video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1355
|
videos/HRA_part1/1355.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic tiger, showcasing its striking orange and black stripes, gently caresses a smaller, more docile white tiger cub with its large, padded paw, both set against a lush, green forest backdrop. The adult tiger displays a tender side, its piercing yellow eyes gazing softly at the cub. The cub, with its playful nature, responds by nuzzling into the larger tiger's paw, highlighting the affectionate bond between them. This intimate moment unfolds in a serene environment, with the tigers surrounded by dense foliage and sunlight filtering through the leaves, casting dappled shadows on the scene.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the white tiger's head and paws, as well as the large tiger's head and paws, in the video has issues."
}
] |
seed42_2668
|
videos/HRA_part0/2668.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a white shirt and black vest, crawls across a vibrant boardwalk, his face a mask of determination. Wooden planks stretch out beneath him, dotted with colorful umbrellas and lively beachgoers. The scene is bathed in warm sunlight, casting dramatic shadows from the boardwalk's railings and nearby beachside cafes. The waiter's unusual mode of transport draws curious glances from passersby, creating a surreal and engaging moment against the backdrop of a bustling seaside promenade.]"
},
{
"from": "gpt",
"value": "Normal. The facial features, hands, and feet of the server in the video were generated abnormally."
}
] |
seed44_3006
|
videos/HRA_part1/3006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, green environment, a small brown mouse stands on the edge of a natural pool, surrounded by dense shrubbery and tall grass, creating an intricate network of thickets. The mouse looks intently at the water, its ears perked and body alert. Suddenly, it bravely leaps into the clear, shimmering pool, swimming with surprising agility, its tiny paws propelling it through the water. As it swims, the camera captures the ripples created by its movement, highlighting the contrast between the busy activity of the mouse and the stillness of the thickets surrounding the pool.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1163
|
videos/HRA_part0/1163.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 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 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. Basically correct."
}
] |
seed44_2088
|
videos/HRA_part1/2088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, snow-covered landscape, a group of people in winter gear are seen interacting with a herd of majestic bison. The individuals are wiping snow off the bison's fur, showing care and connection with the animals. Their faces, wrapped warmly in scarves and hats, express determination and compassion. The bison, with their powerful statures and shaggy coats, stand calmly, accepting the attention. The scene is framed by the serene beauty of nature, with snowflakes gently falling and the distant silhouette of trees providing a peaceful backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1965
|
videos/HRA_part1/1965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully against a vivid blue sky, its keen eyes scanning the terrain below for prey. Its compact body, clad in brown and gray plumage, cuts through the air with agility. The bird's hooked beak and sharp talons are prominent as it banks sharply, casting a fleeting shadow on the green landscape. Against the clear, cloudless sky, the sparrowhawk's silhouette is framed by the distant horizon, highlighting its strength and freedom in flight.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2221
|
videos/HRA_part0/2221.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a medium-large raptor with a brown back and contrasting white underparts, soars gracefully over a serene lake at sunset. Its piercing yellow eyes are fixed on the water below, searching for prey. The bird's distinctive head, marked with a dark eye-stripe and a white throat, contrasts strikingly with its dark cap. Its underwings show a mix of white and brown streaks, while its legs dangle beneath it, ready to grasp a fish. The osprey's silhouette is framed by the warm glow of the setting sun, casting a golden hue over the tranquil waters.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2276
|
videos/HRA_part1/2276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 doctor, wearing a grey t-shirt, beige shorts, and a cap, is organizing his spacious garage, which features a white ceiling and walls. The garage is filled with various items, including bicycles, a stroller, storage containers, and a large, open shelving unit containing numerous tools and equipment. The doctor methodically arranges these items, creating a neat and orderly space. As he works, he occasionally pauses to examine specific objects, such as a red bicycle, before continuing his task with purpose and precision. Throughout the process, the garage remains well-lit, highlighting the doctor's meticulous efforts to transform the cluttered area into a well-organized and functional space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1971
|
videos/HRA_part2/1971.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 with short brown hair, wearing a gray shirt, sits at a modern office desk cluttered with electronics and tools, knitting a red scarf with large needles. The focus is on her hands as they deftly manipulate the yarn and needles, while a laptop with coding screensaver and a blueprint of a circuit board are visible in the background. The office space is filled with tech gadgets, books, and papers, highlighting her professional environment, yet she finds time for a personal hobby, creating a vivid red scarf amidst the technical surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's fingers in the video are not fully generated, and there are missing parts in the yarn and needles."
}
] |
seed44_2144
|
videos/HRA_part1/2144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a helmet, stands in an open field, engaging in a whimsical dance with a kangaroo. Both figures are silhouetted against a vibrant orange sunset, suggesting a surreal and unexpected partnership. The firefighter's movements are energetic and joyful, while the kangaroo, standing on its hind legs, appears to mimic the dance steps, adding a touch of humor and surprise to the scene. Throughout the dance, the firefighter's gear and the kangaroo's natural stance create a dynamic interplay of form and motion, set against the dramatic backdrop of the fading light.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_3010
|
videos/HRA_part1/3010.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin stands majestically on a frosty, snow-covered landscape, its sleek black-and-white feathers glistening under the soft, diffused light of an overcast sky. The penguin, sporting a charming yellow beak and webbed feet, looks intently into the distance, seemingly contemplating the vast icy expanse before it. Behind the penguin, the horizon blends seamlessly into a hazy, muted palette of grays and blues, emphasizing the serenity and isolation of the Antarctic environment. As the camera zooms in, we see the fine details of the penguin's feathers, each one uniquely patterned, adding texture and depth to the image. Throughout the scene, the penguin remains the focal point, a proud and captivating figure in the midst of a desolate yet breathtakingly beautiful world.]"
},
{
"from": "gpt",
"value": "Normal. The penguin's eyes and mouth in the video have generation issues."
}
] |
seed44_2969
|
videos/HRA_part1/2969.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, donning a uniform consisting of a blue shirt and black pants, is seen in a pet store setting, gently caressing a hamster with care. The hamster, nestled in the palm of the worker's hand, is calm and seemingly comfortable with the interaction. The scene is set against a backdrop of various pet supplies and cages, creating a familiar environment for animal lovers. The worker's facial expression conveys a sense of tenderness and respect for the small creature, highlighting the bond between humans and pets.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2561
|
videos/HRA_part0/2561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, clad in a dark green jacket, blue jeans, and a beige hat, walks through a dry, rocky landscape, his attention fixed on a hyena in the distance. The hyena, displaying its characteristic spotted coat and large ears, roams freely in the arid environment. The director, holding a megaphone and script, seems to be guiding the action or observing the hyena's natural behavior, capturing the essence of the wild animal in a cinematic exploration. The scene conveys a sense of adventure and creativity as the director integrates the captivating presence of the hyena into his storytelling.]"
},
{
"from": "gpt",
"value": "Bad. The director's face, hands, and feet generation in the video have issues."
}
] |
seed46_2835
|
videos/HRA_part2/2835.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 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 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": "Good. No obvious issues."
}
] |
seed44_1940
|
videos/HRA_part1/1940.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a well-dressed lawyer, wearing a dark suit, finds himself in a courtroom that resembles a jungle environment. Seated at a desk adorned with law books and vines, he attentively wipes a chimpanzee's face, which is sitting calmly beside him. The chimp, looking somewhat bewildered, is wearing a miniature suit and tie, adding to the surreal atmosphere of the scene. The lawyer's serious demeanor contrasts with the absurdity of the situation, creating a unique visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The movements of the lawyer and the chimpanzee in the video are not smooth."
}
] |
seed42_2670
|
videos/HRA_part0/2670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, sits on a wooden crate under a bright blue sky, with scaffolding and building materials in the background. He gently pets a brown and white dog lying on its back, belly-up, on a pile of gravel, showing a tender moment of connection between the worker and the animal. The worker's hands, rough from labor, contrast with the softness of the dog's fur, creating a touching scene of companionship amidst a rugged worksite.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2737
|
videos/HRA_part0/2737.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil, shallow pond surrounded by lush vegetation, a large moose with a wide, flat antler rack stands with its head submerged underwater. As it lifts its head, water droplets cascade down its face. The animal then proceeds to shake its head vigorously from side to side, flinging water off its fur and antlers. Its ears flap dynamically during the shaking motion, and its tongue can be seen hanging out playfully. Throughout the scene, the moose's eyes remain closed, indicating its enjoyment of the refreshing activity.]"
},
{
"from": "gpt",
"value": "Normal. The moose in the video is basically normal, with slightly uncoordinated movements."
}
] |
seed44_1911
|
videos/HRA_part1/1911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bearded man, presumably a writer, sits cross-legged on a lush, grassy surface, wearing a blue denim jacket and dark pants. He gently caresses a small, brown bear, who reciprocates with a loving nuzzle. The bear, adorned with a red bow tie, displays affection towards the man, who smiles warmly. Both are surrounded by a serene, verdant landscape, with the man's writing materials, including a notebook and pen, visible nearby. The scene conveys a tender moment between the writer and the bear, set against a peaceful outdoor backdrop.]"
},
{
"from": "gpt",
"value": "Normal. No pen was generated."
}
] |
seed46_2665
|
videos/HRA_part2/2665.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a futuristic spacesuit, gently caresses a small, feathered chicken on a Mars base camp, surrounded by high-tech equipment and monitors displaying scientific data. The young woman, with her hair tied back in a bun, looks down at the bird with a warm smile, providing a moment of tenderness in the stark, utilitarian environment. The base camp is illuminated by artificial lights, casting a soft glow on the scene, with the red Martian landscape visible through the transparent dome. The student's affectionate gesture towards the chicken offers a sense of comfort and connection in the otherwise alien setting.]"
},
{
"from": "gpt",
"value": "Bad. The student's hand and the chicken's head in the video have generation issues."
}
] |
seed44_1223
|
videos/HRA_part1/1223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet, sunlit forest, a young woman who resembles a cashier from a local store embarks on a hike, dressed in hiking gear that includes a green jacket, khaki pants, and brown boots. She pauses to look at something intriguing in the distance, her hiking backpack visible. Moments later, she is seen walking confidently along the trail, her attire and equipment suggesting a preparedness for the outdoors. Then, she stops to rest, leaning against a tree trunk, her hiking poles propped up beside her, conveying a sense of peaceful contemplation. Finally, she continues her journey, walking away from the camera, her figure framed by the lush greenery and dappled sunlight, embodying the spirit of adventure and nature.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks smoothly, but the movements are uncoordinated."
}
] |
seed46_1536
|
videos/HRA_part2/1536.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous nurse, clad in a blue medical scrub top and black pants, stands in a dramatic pose against a vivid, cloudy sky, with a buffalo charging in the background, creating a striking contrast. Moments later, she is shown running swiftly across a grassy field, the buffalo now galloping alongside her in the distance, both set against a backdrop of lush greenery and distant mountains. The nurse's attire remains consistent throughout, consisting of the blue scrub top, black pants, and white sneakers, while the buffalo's powerful form and the natural landscape provide a dynamic setting for this unique scene.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's limbs in the video are generated disproportionately, the face is blurry, and the buffalo has missing limbs."
}
] |
seed46_3128
|
videos/HRA_part2/3128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a bulletproof vest, climbs an arduous route up a steep, rocky cliff, demonstrating determination and skill. His equipment includes a helmet, harness, and climbing gear attached to his belt, while he uses a carabiner to secure his rope. The scene is set against a rugged landscape with lush greenery and distant mountains, highlighting the officer's physical prowess and commitment to overcoming challenges. The camera captures his focused face, the intricate details of his gear, and the breathtaking scenery, emphasizing the intensity and purpose of his climb.]"
},
{
"from": "gpt",
"value": "Normal. The man's limbs are missing in the video, and there are issues with the facial generation."
}
] |
seed42_2452
|
videos/HRA_part0/2452.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a yellow jacket and black trousers, stands on a glacier, performing maintenance on a piece of equipment. The scene opens with a close-up of his hands, wearing black gloves, carefully wiping ice from a sophisticated device. The vast, icy landscape stretches behind him, with the sun casting a warm glow on the cold environment. As he continues to wipe away the frost, the camera pans out to reveal the enormity of the glacier and the solitude of his task. The engineer's focused expression and the stark beauty of the icy terrain provide a captivating contrast in this high-definition shot.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's action of wiping frost off the precision device with his hand is basically normal, but there is slight awkwardness."
}
] |
seed44_2991
|
videos/HRA_part1/2991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a lush, green meadow, a majestic turkey struts proudly, its vibrant plumage of bronze, green, and copper feathers shimmering in the sunlight. The turkey's head, adorned with fleshy caruncles, bobs with each step it takes on the soft grass. Surrounding the turkey are scattered wildflowers and tall grass, swaying gently in the breeze, creating a picturesque countryside scene. The turkey, undisturbed, continues its regal procession, its wings occasionally flaring out as if presenting its splendid feathers to the viewer. The serene atmosphere is punctuated only by the distant sounds of nature, adding to the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1620
|
videos/HRA_part2/1620.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, wearing a yellow safety vest and blue jeans, sits on the ground in a rural landscape, gently caressing a small, brown hare. The worker, with a brown beard and wearing a dark cap, looks intently at the camera, while holding the hare near his chest. The scene is set against a backdrop of green grass and trees, creating a harmonious connection between the worker and the natural environment. The hare, seemingly unafraid, rests calmly in the worker's hands, highlighting a tender moment of interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Normal. The character's action of petting the wild rabbit in the video is basically normal, with slight awkwardness."
}
] |
seed46_2202
|
videos/HRA_part2/2202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone giraffe runs across an open savanna, its distinctive patterned coat and long legs propelling it forward in a graceful stride. The scene is captured in vibrant detail, with the grassy plains stretching out behind the majestic creature. The sky is a brilliant blue, dotted with fluffy white clouds, providing a stunning contrast to the earthy tones of the giraffe's coat. As it runs, its spots seem to blur, creating a mesmerizing effect that highlights the beauty and power of this remarkable animal.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed46_2871
|
videos/HRA_part2/2871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an upscale restaurant, a waiter, dressed in a black suit with a white shirt, black tie, and a pocket square, gently caresses a small, live vole on a pristine white tablecloth. The scene is set against a backdrop of expensive cutlery, crystal glasses, and fine china. The waiter's facial expression conveys a sense of care and tenderness, while the vole appears calm and unafraid. The room is softly lit, casting warm shadows on the walls adorned with elegant paintings and tapestries. This unusual interaction unfolds in slow motion, capturing every detail of the waiter's delicate touch and the vole's relaxed demeanor.]"
},
{
"from": "gpt",
"value": "Normal. The server's action of petting the mouse in the video is not smooth and coordinated."
}
] |
seed46_1902
|
videos/HRA_part2/1902.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic child, donning a vibrant yellow shirt and dark blue jeans, is captured in high definition as they dance with uninhibited joy on a wooden stage. The stage is adorned with a colorful backdrop of balloons in various shades of red, green, and blue, creating a festive atmosphere. The child's face is illuminated by stage lights, highlighting their expressions of pure delight. Their energetic movements fill the frame, conveying the infectious spirit of youthful exuberance against the backdrop of the elaborately decorated stage.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, twisted hands, and twisted legs."
}
] |
seed42_2447
|
videos/HRA_part0/2447.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a gorilla wearing an astronaut suit stands before a massive spaceship, its textured surface reflecting the alien landscape. The gorilla looks up at the ship with curiosity and determination, ready to embark on a journey through interstellar space. Suddenly, the scene changes to show the gorilla swimming underwater, its powerful arms propelling it forward through crystal clear water, surrounded by colorful fish and vibrant coral reefs. The contrast between the futuristic space travel and the natural beauty of the underwater world highlights the versatility and adaptability of this extraordinary creature.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and face generation of the gorilla in the video have problems."
}
] |
seed44_1693
|
videos/HRA_part1/1693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful red fox, standing on its hind legs in a grassy meadow under a twilight sky, wears a green bow tie and a brown top hat, adding a whimsical touch to the scene. It dances energetically, with the focus on its expressive face, showing pure joy and playfulness. The fox continues to dance, now surrounded by a group of admiring woodland creatures, including rabbits, squirrels, and birds, all watching in delight from the edge of a dense forest. The fox performs a final dance move, leaping into the air with its front paws raised, against the backdrop of the setting sun, casting a warm golden glow over the entire meadow.]"
},
{
"from": "gpt",
"value": "Normal. The red fox's movements in the video are not smooth."
}
] |
seed46_2115
|
videos/HRA_part2/2115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, donning a brown leather jacket, a gray t-shirt, and jeans, stands against a dark background, holding a megaphone and gesturing with his other hand. Moments later, a wolf, possibly a Timber Wolf, is seen running in a dense forest, its powerful legs propelling it forward with grace and speed. The wolf's fur is a mix of grays and browns, blending seamlessly with the underbrush. The scene transitions to show the wolf's perspective, capturing the blur of trees and foliage as it dashes through the woodland, highlighting its agility and strength in motion.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the scene of the director holding a loudspeaker and making gestures."
}
] |
seed44_2590
|
videos/HRA_part1/2590.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, dressed in a costume reminiscent of a prehistoric mammoth, crawls across a barren, rocky terrain under a desolate, overcast sky. The actor's face is obscured by the mammoth headpiece, which features large, curved tusks and shaggy, gray-brown fur. The costume also includes a body suit with similar fur, giving the impression of a mammoth's bulk. The landscape is dotted with sparse vegetation, adding to the prehistoric feel. As the actor crawls, the camera captures the struggle and determination in the movements, conveying a sense of survival in a harsh environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1925
|
videos/HRA_part2/1925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature male silverback gorilla, marked by a prominent sagittal crest and large, powerful body, crawls through dense, lush vegetation in a misty, mountainous habitat. His dark fur stands out against the vibrant greenery, and his expressive face, complete with attentive eyes and a strong jawline, conveys a sense of intelligence and strength. The scene is set in a protected wildlife reserve, where the gorilla moves purposefully through the undergrowth, highlighting the beauty and resilience of these endangered primates in their natural environment.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the gorilla in the video are missing, and there is an issue with the mouth generation."
}
] |
seed44_2568
|
videos/HRA_part1/2568.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, clad in a red jacket and black pants, races through a city park surrounded by towering skyscrapers, lush greenery, and a clear blue sky. The panda, sporting sunglasses and a determined look, sprints past urban landmarks, including a towering glass building and a bridge. In another scene, the panda leaps over a log, its athletic prowess on full display against the cityscape backdrop. Finally, it continues its run, moving right to left across the screen, with the vibrant city as its dynamic setting.]"
},
{
"from": "gpt",
"value": "Bad. The panda's face and limbs in the video were generated abnormally."
}
] |
seed46_1822
|
videos/HRA_part2/1822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, complete with a stethoscope around his neck and wearing a white lab coat over a blue button-down shirt and khaki pants, sits by a serene lake, holding a fishing rod. The peaceful scene is set against a backdrop of lush greenery and a clear blue sky, with the doctor's attire and occupation contrasting with the tranquil activity of fishing. As he casts his line into the water, the camera captures the reflective surface of the lake and the doctor's focused yet relaxed demeanor, highlighting the juxtaposition between his professional life and his leisurely pursuit.]"
},
{
"from": "gpt",
"value": "Normal. The character's face in the video is slightly distorted, and the hands are twisted."
}
] |
seed42_1549
|
videos/HRA_part0/1549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man named Jay, wearing a black t-shirt, blue jeans, and a silver wristwatch, stands against a plain gray backdrop. Initially, he looks intently at the camera, then breaks into a warm smile. Moments later, he playfully winks, showcasing his friendly demeanor. Finally, Jay is seen laughing wholeheartedly, his joyous spirit captured in high definition, all the while maintaining the simple outfit of a black top, blue denim, and a gleaming watch against the unadorned setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1182
|
videos/HRA_part2/1182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 herd of African buffalo, distinguished by their massive curved horns and sturdy builds, gallop across a sunlit savanna, stirring up clouds of dust in their wake. The lead buffalo, a dominant male, charges ahead with determination, followed closely by the rest of the herd. They run through tall grass, which sways in the breeze, creating a dramatic contrast against the clear blue sky. The action is captured in high definition, focusing on the power and grace of these magnificent animals as they thunder across the landscape.]"
},
{
"from": "gpt",
"value": "Bad. The buffalo's head and legs are twisted in the video."
}
] |
seed46_328
|
videos/HRA_part2/328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 temperate deciduous forest, a professional lawyer, dressed in a gray suit and carrying a leather briefcase, wipes his brow as he pauses from his hike. The lush green forest, filled with tall trees and sunlight filtering through the leaves, provides a serene backdrop. The lawyer, wearing a gray blazer, button-down shirt, and khaki pants, is shown wiping his face with a handkerchief, revealing a moment of respite during his outdoor excursion. The peaceful atmosphere of the forest is highlighted by the dappled sunlight and the vibrant greenery surrounding the well-dressed man.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1487
|
videos/HRA_part0/1487.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 realistic zebra, complete with black and white stripes, finds itself crawling under a barrier typically found at train stations. The striped animal moves slowly and carefully, its body almost touching the ground, as it navigates beneath the yellow and black-striped barrier. The train station's typical features, such as tracks, platforms, and overhead signs, are visible in the background, adding to the surreal nature of the scene. The zebra's unusual behavior in this urban setting creates a striking and memorable image.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_297
|
videos/HRA_part0/297.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the lush, green undergrowth of a temperate rainforest, a wildlife worker, clad in a khaki shirt and hat, carefully crawls on his hands and knees, examining the rich flora. Nearby, a chimpanzee, adapted to this cooler, wetter habitat, curiously observes the human from behind a moss-covered tree trunk, its fur darker due to the climate. The scene captures the unique bond between the worker, dedicated to studying and preserving this ecosystem, and the chimpanzee, a rare sight in temperate rainforests, both interacting within the dense, verdant surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the wildlife worker and the gorilla in the video are slightly unsmooth."
}
] |
seed44_1403
|
videos/HRA_part1/1403.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a grey hoodie, beige khakis, and brown boots, runs across a grassy field under a clear blue sky, holding a remote control. Nearby, a squirrel scampers along the ground, its bushy tail bouncing. In the distance, an AI-piloted drone hovers, capturing aerial footage. The engineer occasionally glances upwards, monitoring the drone's position as it flies, while the squirrel continues its journey among the trees. The scene is set in a suburban park, with houses visible in the background, highlighting the integration of technology and nature in everyday life.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1305
|
videos/HRA_part2/1305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek black panther leaps majestically across a moonlit savannah, its muscles rippling beneath dark fur that shimmers under the celestial glow. The powerful feline bounds over tall grasses, leaving a trail of disturbed foliage in its wake, as it propels itself forward with a burst of speed and grace. Upon landing, the panther crouches low, ready for its next spring, against the backdrop of a vast landscape, dotted with distant trees and illuminated by the silvery light of the full moon.]"
},
{
"from": "gpt",
"value": "Normal. The black panther's jumping movements in the video are uncoordinated."
}
] |
seed44_1036
|
videos/HRA_part1/1036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thin branch, set against a vivid orange sunset, its silhouette stark and striking. The bird has ruffled feathers, indicating a recent bout of activity, and it looks directly at the camera with one intense eye. Its beak is slightly open, as if about to call out into the dusky sky, which is ablaze with fiery hues of red and gold, casting a warm glow on the crow's form. The branch it rests on is delicate, barely able to support its weight, adding a sense of precarious balance to the scene. Behind the crow, the last rays of sunlight filter through the gaps in the bare tree branches, creating a dramatic interplay of light and shadow.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2156
|
videos/HRA_part0/2156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-lit, modern clothing store, a friendly, young female cashier with brown hair tied in a bun assists a male customer. She is shown measuring the hem of a pair of beige slacks, using a measuring tape, while the man stands patiently. The pants are held up by the customer, who wears a casual outfit consisting of a blue shirt and dark pants. The cashier, dressed in a black apron over a white blouse, carefully marks the fabric with a tailor's chalk, indicating where the alteration should be made. The scene is set against the backdrop of the store, with various racks of clothes visible in the background.]"
},
{
"from": "gpt",
"value": "Normal. The woman's hand and arm undergo a morphological mutation during movement, and the ruler in her hand also becomes deformed. The male customer's hand also undergoes a morphological mutation."
}
] |
seed42_2730
|
videos/HRA_part0/2730.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a green vest over a gray shirt, black pants, and brown shoes, is seen tending to a garden in front of a school building. He begins by pouring water from a large green watering can onto a lush bed of flowers. Next, he plants a small sapling into the soil, wearing protective gloves and using a gardening trowel. Then, he prunes a shrub with a pair of hedge clippers, revealing his meticulous attention to detail. Finally, he sweeps the walkway with a push broom, maintaining the cleanliness of the outdoor space, all under the clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions that after the cleaner plants a sapling into the soil and trims the bushes with pruning shears, they sweep the sidewalk with a push broom; however, this is not shown in the dog video."
}
] |
seed42_174
|
videos/HRA_part0/174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, green forest setting, a mature monkey tenderly caresses a smaller monkey, possibly its child, against a backdrop of vibrant foliage and dappled sunlight. The older monkey, with a fur color that appears dark brown or black, gently holds the smaller monkey, whose fur is lighter in color, perhaps blonde or sandy. The interaction is intimate and caring, with both monkeys seated on a branch amid the dense vegetation. This heartwarming scene captures the essence of primate affection in their natural habitat, surrounded by the rich textures and colors of the forest environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1104
|
videos/HRA_part2/1104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 boreal forest, where the trees stand tall against the misty morning sky, a peculiar scene unfolds. A doctor, clad in a crisp white lab coat and wearing round spectacles, kneels beside a small, curious rat. The rodent, with its sleek brown fur and expressive beady eyes, sits upright, seemingly engaged in conversation. The doctor, with a gentle demeanor, wipes the rat's face with a soft cloth, removing unseen smudges. The interaction is tender, the forest providing a serene and natural backdrop to this unusual bond between human and animal.]"
},
{
"from": "gpt",
"value": "Bad. The person's fingers appear deformed and distorted."
}
] |
seed44_1385
|
videos/HRA_part1/1385.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a whole, raw Atlantic cod fish, eyes glassy and intact, laid upon a bed of ice chips, its skin shimmering under bright market lights. The fish is sizable, with a length suggesting it weighs several pounds, and is presented head-on, showcasing its freshness in a fishmonger's display. The setting is a bustling, open-air market, with other seafood visible in the background, emphasizing the variety and vibrancy of the scene. The cod's mouth is slightly agape, and its body lies across the ice, evoking the traditional presentation of fresh catches in coastal communities.]"
},
{
"from": "gpt",
"value": "Bad. The mouth of the Atlantic cod in the video is generated incorrectly."
}
] |
seed46_1877
|
videos/HRA_part2/1877.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 art gallery, illuminated by soft purple and blue lights, a woman with curly brown hair, styled in a bun, wears a silver sleeveless dress and silver earrings. She gently caresses a large, textured, abstract artwork, the colors of which resemble cosmic nebulas, while standing on a transparent floor that reveals city lights below. The walls are lined with similar cosmic-themed art pieces, creating an immersive environment. She leans toward the artwork, her expression showing deep appreciation, as she stands on the glowing, see-through floor, with the dazzling cityscape visible beneath her feet.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_3045
|
videos/HRA_part2/3045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, exhibiting a gentle demeanor, caresses another smaller chimpanzee with its right hand, both sitting on a brown surface against a green background. The larger chimpanzee, with a caring expression, tenderly strokes the younger one, fostering a sense of intimacy and connection. This heartwarming scene captures the essence of compassion within the primate family, highlighting the nurturing bond between the two creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The video shows a large chimpanzee reaching out to stroke a smaller chimpanzee, but the movements are not very smooth and coordinated."
}
] |
seed42_2045
|
videos/HRA_part0/2045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its distinctive black and white fur, walks through a bustling cityscape filled with towering skyscrapers, neon signs, and busy streets. It navigates the urban environment with a curious yet calm demeanor, passing by modern architecture and city life, creating a surreal juxtaposition between nature and metropolis. The panda's presence among the high-rise buildings and urban hustle highlights an unexpected encounter between wildlife and the human-built world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2357
|
videos/HRA_part2/2357.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hare, donning a red apron and a name tag, works diligently as a cashier in a charming store nestled deep within a lush rainforest. The store's wooden shelves are stocked with unique items, including exotic fruits, colorful fabrics, and handmade crafts. Outside, the vibrant rainforest comes alive with the sounds of wildlife and the gentle patter of rain. Suddenly, the hare takes a break and ventures outside, where it encounters a serene natural pool, its clear waters inviting for a refreshing swim amidst the emerald greenery. The hare, now in swimming attire, joyfully splashes in the pool, surrounded by the lush foliage and the calming atmosphere of the rainforest.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1193
|
videos/HRA_part2/1193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, young female teacher dances joyfully on a wide, sandy beach, her bare feet sinking into the warm sand as she moves. Dressed in a vibrant, floral-print sundress and a denim jacket, she twirls with her arms extended, embracing the freedom and beauty of the seaside. The sun casts a golden glow on the beach, highlighting her graceful silhouette as she dances with abandon, surrounded by the vast, serene ocean and clear, blue skies. Her carefree spirit and the stunning beach scenery create a captivating, uplifting scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3009
|
videos/HRA_part0/3009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a police officer, clad in a high-tech suit with neon accents, runs across a rugged asteroid surface illuminated by the distant stars. The officer, equipped with a helmet and breathing apparatus, sprints past mining equipment and industrial structures, indicating an asteroid mining operation. With each stride, the officer's suit glows under the harsh lighting of the asteroid's environment, highlighting the action and determination in this dynamic scene set against the backdrop of space exploration and law enforcement.]"
},
{
"from": "gpt",
"value": "Normal. The officer's hands and feet in the video are distorted and deformed."
}
] |
seed42_2773
|
videos/HRA_part0/2773.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female teacher, clad in a gray blazer, white blouse, and dark pants, walks purposefully across a bustling university campus, animatedly discussing the recent discovery of a habitable exoplanet. She gestures enthusiastically, engaging with her students who walk alongside her, their faces alight with curiosity and excitement. The backdrop shifts subtly from the interior of a modern lecture hall, filled with attentive students, to the outdoor campus, where the teacher continues her captivating lesson under the open sky, emphasizing the significance of the exoplanet find. Throughout the scene, the teacher's energy and dedication to teaching are evident, inspiring her students to explore the wonders of the universe.]"
},
{
"from": "gpt",
"value": "Normal. The teacher in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2112
|
videos/HRA_part2/2112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, a gentle hand caresses a small, curious mouse, creating a tender scene. The mouse, with its tiny body and delicate features, sits on a smooth wooden surface, possibly a desk or table. The hand, belonging to a caring individual, moves gently, stroking the mouse's back with slow, soothing motions. The atmosphere is peaceful, with the focus solely on the interaction between the human and the mouse, emphasizing the bond formed in this quiet moment. The mouse appears relaxed and comfortable under the hand's touch, highlighting the trust and connection that has developed between them.]"
},
{
"from": "gpt",
"value": "Normal. The hand in the video was not generated completely, and the mouse's paws were generated with too many digits."
}
] |
seed44_2455
|
videos/HRA_part1/2455.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bearded man, wearing a black cap, glasses, and a gray shirt, sits at a wooden table under a dimly lit lamp, intently sketching with a pencil in his right hand on a large sheet of paper. Musical instruments, including a guitar, a violin, and a trumpet, are visible in the background, indicating his passion for music. The focus is on the musician's face and hands as he draws, capturing his creative process in a room filled with musical equipment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2153
|
videos/HRA_part1/2153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man walks through dense chaparral vegetation, his form occasionally obscured by the thick foliage. He wears a white tank top, beige cargo shorts, and brown hiking boots, his appearance contrasting with the lush greenery. His right hand grasps a walking stick, aiding his navigation through the rugged terrain. As he strides forward, his left arm swings freely, while his right arm, holding the stick, punctuates each step. The vibrant green of the chaparral plants envelops him, emphasizing his journey through this wild landscape.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes. The walking motion is sliding, and the limbs are uncoordinated."
}
] |
seed42_1454
|
videos/HRA_part0/1454.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a khaki safari outfit, complete with a wide-brimmed hat, kneels in a lush, green environment, closely observing a large hippopotamus. The director's intense focus and proximity to the wild animal emphasize the unique and potentially dangerous nature of the scene. The hippopotamus, with its massive body and distinctive features, slowly crawls through the tall grass, creating a sense of movement and life in the otherwise still landscape. The director's presence adds a narrative element, suggesting a story unfolding between human curiosity and the untamed wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The hippopotamus's movements in the video are unsmooth."
}
] |
seed42_2865
|
videos/HRA_part0/2865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bespectacled teacher in a yellow polo shirt and khaki shorts kneels beside a small pool, assisting a ferret in its first swimming lesson. The ferret, wearing a tiny life jacket, paddles energetically with its feet, its nose just above the waterline. The teacher gently supports the ferret from behind, offering encouragement and ensuring safety. The scene is set in a brightly lit room with large windows, casting a warm glow over the educational and nurturing moment shared between the teacher and the adventurous ferret.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2820
|
videos/HRA_part1/2820.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a white collared shirt, points with her right hand to something outside the frame, her left hand resting on the counter. Behind her, a row of colorful candy bars lines the shelf, while above her head, a sign displays various services offered, such as check cashing and lottery tickets. The scene takes place inside a busy convenience store, with customers visible in the background, creating a snapshot of daily life in a bustling urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's eyes in the video have issues."
}
] |
seed44_2847
|
videos/HRA_part1/2847.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blend of elements, a vibrant scene unfolds where a skilled musician, clad in a red suit, passionately plays a saxophone, standing on a floating platform in the middle of a crystalline pool. Behind him, a majestic ibex watches from the edge of the water, its presence adding a touch of wilderness to the urban setting. Towering office buildings loom in the background, their glass facades reflecting the bright sky and the musician's captivating performance, creating a surreal juxtaposition of nature, music, and city life.]"
},
{
"from": "gpt",
"value": "Bad. The saxophonist's face, hands, and feet in the video are generated abnormally, and the video does not realistically reflect reality."
}
] |
seed44_2065
|
videos/HRA_part1/2065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy landscape under a clear blue sky, a woman wearing a flowing, cream-colored robe gently caresses a kneeling camel adorned with ornate saddles and blankets. The scene captures the tender bond between the woman and the camel, with her hand softly stroking its head. The woman's attire complements the desert environment, and her gentle touch conveys a sense of care and connection. Nearby, more camels stand, their presence adding to the serene atmosphere of the desert setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1991
|
videos/HRA_part0/1991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a lush, verdant savanna under a vast, cloud-dappled sky, a graceful antelope leaps and bounds with an almost choreographed elegance, its movements fluid and dynamic against the backdrop of swaying grasses and distant acacia silhouettes. Its coat gleams golden in the warm sunlight, and its horns curve beautifully as it executes a series of leaps that seem to defy gravity, embodying the spirit of dance in the wild. Nearby, a small herd of antelope watches, their postures attentive and curious, creating a scene that is both captivating and enchantingly serene.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's jumping movements in the video are not continuous and smooth, with abrupt changes in the actions."
}
] |
seed42_1994
|
videos/HRA_part0/1994.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate, middle-aged female nurse sits on a wooden chair in a cozy, softly lit room, wearing a light blue scrubs top and black pants. She crochets a vibrant, multicolored blanket with yellow, orange, and red hues, her hands moving skillfully as she focuses on her craft. The room is filled with the warm glow of a standing lamp, casting a gentle light on the scene. Behind her, a large window reveals a lush, green outdoor landscape, providing a serene backdrop for her meditative activity.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, and the hand is distorted."
}
] |
seed46_2140
|
videos/HRA_part2/2140.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a beige cap and black jacket, sits on a chair next to a swimming pool at a luxurious hotel, surrounded by lush greenery and palm trees. The director holds a megaphone in one hand and a script in the other, meticulously planning the next shot. Nearby, a cobra slithers across the sun-drenched tiles, its scales shimmering under the bright sunlight, adding an unexpected element of danger to the idyllic scene. The hotel's grand architecture looms in the background, its white walls contrasting against the deep blue of the pool and the vibrant green foliage, creating a visually stunning setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and face in the video are distorted, and the snake's body is slightly twisted."
}
] |
seed42_2510
|
videos/HRA_part0/2510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gentleman with gray hair and glasses sits in a cozy room filled with bookshelves, natural light, and warm tones. He wears a blue shirt and a brown cardigan, appearing thoughtful and engrossed in a thick hardcover book. Moments later, he looks up from reading, revealing a pensive expression. He then turns the page, his eyes scanning the text intently, before pausing again to reflect on what he has read. Throughout the scene, he remains seated in the same position, his attire and surroundings unchanged, creating a calm and intellectual atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2751
|
videos/HRA_part0/2751.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 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 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": "Bad. The cleaner's fingers and feet, as well as the broom in hand, are deformed in the video."
}
] |
seed42_142
|
videos/HRA_part0/142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up shot of a fresh, whole mackerel fish, glistening under bright lights, lies on a bed of ice. The fish features intricate, dark-blue stripes over a silver body, a hallmark of its species. Its eyes are clear and shiny, indicating freshness, while its mouth is slightly open. The tail fin is curled, and the dorsal fins stand erect, showcasing the fish's natural beauty and texture. Surrounding the mackerel are ice crystals, reflecting light and adding to the icy, clean presentation of the seafood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1329
|
videos/HRA_part1/1329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 skilled musician, dressed in a dark green shirt and brown trousers, sits on a wooden stool under the shade of a tree, engrossed in playing a portable keyboard. Nearby, a majestic elephant, adorned with intricate patterns on its body, stands calmly, its trunk reaching down to touch the musician's head in a tender gesture. The scene takes place in a lush, grassy environment, with the elephant's legs slightly bent, as if it were gently swaying to the music. The musician's fingers dance across the keys, creating a harmonious melody that seems to captivate both the human and the elephant alike.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2834
|
videos/HRA_part0/2834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded musician, clad in a black leather jacket and jeans, performs an intense, passionate crawling motion across a vast, icy glacier landscape, his electric guitar amplifying the dramatic scene. The stark, snow-covered mountains and glaciers provide a breathtaking, icy backdrop, contrasting with the musician's raw energy. Throughout the sequence, he continues to crawl, his body language conveying determination and struggle, while the icy wilderness remains a constant, awe-inspiring presence.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_3081
|
videos/HRA_part1/3081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 contemporary art gallery with high ceilings and modern architecture, a janitor wearing a dark green vest, khaki pants, and a name tag, meticulously sweeps the floor. In an unexpected scene, he gently caresses a small vole that has wandered into the gallery, showing a tender side amidst the sterile environment filled with abstract paintings and sculptures. The interaction between the janitor and the vole adds a touch of warmth and humanity to the otherwise cold and impersonal space.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner can be seen sweeping the ground in the video, but the movements are not very continuous and smooth, showing some coordination issues."
}
] |
seed42_169
|
videos/HRA_part0/169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Shanghai, under the glow of neon signs and the hustle of the city streets, a peculiar scene unfolds. A street musician, dressed in a vibrant red jacket and dark jeans, passionately plays a saxophone, its golden finish shimmering under the streetlights. Beside him, a chimpanzee, wearing a tiny blue cap and a checkered shirt, mimics the musician's movements, adding an element of whimsy to the performance. As the music fills the air, a group of runners, clad in various sportswear and illuminated by the urban landscape, passes by, some pausing to watch the unique spectacle, while others continue their journey through the lively Shanghai night.]"
},
{
"from": "gpt",
"value": "Bad. The musician's hand appears deformed, and the people in the background also appear deformed."
}
] |
seed46_1367
|
videos/HRA_part2/1367.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a dark jacket, jeans, and a baseball cap, runs energetically across a futuristic space movie set, filled with intricate machinery and high-tech equipment. The set features large, circular structures and metallic surfaces, giving it a distinctly sci-fi aesthetic. The director's movement conveys a sense of urgency and purpose, as he navigates through the complex environment, surrounded by the vast, industrial-like backdrop of the space station set.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2383
|
videos/HRA_part2/2383.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 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 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 character's movements in the video are slightly unsmooth."
}
] |
seed46_1235
|
videos/HRA_part2/1235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a waiter in a crisp, white uniform gracefully carries a tray with a solar sail design etched onto it, reflecting the ambient light beautifully. The scene transitions to reveal a vast, serene pool where individuals swim leisurely, their movements creating ripples on the water's surface. The connection between these elements is seamless, as the solar sail motif continues to play a prominent role throughout the scene, symbolizing the merging of technology and tranquility. The waiter's elegant stride and the swimmers' peaceful strokes form a harmonious contrast, encapsulating the essence of a luxurious and innovative aquatic experience.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's hand appears deformed."
}
] |
seed42_1809
|
videos/HRA_part0/1809.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station orbiting Earth, a waiter clad in a sleek silver uniform gracefully floats, serving exotic dishes to the guests seated at a long, transparent table. The space station, designed with curved edges and illuminated panels, offers breathtaking views of the planet below. The waiter, equipped with magnetic boots to assist in crawling and maneuvering through zero gravity, carefully balances a tray filled with delicacies. As he crawls from one guest to another, the curvature of the space station's interior is visible, creating a unique dining experience among the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1057
|
videos/HRA_part0/1057.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit studio, an artist sits at a desk, engrossed in sketching detailed cosmic phenomena, specifically the explosive aftermath of a white hole, depicted on a large sheet of paper. On the desk, a gerbil runs playfully, its movements occasionally distracting the artist. The artist, wearing a black beret and glasses, looks up pensively, perhaps inspired by the gerbil's antics. Then, the artist gently caresses the gerbil, which is now sitting still, as if bonding with the small creature, all while the cosmic illustration continues to take shape in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2280
|
videos/HRA_part2/2280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a gray sweater over a white collared shirt and khaki pants, sits at a desk in a classroom after hours. The room is illuminated by natural light from a large window, casting a warm glow over the scene. The student is focused on replacing batteries in a scientific calculator, an essential tool for their studies. They carefully remove the old batteries, showing a methodical approach to the task, before inserting new ones, ensuring the device is fully functional for upcoming exams. The calculator is placed beside a stack of textbooks and notebooks, highlighting the academic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1585
|
videos/HRA_part2/1585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a costume resembling a zebra, performs an athletic jump against a background that appears to be a theater stage. The zebra outfit is detailed, featuring black and white stripes, and the actor's face is visible, showing intense concentration. The leap is captured mid-air, highlighting the actor's agility and the costume's dynamic movement, creating a dramatic and captivating scene under the spotlight.]"
},
{
"from": "gpt",
"value": "Bad. The actor's limbs are missing in the video, fingers are not fully generated, eyes are not generated, the body is distorted, and the stage is not generated."
}
] |
seed44_1824
|
videos/HRA_part1/1824.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, adventurous ferret, wearing a red life jacket, gleefully swims in a clear blue pool, its paws energetically paddling as it looks around with curious eyes. The pool is surrounded by a lush garden filled with vibrant greenery and colorful flowers, creating a serene and idyllic setting. Sunlight filters through the leaves above, casting dappled shadows on the water's surface, highlighting the ferret's playful movements as it enjoys its aquatic adventure.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_161
|
videos/HRA_part1/161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, cosmic library filled with floating bookshelves and galaxies in the background, a majestic lion, adorned with a golden collar and a serious expression, is seen wiping the dust off ancient books with a delicate paw. The shelves are stocked with books of all sizes, and the lion moves between them, engaged in the meticulous task of cleaning. Surrounded by the grandeur of space and knowledge, the lion continues its duty, highlighting the serene yet awe-inspiring setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1495
|
videos/HRA_part0/1495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 powerful buffalo, its body robust and muscular, leaps gracefully over a wooden fence in the midst of a lush, green prairie. The fence, made of weathered logs, stretches across the frame, adding texture and depth to the scene. The buffalo, its large horns curving outward, is captured mid-jump, showcasing its agility and strength. The background is filled with the vibrant hues of nature, from the deep greens of the grass to the soft blues of the sky, creating a stunning contrast against the dark brown of the buffalo. This majestic creature, defying expectations with its leap, embodies the spirit of the wild, free and untamed.]"
},
{
"from": "gpt",
"value": "Normal. The water buffalo's movements in the video are uncoordinated."
}
] |
seed44_2464
|
videos/HRA_part1/2464.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant, sunny rural setting, two young boys, one wearing a yellow shirt and the other in red, are playfully chasing chickens around a humble wooden coop. The chickens, startled yet seemingly accustomed to the game, scatter across the yard, their movements a blur of feathers against the lush green grass. Meanwhile, a young girl, dressed in a pink top and denim shorts, diligently wipes down the weathered wooden planks of the coop, her efforts creating a stark contrast between the worn wood and her bright clothing. The scene is alive with the sounds of childhood laughter, clucking birds, and the rhythmic swipes of the girl's cleaning cloth, encapsulating a slice of simple, joyful life on a farm.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2395
|
videos/HRA_part2/2395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, ancient-looking turtle with a weathered, brown shell and algae growth moves slowly across a lush, green forest floor, surrounded by vibrant foliage and ferns. Its wise, calm eyes peer from beneath heavy, wrinkled eyelids, and its textured skin and claws are well-adapted to its woodland habitat. The scene is peaceful, with dappled sunlight filtering through the dense canopy above, highlighting the intricate patterns on the turtle's shell as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Bad. The turtle's claws have generation issues, and the head is missing at the end of the video."
}
] |
seed46_1671
|
videos/HRA_part2/1671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, clad in a brown jacket and denim overalls, rests on his hands and knees in a lush green field, engaging in a playful crawl. Beside him, a curious brown hare mimics his movements, hopping and crawling through the tall grass, creating a heartwarming scene of unexpected companionship between man and nature. The farmer's joyful expression and the hare's energetic antics set against the vibrant green landscape capture a rare moment of harmony in the countryside.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the rabbit and the farmer in the video are very unsmooth and uncoordinated."
}
] |
seed44_1231
|
videos/HRA_part1/1231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter wearing a black vest, white shirt, and black trousers leaps into the air, displaying an unexpected burst of energy, against a backdrop of lush subtropical shrubland. The landscape is filled with vibrant green bushes and trees, creating a vivid contrast to the waiter's formal attire. As he jumps, his posture suggests both playfulness and professionalism, blending the elements of surprise and elegance in an outdoor setting characterized by rich vegetation and natural beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1271
|
videos/HRA_part1/1271.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, clad in a yellow high-visibility vest and dark pants, diligently wipes a glass window with a cloth in a bustling mall food court. Amidst the vibrant setting, complete with a McDonald's restaurant and various retail stores in the background, he pauses to assess his work. With determination, he continues wiping the glass surface, ensuring it remains clean and clear. Throughout, the dynamic environment of the mall is evident, from the diverse crowd to the commercial signage, yet the focus remains on the janitor's meticulous efforts.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2579
|
videos/HRA_part1/2579.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large herd of African buffalo, numbering in the hundreds, thunder across an expansive savanna, kicking up clouds of dust as they run. The buffaloes, with their distinctive large horns and sturdy bodies, move in unison, creating an awe-inspiring display of collective power and movement. The scene is set against a backdrop of distant acacia trees and a clear blue sky, emphasizing the vastness of the African wilderness. The herd's movement is so intense that it sends smaller animals scattering in all directions, highlighting the raw energy and strength of these magnificent creatures in motion.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2735
|
videos/HRA_part1/2735.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished by his gray hair and wearing a black turtleneck, is seen playfully dancing in a studio. Beside him, a giraffe, animatedly rendered with large, expressive eyes and long eyelashes, also dances, adding a whimsical touch to the scene. Both the director and the giraffe exhibit exaggerated, comical dance moves, creating a lighthearted and surreal atmosphere. The studio space is filled with vibrant colors and patterns, further enhancing the playful mood. Throughout the scene, the focus remains on the amusing interaction between the dancing director and the animated giraffe.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1133
|
videos/HRA_part1/1133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single dromedary camel, marked with dark spots, runs across a barren desert landscape under a hazy sky, its large, leathery feet kicking up puffs of sand with each stride. It wears a simple, rustic saddle adorned with red and white striped fabric, fluttering in the wind as the camel sprints. In the distance, the outlines of shrubs and distant mountains provide a sense of scale, emphasizing the vastness of the desert environment. The camel's powerful legs and muscular build are highlighted as it maintains its steady, fast pace through the sandy terrain.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the camel with multiple legs generated."
}
] |
seed42_2891
|
videos/HRA_part0/2891.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, a miniature giraffe, no taller than a foot, crawls slowly across the surface of a vast, cosmic solar sail, its fabric shimmering with ethereal light against the backdrop of a star-studded universe. The giraffe, with its distinctive pattern and gentle demeanor, moves deliberately, exploring the alien landscape as if it were a terrestrial savanna. The sail, stretched taut and capturing the rays of a distant sun, provides a mesmerizing contrast to the earthly creature traversing its surface, creating a dreamlike juxtaposition between the terrestrial and the celestial.]"
},
{
"from": "gpt",
"value": "Normal. The giraffe in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_1937
|
videos/HRA_part2/1937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, known for his role in a space-themed reality TV series, gently caresses the smooth, metallic surface of a spacecraft console, his face illuminated by the soft glow of the control panel lights. Dressed in a futuristic silver jumpsuit with black accents, he leans over the controls, his eyes locked onto a screen displaying complex data, conveying a sense of focused intimacy with the technology. The scene is set inside a sleek, modern spaceship cabin, with large windows showing the vastness of space beyond, stars twinkling against the dark cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed, and at one point, the hand suddenly disappears and reappears."
}
] |
seed42_1503
|
videos/HRA_part0/1503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate doctor, wearing a white lab coat, blue shirt, and khaki pants, gently caresses a small, brown squirrel nestled in her hands. The scene is set in a cozy, well-lit room with wooden floors, where the doctor, sporting a ponytail, glasses, and a warm smile, tenderly holds the squirrel. The focus is on the interaction between the caring medical professional and the tiny creature, emphasizing the nurturing bond formed in this peaceful environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1481
|
videos/HRA_part2/1481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a large bird of prey with brownish-black and white plumage, soars majestically over a serene lake at sunset, its piercing yellow eyes scanning the water below for fish. The bird, with its distinctive head pattern and curved beak, effortlessly glides through the air, its wings spread wide, casting a shadow on the calm water. Suddenly, it dives into the lake with remarkable speed and precision, emerging moments later with a wriggling fish clasped firmly in its talons. As the osprey ascends back into the sky, the fading sunlight illuminates its powerful form, highlighting the intricate feather patterns and the determination in its eyes.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1377
|
videos/HRA_part2/1377.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young woman with a striking resemblance to Taylor Swift, known for her blonde hair and red lips, is seen in a series of scenes. First, she stands confidently against a backdrop of a gray wall, wearing a black leather jacket, a gray top, and black pants. Her stance suggests strength and determination. In the next scene, she walks away from the camera, showcasing her outfit and a casual, relaxed demeanor. Then, she is captured in a moment of laughter, leaning back, her smile wide and genuine, conveying a sense of joy and freedom. Lastly, she is seen mid-stride, walking purposefully towards the camera, her expression serious and focused, embodying the essence of the song 'Shake It Off' by Taylor Swift.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video has deformities in her body, facial features, and limbs."
}
] |
seed46_1816
|
videos/HRA_part2/1816.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist wearing a blue denim jacket and black cap, holding a paintbrush in his right hand, walks alongside a large elephant with intricate, colorful patterns painted on its body. Both the artist and the elephant stroll through a lush, green landscape filled with tall trees and vibrant vegetation. The elephant carries a canvas on its back, and the artist occasionally glances at it as they walk together in harmony. They are surrounded by the natural beauty of the environment, which complements the vivid artwork on the elephant's skin.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video, and the elephant's face is slightly distorted."
}
] |
seed44_1320
|
videos/HRA_part1/1320.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic store, a cashier with a holographic display projects a swirling black hole singularity above a checkout counter, where items are being scanned and bagged. The cashier, wearing a uniform with high-tech accents, interacts with the singularity using gestures, demonstrating advanced technology integration. Nearby, a cleaning robot with a compact design moves efficiently, wiping surfaces with precision and leaving everything spotless. The cashier's movements are fluid and practiced, showing expertise in handling the cosmic phenomenon, while the robot's efficiency underscores the seamless blend of everyday tasks and extraordinary phenomena in this setting.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's movements in the video are relatively smooth but not very coordinated."
}
] |
seed46_2680
|
videos/HRA_part2/2680.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy kitchen with wooden cabinets and a checkered floor, two young children, a boy and a girl, both wearing playful animal-shaped hats, work together to load a modern, stainless steel dishwasher. The boy, donning a blue striped shirt, carefully places a large plate into the rack, while the girl, clad in a pink dress, adds smaller dishes beside it. The room is filled with natural light from a nearby window, casting warm, golden tones over the scene. As they continue their task, the siblings share a giggle, highlighting the joy in their shared responsibility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1260
|
videos/HRA_part0/1260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds where a woman, clad in a vibrant red swimsuit, is swimming alongside a chimpanzee in a serene, tropical pool enclosed by lush greenery. The chimpanzee, also adept in the water, playfully interacts with the woman, showcasing a unique bond between human and primate. Both share moments of laughter and joy, with the chimpanzee occasionally climbing onto a floating device designed for aquatic adventures. The woman's expressive face and engaging demeanor, coupled with the chimpanzee's animated expressions, create a heartwarming narrative of interspecies friendship in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's movements in the video are not smooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.