos/HRA_part0/2710.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, resembling Colin Farrell, is seen walking through a dense forest with tall trees, wearing a brown jacket, jeans, and boots. Suddenly, the scene changes to reveal a prehistoric setting, where the actor now finds himself casually strolling beside a woolly mammoth. Both the actor and the mammoth continue their leisurely walk together, with the mammoth's massive frame towering over the actor, who appears unfazed by the extraordinary situation. They meander through the ancient landscape, surrounded by lush vegetation and underbrush, creating a surreal juxtaposition of eras and species.]"
},
{
"from": "gpt",
"value": "Bad. The actor's walking movements are not very continuous, there is a lack of coordination; the long-haired elephant's walking movements are not very noticeable, the movements are basically normal."
}
] |
seed42_103
|
videos/HRA_part0/103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, donning a brown jacket and khaki pants, stands at a modern bus stop, gently caressing the sleek metal pole, seemingly finding comfort in its solid presence. His eyes are closed, lost in thought, as the urban landscape hums around him. The bus stop is designed with clean lines and glass panels, offering a glimpse into the daily life of the city. Passersby glance curiously at the engineer, his connection to the inanimate object a stark contrast to the hurried pace of the surroundings. The scene captures a rare moment of intimacy between a person and the urban infrastructure they interact with daily.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2334
|
videos/HRA_part0/2334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, dressed in a casual red jacket and dark pants, is seen running along a scenic harbor, the sunlight reflecting off the water. She runs with determination, passing by a variety of ships docked in the harbor, from small sailboats to large cargo vessels. Her movement is fluid and purposeful, her gaze fixed ahead, indicating her focus and drive. The harbor's activity provides a dynamic backdrop, with seagulls flying overhead and the sounds of the bustling waterway adding to the atmosphere. Despite the surroundings, the teacher maintains her pace, her stride strong and consistent as she continues her run along the harbor's edge.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's legs and arms show abnormal deformities when running."
}
] |
seed44_2835
|
videos/HRA_part1/2835.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet tender scene, a large brown bear gently caresses a smaller, lighter-brown bear against the backdrop of a vast savanna landscape. The two bears sit on the golden grass, under a clear blue sky dotted with a few white clouds. The big bear has its arm around the smaller one, while the other paw is softly stroking the smaller bear's head. Both bears wear collars, indicating they might be part of a conservation program. This heartwarming interaction unfolds in a protected area of the savanna, where wildlife coexists in harmony.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the brown bear's head and paws in the video has problems."
}
] |
seed42_2272
|
videos/HRA_part0/2272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, rakes leaves in a community garden, his gold nametag gleaming under the sunlight. He pauses to smile warmly at the camera, his friendly demeanor evident. Wearing a dark blue police uniform complete with a name badge and a cap, he continues raking, surrounded by piles of autumn leaves in various shades of orange, red, and brown. The video closes with him raking diligently, highlighting the unexpected sight of a law enforcement officer engaging in a domestic chore, fostering a sense of community and service.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2260
|
videos/HRA_part2/2260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, dressed as a waiter in a crisp white shirt, black vest, and striped bow tie, crawls across a wooden floor. The room is dimly lit, with a large, elegant chandelier hanging above. The badger moves toward a grand dining table set with fine china and silverware, passing by a towering bookshelf filled with leather-bound books. The camera captures the badger's earnest expression and the intricate details of its costume, all set against the backdrop of a lavishly decorated room.]"
},
{
"from": "gpt",
"value": "Bad. The badger's crawling movements can be clearly seen in the video, but the movements are not very smooth and appear uncoordinated."
}
] |
seed46_1089
|
videos/HRA_part2/1089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit museum hall, a life-sized jaguar statue leaps across the space, seemingly frozen in mid-air as it jumps from one side to the other. The museum is filled with exhibits of historical artifacts, including ancient pottery and weaponry displayed in glass cases along the walls. The jaguar, crafted with intricate details and positioned mid-jump, captures the animal's agility and power, making it the focal point of the room. Its leap is so vividly portrayed that it appears ready to pounce at any moment, adding a dynamic element to the otherwise static environment.]"
},
{
"from": "gpt",
"value": "Bad. The claws and face of the statue in the video have generation issues."
}
] |
seed46_2943
|
videos/HRA_part2/2943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its dark brown coat and long, curved horns, is captured mid-stride as it sprints across a rocky terrain. The detailed shot focuses on the ibex's powerful legs and hooves, which grip the stone surface, propelling it forward with agility and strength. The ibex's body is outlined against a backdrop of rugged mountains and a clear blue sky, emphasizing its natural habitat. The video highlights the animal's endurance and speed as it navigates the challenging landscape with ease.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the argali's face and legs distorted."
}
] |
seed46_215
|
videos/HRA_part2/215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a helmet, gently caresses a tiny, spiky hedgehog with a gloved hand, their eyes tenderly locked in a heartwarming connection. The scene is set against a backdrop of a partially extinguished fire, with billowing smoke and the remnants of flames, highlighting the contrast between the rough exterior of the firefighter and the delicate nature of the animal. The hedgehog, seemingly unharmed, nestles into the palm of the firefighter's hand, creating a poignant moment of compassion amidst the chaos.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions a firefighter gently petting a hedgehog, which does not appear in the video."
}
] |
seed42_1699
|
videos/HRA_part0/1699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative writer, donning a blue button-down shirt and khaki pants, rearranges furniture in a cozy room with wooden floors and a fireplace, aiming to find inspiration. He thoughtfully adjusts a brown leather sofa, placing it at an angle near the hearth, with a glass coffee table in front. Next, he moves a wooden chair with a green cushion to the right side of the sofa, creating a conversational space. Then, he positions a tall bookshelf behind the chair, filled with books and trinkets, adding character to the room. Lastly, he places a small wooden desk with a typewriter next to the window, basking in natural light, perfect for writing, all while maintaining the warm, inviting atmosphere of the space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2877
|
videos/HRA_part2/2877.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a black leather jacket, gray jeans, and a black beret, stands on a lush green hillside under a clear blue sky, engaging in an eccentric dance. In the foreground, a majestic leopard, its golden eyes locked on the director, prowls among the tall grass, adding a sense of wild energy to the scene. The director's animated movements contrast with the leopard's watchful stillness, creating a captivating interplay between human creativity and untamed nature.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1599
|
videos/HRA_part1/1599.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room painted a calming shade of blue, two young children, a boy and a girl, both wearing pajamas, sit on a large bed with white sheets. The girl, with her blonde hair in pigtails and clad in pink pajamas, cries with her mouth wide open, tears streaming down her cheeks, her hands covering her face. Beside her, the boy, wearing blue pajamas, leans forward with concern, placing a comforting hand on her back, his brown hair tousled and his eyes filled with empathy, offering a silent support amidst their shared distress.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_2414
|
videos/HRA_part1/2414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant orchard filled with apple trees heavy with ripe fruit, a large brown bear stands on its hind legs, its shaggy fur glistening in the dappled sunlight. It reaches up with a massive paw, gently swiping at the low-hanging branches laden with apples. The bear then lowers itself to all fours, picking up an apple it has dislodged, and wipes it carefully on its thick fur before taking a hearty bite, savoring the sweet, juicy flavor amidst the peaceful surroundings of the orchard.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1852
|
videos/HRA_part1/1852.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female cashier, with a casual hairstyle and wearing a dark green jacket over a gray t-shirt, leans against a white wall with a wooden panel. She holds a book titled \"The Great Gatsby\" by F. Scott Fitzgerald, reading it intently during a break. The scene is set in a grocery store aisle, with shelves stocked with products like canned goods and boxes of cereal visible in the background. The cashier's relaxed posture and focused gaze on the classic novel convey a sense of peace and personal time amidst her work environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1780
|
videos/HRA_part2/1780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 friendly female cashier with brown hair pulled into a bun, wearing a green apron over a striped shirt, leans over to gently caress a koala standing on its hind legs on the counter. The koala, with its soft gray fur and curious expression, reaches up with its paw toward the cashier's face, creating a heartwarming interaction between the two. Behind the counter, a cash register and various retail items can be seen, adding to the unique setting of this tender moment.]"
},
{
"from": "gpt",
"value": "Bad. No cash register and retail products were generated."
}
] |
seed46_2261
|
videos/HRA_part2/2261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an array of colorful fish. The grouper, with its distinctive spotted pattern and wide, flat head, explores its surroundings with a slow, methodical motion. Its eyes, fixed on the camera, seem to convey intelligence and awareness. The water is crystal clear, allowing every detail of the grouper's body and the intricate ecosystem it inhabits to be visible. The scene is illuminated by natural sunlight filtering through the surface, casting dappled light on the sandy seabed and the marine life above.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the mouth and fins of the grouper in the video has problems."
}
] |
seed44_1841
|
videos/HRA_part1/1841.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna stretching into the horizon, a group of three people, two men and a woman, wearing beige safari outfits and wide-brimmed hats, walk side by side, their shadows cast long by the afternoon sun. They traverse the grassy landscape dotted with scattered acacia trees, their journey unfolding under a clear blue sky. Alongside them, a herd of gazelles grazes peacefully, the animals' lithe forms and delicate movements contrasting with the humans' steady pace. The people occasionally glance at the wildlife, their expressions a mix of wonder and respect for the natural world they explore together.]"
},
{
"from": "gpt",
"value": "Normal. The person's legs show deformities and abnormalities."
}
] |
seed44_2642
|
videos/HRA_part1/2642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 hamster, with its distinctively furry cheeks and nose, energetically runs inside a clear plastic exercise ball. It scampers across a room filled with everyday objects like furniture and potted plants, providing a unique perspective on a typical living space. The hamster's movement is fluid and rapid, highlighting its determination and playful nature as it explores its surroundings within the safety of the transparent sphere.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's paws are missing in the video, and the body and face are generated blurry."
}
] |
seed44_1860
|
videos/HRA_part1/1860.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sun-dappled forest, a small, bushy-tailed squirrel gently caresses a smooth, brown egg nestled among vibrant green moss on a flat rock. The squirrel, with its soft, gray fur and alert eyes, tenderly touches the egg with its tiny paws, creating a heartwarming scene of unexpected care. The lush surroundings include tall trees, filtered sunlight, and a variety of foliage, adding depth and texture to the intimate moment shared between the squirrel and the fragile egg.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2383
|
videos/HRA_part0/2383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A thoughtful writer, clad in a brown jacket and blue jeans, traverses the sunlit chaparral landscape, his attire complemented by brown shoes and a backpack. He pauses to gaze into the distance, the vast expanse of shrubland stretching before him. Continuing his journey, he walks among the low-lying vegetation, the golden grasses swaying gently in the breeze. Occasionally, he stops to jot down notes, his focus intense, capturing the essence of his surroundings in his leather-bound journal. Throughout his walk, the chaparral scenery provides a serene backdrop, punctuated by the rustling of leaves and the distant call of birds.]"
},
{
"from": "gpt",
"value": "Normal. The writer's fingers and feet are missing in the video, the face is generated blurry, and there are issues with the legs."
}
] |
seed46_1758
|
videos/HRA_part2/1758.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, middle-aged teacher waves energetically with both hands from a classroom filled with colorful decorations, wearing a bright yellow sweater over a patterned dress, against a backdrop of windows showing a clear blue sky, conveying a sense of warmth and welcome. She stands in front of a whiteboard adorned with educational posters and student artwork, her smile and enthusiastic gesture creating an inviting atmosphere for students. The room is bathed in natural light, highlighting the teacher's animated expression and the vibrant learning environment.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers and arms in the video are missing."
}
] |
seed42_2880
|
videos/HRA_part0/2880.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a flowing white dress, interacts with a majestic lion in a surreal setting, emphasizing their connection. She crawls on a surface covered with lush green grass, facing the lion with a relaxed demeanor. The lion, also crawling, responds to her with curiosity, its golden eyes locked onto hers. Both the woman and the lion are framed by the vibrant greenery of their surroundings, highlighting the unusual yet peaceful encounter between human and beast.]"
},
{
"from": "gpt",
"value": "Normal. The lion's face is distorted in the video."
}
] |
seed42_1942
|
videos/HRA_part0/1942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male chef, donning a traditional white chef's uniform with a name tag reading \"Chef Tyler,\" sits at a wooden table in a rustic, candlelit dining room. He savors a spoonful of his signature dish, a creamy risotto, with eyes closed in blissful concentration. His neatly trimmed beard and mustache, along with short brown hair, add to his distinguished appearance. Behind him, a bustling restaurant kitchen is visible through an open doorway, offering a glimpse into the energetic culinary environment. Throughout the scene, Chef Tyler continues to enjoy his meal, occasionally glancing up with a satisfied smile, embodying the essence of a passionate and accomplished chef relishing his own creation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_104
|
videos/HRA_part1/104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, wearing a gray jacket and blue jeans, walks through the lush greenery of a botanical garden, surrounded by vibrant flowers and towering trees. They pause to examine a particularly interesting plant, their backpack resting on the ground beside them. The sunlight filters through the leaves overhead, casting dappled shadows on the path. In the background, the serene sound of a nearby fountain can be heard, adding to the peaceful atmosphere of the scene. The student continues on their leisurely stroll, taking in the beauty of nature around them.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_2600
|
videos/HRA_part1/2600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal blend of scenes, a majestic African lion strides powerfully across a vast, barren asteroid, its golden coat contrasting starkly against the monochrome landscape pockmarked with craters. The lion, undeterred by the alien environment, explores the rocky terrain as if it were a savannah, with distant stars and a nebula providing a cosmic backdrop. Nearby, a futuristic mining facility operates diligently, extracting precious resources from the asteroid's surface, emphasizing the juxtaposition of nature and technology in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed44_1683
|
videos/HRA_part1/1683.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow safety vest and black pants, diligently wipes down a control panel in a modern, well-lit power plant. Surrounded by high-tech machinery and screens displaying operational data, he focuses intently on his task, ensuring every surface is clean and free of dust. The environment is pristine, with a sense of order and functionality pervading the space. The janitor's actions are methodical, emphasizing the importance of maintenance in this critical facility.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_2739
|
videos/HRA_part2/2739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, clad in a light blue uniform, gently caresses the fur of a calm, gray wolf sitting beside her, both under the shade of a large tree in a grassy field. The wolf looks up at her with a relaxed demeanor, while she tenderly strokes its head, conveying a sense of mutual trust and peace between human and wild animal. Moments later, she holds the wolf's snout softly, her caring gaze meeting its calm eyes, with the serene natural surroundings enhancing the emotional connection depicted.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2089
|
videos/HRA_part1/2089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 creative blend of scenes, two smiling children, a boy in a blue jacket and a girl in a pink jacket, walk alongside a life-sized zebra puppet, its distinctive black and white stripes vivid against a neutral background. The children hold hands, looking up in wonder, as the zebra puppet, operated by an unseen handler, walks alongside them. Behind them, a large, high-definition screen displays a captivating visualization of dark matter research, featuring swirling galaxies and complex data visualizations, seamlessly merging elements of nature, childhood innocence, and scientific exploration.]"
},
{
"from": "gpt",
"value": "Bad. Did not generate a girl wearing a pink jacket."
}
] |
seed46_3219
|
videos/HRA_part2/3219.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. No obvious issues."
}
] |
seed46_10
|
videos/HRA_part2/10.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent peacock, resplendent in its vivid plumage, stands majestically in a lush garden setting. Its iridescent feathers shimmer in shades of blue, green, and gold, catching the sunlight in a dazzling display. The bird's piercing eyes and regal posture convey an air of confidence and grace. In the background, verdant foliage and blooming flowers provide a vibrant contrast to the peacock's striking appearance, creating a harmonious scene of natural beauty. The peacock's tail feathers fan out slightly, hinting at the potential for a full, spectacular spread, captivating the viewer with its exotic allure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1375
|
videos/HRA_part0/1375.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning close-up of a rainbow trout fills the frame, its vibrant colors and intricate patterns captivating the viewer. The fish, partially submerged in crystal-clear water, showcases its beauty against a backdrop of smooth river stones and lush green vegetation. Its silver scales glisten in the sunlight, while its red and blue stripes stand out against the clear water. The trout's large, expressive eyes and delicate fins add to its charm, making it the undeniable star of the scene. The rippling water around it creates a sense of movement and life, immersing the viewer in the tranquil yet dynamic environment of a freshwater stream.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1253
|
videos/HRA_part2/1253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant scene set within lush wetlands, several figures clad in elaborate costumes dance energetically, their movements synchronized in a captivating performance. The dancers wear colorful outfits adorned with feathers and intricate patterns, their faces painted in festive designs. The backdrop showcases the beauty of the wetlands, with tall reeds swaying gently in the breeze and waterfowl flying overhead. Sunlight filters through the clouds, casting a warm glow on the dancers as they leap and twirl, embodying the spirit of nature in their lively dance.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is severely distorted, the arms are severely twisted, and the legs are severely distorted."
}
] |
seed46_1718
|
videos/HRA_part2/1718.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches on a thin branch, its vibrant plumage of green, blue, and orange feathers catching the sunlight. It has a slender body, a long, pointed tail, and a distinctive, curved beak. The bird's eyes are alert, scanning the surroundings for potential prey. Suddenly, it takes flight, its wings a blur of motion as it darts through the air, chasing after an unsuspecting insect. The scene is set against a backdrop of lush vegetation and clear blue skies, capturing the bird's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Bad. The flapping of the wings can be seen, but the movements are not continuous, there are abrupt changes."
}
] |
seed44_1874
|
videos/HRA_part1/1874.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy blue uniform with a badge and a black belt, runs through a vast meadow filled with lush green grass and vibrant wildflowers. The landscape stretches to the horizon, dotted with distant trees. His expression is one of determination, eyes focused ahead, and he strides with purpose, leaving a faint trail in the dewy grass. The sun, partially obscured by a cloud, casts a soft, golden light over the scene, highlighting the officer's movement as he navigates the uneven terrain, demonstrating commitment and urgency in his duty.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the police running, but the movements are not very smooth and coordinated."
}
] |
seed42_2975
|
videos/HRA_part0/2975.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 NASA jumpsuit walks alongside a curious, friendly bear in a space helmet, both exploring a futuristic space station designed for tourism. The station, filled with advanced technology and panoramic views of the cosmos, offers a unique blend of engineering marvels and extraterrestrial wildlife encounters. The engineer, equipped with tools and a tablet, ensures the safety and functionality of the space station's systems, while the bear, adorned with a custom spacesuit and helmet, roams freely, interacting with visitors and adding an unexpected touch of whimsy to the space tourism experience. Together, they navigate the corridors and observation decks, creating an unforgettable scene of human and animal adaptation to life beyond Earth's atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's head, arms, and hands are distorted in the video, as well as the bear's body, head, feet, and legs."
}
] |
seed44_1020
|
videos/HRA_part1/1020.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, dressed in a navy pea coat, beige trousers, and brown shoes, is gracefully dancing in a large, empty room with polished wooden floors and high ceilings. In the background, a magnificent cat leaps playfully, its silhouette outlined by the warm glow of the rising sun, which streams through a window, casting a soft light on a potted plant. Mercury, visible as a bright star in the twilight sky outside, adds a celestial touch to the scene. The director's dance moves, captured in a series of fluid poses, convey a sense of joy and creative inspiration, while the cat's energetic jumps mirror the director's movements, creating a harmonious connection between the two.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1010
|
videos/HRA_part1/1010.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, dressed in a dark gray jacket and light gray shirt, sits at a desk in a space hotel room, the Earth visible through the window behind him. He wipes the screen of his laptop with a cloth, revealing the reflection of the planet. The room is illuminated by soft, ambient light, giving it a futuristic yet cozy feel. The writer's focused expression and the clean, high-tech environment convey a sense of dedication and precision in his work, all set against the backdrop of the majestic Earth, which fills the large window behind him.]"
},
{
"from": "gpt",
"value": "Good. Basically no obvious problems."
}
] |
seed46_1053
|
videos/HRA_part2/1053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, with its distinctive short tail and tufted ears, strides purposefully across a dry, rocky terrain under the clear blue sky. Its tawny fur, marked with spots and stripes, blends perfectly with the arid environment. The cat's piercing eyes remain alert, scanning the surroundings for potential prey or threats, as it moves with a confident gait, showcasing its natural agility and strength in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated, and there are many extra legs appearing."
}
] |
seed42_249
|
videos/HRA_part0/249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal and imaginative scene, two children, a boy and a girl, are dancing in a whimsical, cartoon-like environment. The girl, with curly red hair, wears a pink dress, while the boy, sporting brown hair, dons a blue shirt. They are accompanied by a friendly, animated coyote who mirrors their dance moves. The backdrop is a scientific laboratory filled with high-tech equipment, where researchers in lab coats are studying dark matter. This unusual juxtaposition of elements creates a captivating and unique visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1516
|
videos/HRA_part1/1516.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 industrious male engineer, wearing a blue button-down shirt and glasses, meticulously irons his clothes in a modestly furnished room with a wooden floor and cream walls. He stands at an ironing board covered with a white cloth, carefully smoothing out wrinkles in a garment. The room is illuminated by natural light from a window behind him, casting a warm glow over the scene. On the wall to his right, a large painting in shades of green adds a splash of color to the otherwise simple space. Beside the window, a desk with a laptop and engineering blueprints hints at his professional life, while a shelf filled with books and a houseplant brings a personal touch to the environment.]"
},
{
"from": "gpt",
"value": "Bad. The head and hands of the person in the video, as well as the iron, were generated incorrectly."
}
] |
seed46_2751
|
videos/HRA_part2/2751.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 street worker in Shanghai, wearing a green vest and holding a broom, gently caresses the concrete surface as he meticulously sweeps the city sidewalk. Behind him, a bustling urban landscape unfolds, with high-rise buildings, neon signs, and the occasional passerby, all set against the backdrop of a vibrant metropolis. The worker's focused gaze and the tender touch of his broom on the pavement convey a sense of care and routine amidst the dynamic energy of Shanghai's streets.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1169
|
videos/HRA_part2/1169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great blue heron, with its signature blue-gray feathers and long, slender legs, stands majestically in the shallow waters of a serene lake. Its sharp, yellow eyes scan the water's surface as it patiently awaits its next meal. Suddenly, the heron strikes with lightning speed, its sharp beak piercing the water to catch a small fish. As it emerges victorious, the heron proudly displays its catch before swallowing it whole. All the while, the calm surroundings of the lake provide a peaceful backdrop, with gentle ripples on the water and the distant silhouette of trees completing the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2850
|
videos/HRA_part2/2850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a blue scrubs top and black pants, stands in a verdant garden filled with lush greenery and colorful flowers. She is engaged in digging a hole with a small spade, her face expressing determination and focus. The sunlight filters through the leaves above, casting dappled shadows on the rich soil beneath her feet. Despite her work, her demeanor conveys a sense of peace and purpose, as if tending to the earth is just another form of care she provides.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video has uncoordinated movements while digging a hole."
}
] |
seed44_1855
|
videos/HRA_part1/1855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bespectacled female doctor in a white lab coat, adorned with colorful pins, dances energetically in a spacious, well-lit room. Her attire includes a vibrant red blouse and stylish glasses, adding to her lively appearance. In her arms, she cradles a relaxed, curious ferret, which seems unperturbed by the dancing. The pair moves in sync, the doctor's joyful expression and the ferret's inquisitive gaze capturing the essence of an unexpected yet delightful moment.]"
},
{
"from": "gpt",
"value": "Bad. The faces of the characters in the video are distorted, as well as their arms, hands, the ferret's body, paws, face, and legs."
}
] |
seed44_1806
|
videos/HRA_part1/1806.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit enclosure, a majestic black panther sits calmly, its piercing eyes gazing intently. It gently caresses a log with its massive paw, adorned with thick, black fur and sharp claws. The panther's regal demeanor is underscored by its relaxed posture and the tender interaction with the wooden surface, set against a backdrop of lush vegetation and a water source, creating a serene atmosphere in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 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 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": "Good. No obvious issues."
}
] |
seed44_1
|
videos/HRA_part1/1.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the golden glow of twilight, a slender, reddish-brown jackal stands out against a sandy desert landscape, its piercing eyes and alert ears capturing the viewer's attention. It begins to move gracefully, its body swaying in a dance-like motion, as if responding to an unheard melody. The jackal's fluid movements are juxtaposed against the stillness of the desert, creating a mesmerizing scene where nature and rhythm intertwine. Its agile form, framed by the warm hues of the setting sun, tells a story of survival and spirit in the vast wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the jackal in the video are missing, the tail is too long, and there are problems with the eyes."
}
] |
seed42_1858
|
videos/HRA_part0/1858.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 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 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": "Good. Basically no problem."
}
] |
seed42_1107
|
videos/HRA_part0/1107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, dreamlike scene, a sleek, golden leopard with piercing green eyes gently caresses a miniature Mars rover replica with its paw, set against a cosmic, starry backdrop. The rover, adorned with intricate details mimicking real-life space exploration vehicles, sits motionless under the tender touch of the majestic feline. This juxtaposition of elements from different worlds - the wild, untamed beauty of the leopard and the marvels of human engineering represented by the rover - creates a captivating, otherworldly narrative.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's movements in the video are basically normal, with slight coordination issues."
}
] |
seed42_2539
|
videos/HRA_part0/2539.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, a young female cashier, dressed in a black apron over a white blouse, serves customers with a warm smile at an outdoor market stall. The background is filled with the vibrant energy of city life, complete with honking cars, pedestrians, and street vendors. Suddenly, the focus changes to a public pool where a group of diverse individuals, including a man in swimming trunks and a woman in a floral-print swimsuit, splash and play in the water. The atmosphere is lively and joyful, with the sounds of laughter and splashing filling the air, offering a stark contrast to the busy urban environment previously depicted.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_3036
|
videos/HRA_part2/3036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 teenage boy wearing a red jacket and khaki pants is sprinting across a grassy field, his gaze fixed ahead with determination. As he runs, a small rabbit enters the frame from the bottom right corner, bounding alongside him. The student acknowledges the rabbit with a brief glance, but both continue their run, the student maintaining his focus and the rabbit keeping pace, against the backdrop of a clear blue sky and distant green hills.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the boy running and the rabbit jumping side by side, but the movements are not continuous and smooth, with noticeable jerks."
}
] |
seed44_3161
|
videos/HRA_part1/3161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with a rugged appearance, wearing a white tank top, beige overalls, and a wide-brimmed straw hat, is seen singing passionately. He stands against the backdrop of a vibrant sunset, with lush green fields stretching into the horizon. His weathered hands hold the microphone as he belts out his song, his eyes closed in intense concentration. The scene is filled with the warm hues of twilight, casting a golden glow on the farmer and the verdant landscape, evoking a sense of peace and harmony with nature.]"
},
{
"from": "gpt",
"value": "Good. The character's movements in the video are basically normal."
}
] |
seed42_1411
|
videos/HRA_part0/1411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene set in a vast, starlit cosmos, a renowned actor, dressed in a flowing white robe, participates in an otherworldly religious ceremony. The celestial setting features an enormous, ethereal bear standing on its hind legs, appearing majestic against the backdrop of distant galaxies. The actor, with a determined look, is seen running alongside the cosmic bear, both moving in unison within the sacred space ritual, their journey illuminated by the glow of nebulae and stars.]"
},
{
"from": "gpt",
"value": "Normal. The actor and the bear's running movements can be seen more clearly, but the continuity is poor."
}
] |
seed46_2237
|
videos/HRA_part2/2237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, majestic tuna fish glides through the crystal-clear waters of the ocean, its sleek silver body cutting through the water with grace and power. The sunlight filters down from the surface above, casting shimmering patterns across the tuna's scales. Schools of smaller fish scatter in its path, the tuna's presence commanding respect in the underwater realm. In the distance, the silhouette of a reef can be seen, adding depth and context to the tuna's aquatic habitat. The video captures the tuna from various angles, showcasing its size and strength as it navigates its natural environment with ease.]"
},
{
"from": "gpt",
"value": "Normal. The video shows too many tuna fins generated, and they are in incorrect positions; the fish mouth is also missing parts."
}
] |
seed44_3165
|
videos/HRA_part1/3165.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 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 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": "Normal. The woman's fingers in the video are deformed, her face is incompletely generated, the brush strokes are slightly distorted, and the buttocks are distorted."
}
] |
seed46_1728
|
videos/HRA_part2/1728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female barista, wearing a gray apron over a black shirt, completes a transaction with a customer at a contemporary coffee shop. The cafe features wooden floors, a glass cooler, and a large digital menu display. After the sale, she turns to prepare a coffee beverage, carefully measuring ingredients into a French press. With practiced movements, she adds hot water from a stainless steel kettle and stirs the mixture. The barista then pours the freshly brewed coffee into a white ceramic cup, adding a touch of foam art on top before presenting it to the customer with a warm smile. Throughout the process, the cafe's modern decor, including high-top tables and minimalist chairs, provides a backdrop to the barista's efficient and skilled routine.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_3150
|
videos/HRA_part2/3150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, possibly his cub, against the backdrop of a lush, green savanna during golden hour. The adult lion, with its voluminous tawny mane, displays affection, while the cub, sporting a lighter coat and smaller stature, responds with innocent playfulness. The heartwarming interaction unfolds under a vast, cloud-dappled sky, with scattered acacia trees and distant mountains completing the serene African landscape. This intimate moment captures the rare display of tenderness and bonding within the lion family, far from the typical fierce and powerful image associated with these animals.]"
},
{
"from": "gpt",
"value": "Normal. The lion's face is distorted, legs are twisted, claws are deformed, and the body is contorted."
}
] |
seed42_2217
|
videos/HRA_part0/2217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed writer, wearing a gray t-shirt, sits at a desk in a modern, minimally decorated room with large windows and a wooden floor, yawning widely as he leans back in his chair. The room is sparsely furnished, featuring a desk lamp and a painting on the wall. As the scene progresses, the yawning writer, now seen from the side, wears a black cap and glasses, revealing more of his appearance. He continues to yawn, appearing tired yet relaxed, as he rests his head on his hand, gazing out the window. Throughout, the setting remains a contemporary space with ample natural light and simple decor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1163
|
videos/HRA_part2/1163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant, freshly-caught salmon, its skin shimmering with hues of silver and pink, glistens under bright lights. The fish, set against a dark, textured background, boasts a rich gradient of colors from deep red to pale orange on its flesh, which is artfully presented with a diagonal cut to reveal its succulent texture. Delicate wisps of smoke rise from the salmon, indicating its recent preparation, while a chef's hand, adorned with a simple wedding band, holds a sharp filleting knife nearby, ready to prepare this exquisite piece of seafood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2929
|
videos/HRA_part1/2929.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown jacket over a striped shirt and khaki pants, performs a surprising leap over a row of yellow school lockers, demonstrating unexpected athleticism. In the next scene, he jumps again, this time over a green garbage can, showcasing his lively spirit. Then, he leaps over a red fire extinguisher mounted on a wall, his movements fluid and agile. Finally, the janitor, still clad in his brown jacket and khakis, clears a hurdle formed by a mop and bucket, his face expressing pure delight in these spontaneous acts of physicality, all within the confines of a school corridor.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's movements in the video are not smooth."
}
] |
seed46_3197
|
videos/HRA_part2/3197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars gracefully over a vast, shimmering ocean, its wings spread wide against a backdrop of rolling clouds and a cerulean sky. The bird's white plumage is highlighted by the golden rays of the sun, casting a serene glow over the scene. As it glides effortlessly, its keen eyes scan the waters below for signs of prey, demonstrating the harmony between creature and environment. The albatross then swoops down, its silhouette framed by the sun, before rising back into the heavens, embodying the spirit of freedom and the majesty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The albatross can be seen soaring in the video, but the movements are very discontinuous and uncoordinated."
}
] |
seed46_1879
|
videos/HRA_part2/1879.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, balding teacher sits slumped at a large wooden desk, surrounded by stacks of books and papers, in a dimly lit room. His glasses have slipped down his nose, and his head rests on a pile of graded exams, indicating exhaustion from late-night grading. The cluttered desk, filled with educational materials, suggests a dedicated educator overwhelmed by his workload. Behind him, a window reveals the glow of streetlights outside, hinting at the late hour. The teacher's weary posture and closed eyes depict a moment of much-needed rest amidst the demands of his profession.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2587
|
videos/HRA_part1/2587.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and whimsical scene, a Bactrian camel with two humps, typically found in desert environments, is seen swimming in crystal-clear waters. The camel, with its shaggy brown coat and large, curious eyes, moves gracefully through the water, its head held high above the surface. The backdrop features lush greenery and palm trees, contrasting the camel's usual habitat. The setting sun casts a warm glow over the landscape, creating a surreal and captivating moment where desert meets sea.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1287
|
videos/HRA_part2/1287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 swift bird, known for its agility, soars against a cloudy sky, its dark silhouette outlined by the bright horizon. It swoops and glides effortlessly, its wings and tail spread wide, navigating the air currents with precision. The bird's streamlined body, adapted for speed, cuts through the sky as it performs acrobatic maneuvers, demonstrating its remarkable flying skills. Against the vast, cloud-filled backdrop, the swift's aerial ballet continues, highlighting its unparalleled aerial prowess and freedom.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2289
|
videos/HRA_part0/2289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, donning a straw hat, a plaid shirt, and denim overalls, is shown exerting effort as he pulls on a rope tied to a stubborn old tractor stuck in a muddy farm field. The farmer's weathered hands grip the rope tightly, his face contorted with determination, while the lush greenery and distant rolling hills provide a picturesque rural setting. The scene highlights the farmer's resilience and hard work against the backdrop of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_31
|
videos/HRA_part2/31.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pufferfish, round and plump, navigates the vibrant coral reef with its intricate patterns and varied marine life, showcasing the wonders of the underwater world. Its body, inflated to twice its normal size, displays a mesmerizing display of geometric shapes in muted tones against the backdrop of the deep blue sea. The fish's small, beady eyes stand out prominently on its distended form, while its fins propel it gracefully through the water, surrounded by an array of colorful corals and other sea creatures. This underwater scene highlights the unique survival mechanism of the pufferfish in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1406
|
videos/HRA_part0/1406.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate writer, donning a dark green blazer over a white shirt, is depicted against a backdrop of space exploration imagery, including astronauts and planets. Initially, she stands pensively, holding a book with both hands, her gaze directed downward. Then, she looks up, her expression shifting to one of determination, as if contemplating the vastness of space. Next, she is shown dancing energetically, her right arm raised, embodying the joy and freedom of movement. Finally, she strikes a confident pose, her left hand resting on her hip, her eyes gazing into the distance, encapsulating the spirit of adventure and creativity in the realm of space exploration.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_2993
|
videos/HRA_part2/2993.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single koala, with endearing dark eyes and a round face, clutches a branch of a eucalyptus tree with its sharp claws, its furry body swaying gently. It lovingly caresses the branch with its paw, displaying affectionate behavior typically seen between mother and joey. The koala's soft, thick fur and distinctive rounded ears are highlighted against the textured bark of the tree, creating a tender and captivating scene in nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1008
|
videos/HRA_part2/1008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and a protective mask, crawls determinedly across a rugged, volcanic landscape under a smoky orange sky, his actions highlighting bravery and urgency. Beside him, a fellow firefighter also crawls, both navigating the harsh terrain with focused intensity. Their mission is underscored by the dramatic setting of an erupting volcano in the background, emphasizing the high stakes and danger they face. Throughout, the two figures crawl resolutely forward, their forms silhouetted against the fiery, chaotic backdrop, symbolizing human resilience against nature's fury.]"
},
{
"from": "gpt",
"value": "Bad. The character's legs in the video are unrealistic, and the hands and head generation are also unreasonable."
}
] |
seed46_2029
|
videos/HRA_part2/2029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a tailored gray suit, stands confidently in a lush green backyard, holding a golden chicken with care. The vibrant green grass complements his attire, while the chicken adds a touch of whimsy. Nearby, a swimming pool glistens under the sunlight, its clear blue water contrasting beautifully with the greenery. The lawyer gently places the chicken on the grass, its feathers gleaming in the sun, before walking towards the pool. He pauses at the edge, contemplating the serene water, creating a juxtaposition between his professional demeanor and the unexpected presence of the chicken in this peaceful setting.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's hands and feet, and the chicken generation have problems; the chicken's head gradually distorts and deforms in the middle frames."
}
] |
seed44_2000
|
videos/HRA_part1/2000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man with salt-and-pepper hair and a neatly trimmed beard speaks passionately, gesturing with his hands to emphasize his points. Dressed in a navy suit with a crisp white shirt and a red tie, he commands attention against a backdrop of city lights and a blurred crowd. His animated expressions and dynamic body language convey the intensity of his conversation, drawing the viewer into the engaging dialogue taking place in this urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth."
}
] |
seed42_294
|
videos/HRA_part0/294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate teacher, donning a red top and black leggings, executes a captivating zero-gravity dance in a spacious, well-lit room. She leaps and twirls effortlessly, mimicking the weightlessness of space, as if defying Earth's gravity. Seamlessly transitioning, she begins running in place, her movements fluid and energetic, demonstrating the illusion of floating while maintaining contact with the ground. Throughout, her expressive face conveys the exhilaration and freedom of movement in a zero-gravity environment.]"
},
{
"from": "gpt",
"value": "Bad. The teacher can be clearly seen dancing in the video, but the movements are very discontinuous, and there are sudden changes in the teacher's limbs."
}
] |
seed46_2043
|
videos/HRA_part2/2043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a gray jacket and dark pants, walks down a clean hallway illuminated by bright overhead lights, holding a small, active gerbil in a transparent plastic ball. The gerbil, running energetically on its wheel inside the ball, seems unfazed by the movement. The janitor navigates around a corner, continuing his journey with the gerbil in tow, the clean environment and well-lit corridor reflecting the diligence of his custodial duties.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's movements in the video are not smooth, and the human actions are not smooth."
}
] |
seed42_2046
|
videos/HRA_part0/2046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a dark green jacket over a gray shirt, tends to laundry in a busy laundromat. Surrounded by rows of washing machines and dryers, he checks the status of a load in a washer, occasionally glancing at the patrons around him. He then moves to a dryer, where he retrieves a bundle of freshly laundered linens, carefully folding them with practiced hands. Amidst the hum of machinery and the scent of detergent, the janitor continues his duties, maintaining order in the bustling environment. Throughout the scene, he remains focused and diligent, his actions highlighting the routine yet essential task of laundry care in a public space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2825
|
videos/HRA_part2/2825.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 arms of the character in the video are twisted, the hands are twisted, the face is distorted, the lion's legs are twisted, and the face is distorted."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.