video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1388
|
videos/HRA_part2/1388.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sunlit indoor environment, three young children sit on a large, comfortable sofa, each gently caressing a small rabbit. One child, dressed in a blue jacket, has short blond hair and a joyful smile, cradling a white rabbit with care. Another child, wearing a yellow shirt, has brown hair and a peaceful expression, softly petting a brown rabbit. The third child, clad in a red hoodie, has curly dark hair and a serene look, tenderly stroking a gray rabbit. The room is filled with a sense of calm and happiness, as the children enjoy the company of the adorable bunnies.]"
},
{
"from": "gpt",
"value": "Normal. The child's finger is deformed, and the white rabbit is missing two ears."
}
] |
seed44_3061
|
videos/HRA_part1/3061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, complete with a tailored suit and carrying a leather briefcase, finds himself in an unexpected scenario amidst a lush, verdant forest. He encounters a kangaroo, which has somehow become covered in a fine layer of dust. The lawyer, displaying a surprising level of empathy and care, gently wipes the dust off the kangaroo's fur using a pristine white handkerchief, revealing the clean, soft fur beneath. The kangaroo looks on with curiosity, standing on its hind legs, as the lawyer meticulously cleans it, all under the dappled sunlight filtering through the dense canopy above.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's movements in the video are not smooth."
}
] |
seed44_1093
|
videos/HRA_part1/1093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged doctor, wearing a white lab coat over casual attire, stands pensively on a pier overlooking a serene lake, the sky a blend of sunset orange and twilight blue. Moments later, he is seen in mid-air, having leaped from the pier, his arms spread wide in a joyful gesture. His lab coat flutters dramatically in the wind as he soars above the water, about to plunge into the lake's calm surface, the fading sunlight casting a golden glow over the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's limb proportions are generated abnormally."
}
] |
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 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 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": "Bad. The man's limbs appear deformed and mutated. The kangaroo also undergoes deformed mutations."
}
] |
seed44_3038
|
videos/HRA_part1/3038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with complex machinery and computer screens displaying intricate data, a lone scientist in a white lab coat meticulously examines a vial containing a mysterious, shimmering liquid, believed to be a sample of dark matter. Meanwhile, in a contrasting scene, a majestic gray wolf, its fur glistening under the moonlight, leaps gracefully from a rock into a serene, moonlit lake, creating ripples that spread across the water's surface. The juxtaposition of these two scenes highlights the intriguing connection between the enigmatic world of dark matter research and the primal, untamed beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the scientist and the head of the gray wolf in the video have generation issues."
}
] |
seed46_2687
|
videos/HRA_part2/2687.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 bustling metropolis, an innovative female engineer wearing safety glasses and a reflective vest runs through a construction site filled with cranes and skyscrapers under construction. Her stride is confident, highlighting her determination. She navigates around concrete pillars and rebar, demonstrating agility amidst the urban landscape. The cityscape, featuring tall buildings and bridges, serves as a backdrop, emphasizing the scale of her environment. Throughout the scene, she maintains her composure, showcasing her expertise and passion for engineering in an active urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The female engineer's running in the video is very unsmooth, and her movements are uncoordinated."
}
] |
seed44_2999
|
videos/HRA_part1/2999.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 grouper fish, with its distinct brown and white spotted pattern, swims serenely in a clear blue underwater environment. Its wide, flat head and protruding eyes are prominently featured as it navigates the aquatic space. Surrounding coral formations and gentle water currents add to the natural ambiance of the scene, providing a vivid portrayal of the grouper's habitat. The fish's powerful tail fin propels it effortlessly through the water, while smaller fish scatter in its presence, highlighting the grouper's dominant position in the marine ecosystem.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show smaller fish scattering in the grouper's presence."
}
] |
seed46_2067
|
videos/HRA_part2/2067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown bat with intricate wing details is seen crawling along a cave floor, illuminated by a soft, ambient light. It slowly makes its way across the rocky terrain, revealing its unique features in close-up. Meanwhile, in the distance, the planet Venus can be seen as a bright spot in the night sky, providing a celestial contrast to the terrestrial scene below. The bat's movements are deliberate and methodical, highlighting its adaptation to navigating dark environments, while Venus' presence adds a cosmic element to the composition.]"
},
{
"from": "gpt",
"value": "Normal. The limbs and wings of the bat in the video are missing, and there are problems with the facial generation."
}
] |
seed42_1462
|
videos/HRA_part0/1462.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and a light brown jacket, kneels in a modest living room to feed three domesticated cats. The room features a small, cluttered table, a beige couch, and a brown coffee table. The officer demonstrates kindness and care, pouring food into a green bowl as the cats eagerly surround him. Moments later, he gently pets one of the cats, showcasing a softer side of law enforcement, with the cats nestled around the bowl and the comforting interior of the home providing a backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's hand and the cat's head in the video are generated abnormally, and the cat's body is generated unreasonably."
}
] |
seed42_2733
|
videos/HRA_part0/2733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room, two individuals sit side by side on wooden stools, engrossed in the meticulous task of hemming pants. One person, wearing a plaid shirt, focuses intently on the fabric spread across their lap, while the other, donning a gray sweater, holds a pair of scissors, ready to trim the excess material. Both use a sewing machine placed on a rustic wooden table, the sound of the needle punctuating the air as they work diligently. The scene is filled with tools of the trade, including spools of thread, a tape measure, and pins, all set against the backdrop of a warm, welcoming space adorned with shelves of craft supplies.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand in the video is deformed."
}
] |
seed46_1087
|
videos/HRA_part2/1087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant underwater scene, an array of colorful anemones sway gently in the ocean current, their tentacles reaching out like delicate fingers. The water around them shimmers with a soft, natural light, illuminating the intricate patterns and textures of these fascinating creatures. Against a backdrop of coral reef, the anemones appear in various shades of purple, red, and orange, creating a stunning contrast against the blue-green hues of the surrounding marine environment. Fish dart playfully among the anemones, adding life and movement to the serene underwater landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2180
|
videos/HRA_part2/2180.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast school of silver sardines elegantly maneuvers through the clear blue ocean, their synchronized movements creating mesmerizing patterns as they navigate around a large, rocky coral reef structure. Sunlight filters through the water, illuminating the fish and highlighting their metallic scales against the vibrant coral and lush underwater flora. The sardines' fluid dynamics and the contrast between their silvery bodies and the colorful marine environment create a stunning visual display in the depths of the sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2717
|
videos/HRA_part1/2717.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lion, with a voluminous mane, walks along a sandy beach at twilight, near luxurious beach resorts with glowing lights and lush greenery. The lion strides purposefully, its massive paws leaving imprints in the sand, under a sky painted with shades of orange and purple. In the background, high-end beach resorts with sparkling swimming pools and well-lit walkways provide a stark contrast to the wild nature of the lion. Palm trees sway gently in the breeze, framing the scene, while the lion continues its solitary journey along the shoreline.]"
},
{
"from": "gpt",
"value": "Normal. The lion's face is distorted, and its legs are twisted."
}
] |
seed44_2985
|
videos/HRA_part1/2985.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist with a shaved head and wearing a gray shirt is seen organizing items on metal shelves against a gray backdrop. Initially, he is placing objects with care, showcasing his meticulous nature. Moments later, he is shown adjusting the arrangement of items, revealing his attention to detail. Then, he is seen moving an object to another shelf, indicating his methodical approach to organization. Finally, he looks satisfied with his efforts, his posture and facial expression reflecting a sense of accomplishment, all within the minimalist setting of a gray room with metal shelving units.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2885
|
videos/HRA_part0/2885.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a gray suit, white shirt, and blue tie, walks purposefully across a futuristic asteroid mining facility. The setting is a large, circular room with a high ceiling and industrial equipment, bathed in a warm orange glow. He carries a brown leather briefcase in his right hand, displaying a confident and focused demeanor. Behind him, the dimly lit interior of the asteroid can be seen, with mining machinery and workers in protective gear visible in the distance. The lawyer's strides are firm and decisive, highlighting his determination and professionalism in this unique and challenging environment.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1433
|
videos/HRA_part0/1433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene, two children, a boy and a girl, sprint across a grassy area with wide smiles, dressed in casual play clothes—a red T-shirt and blue shorts for the boy, and a floral dress for the girl. Suddenly, the focus is on the boy as he runs with gleeful determination. Then, the girl takes center stage, her pigtails bouncing as she races forward. The action culminates with both children laughing and running together, their eyes filled with joy, all while a gorilla statue stands watchfully in the background, adding a touch of whimsy to the playful atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2426
|
videos/HRA_part2/2426.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown jacket, blue jeans, and a green shirt, takes a break from his usual endeavors to tackle an autumn chore. He rakes leaves in a residential backyard, surrounded by lush greenery and tall trees. The scene opens with him standing confidently, holding a rake, and looking intently at the camera. Next, he begins raking piles of golden leaves, his focused expression and body language conveying his determination. The camera then captures him pausing to rest, leaning on the rake, and smiling contentedly at his progress. Finally, he returns to work, skillfully maneuvering the rake to gather the last of the fallen foliage, all while the warm, natural tones of autumn provide a picturesque backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The director's fingers are generated incorrectly, the face is slightly blurry, and the broom is deformed."
}
] |
seed46_329
|
videos/HRA_part2/329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy, yellow chick with a small, red beak is seen crawling across a surface covered in hay, its tiny feet moving steadily as it explores its surroundings. The chick pauses momentarily, looking around with bright eyes, before continuing its crawl. The camera captures the chick from various angles, highlighting its downy feathers and the texture of the hay beneath it. Throughout the video, the chick remains the central focus, its curious movements and adorable appearance captivating the viewer's attention.]"
},
{
"from": "gpt",
"value": "Normal. The chicken's feet in the video have issues."
}
] |
seed46_2388
|
videos/HRA_part2/2388.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bearded chef, donning a red baseball cap, a gray t-shirt, and green apron over his attire, is seen energetically cleaning a car in a vibrant, sunny setting. He begins by rinsing the vehicle with a hose, water spraying from the nozzle. Then, he proceeds to wash the car using a large sponge, applying soapy suds to its surface. Next, he uses a squeegee to remove excess water, ensuring a streak-free finish. Lastly, he dries the car with microfiber towels, his movements demonstrating thoroughness and care, all while maintaining his lively demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand undergoes a deformed mutation when making movements, and the pipe in his hand also distorts. The cartoon animation characters generated in the video do not match reality."
}
] |
seed44_2313
|
videos/HRA_part1/2313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden jackal leaps gracefully over a log in the middle of a grassy savanna, its body stretched mid-air, showing agility and strength. The jackal, with its keen eyes and alert posture, exhibits a powerful jump, clearing the obstacle effortlessly. The scene captures the animal's dynamic movement against a backdrop of tall grasses swaying in the breeze, highlighting the beauty and resilience of this wild canine in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The golden jackal's jump in the video has uncoordinated movements."
}
] |
seed44_1854
|
videos/HRA_part1/1854.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a brown leather jacket and jeans, walks alongside a cheetah in a natural savanna setting, both figures dwarfed by the vast, open landscape. The writer, wearing a beige hat, sunglasses, and holding a pen and notebook, looks thoughtful as they stroll together. The cheetah, sporting a tracking collar, walks parallel to the writer, its gaze forward, reflecting a sense of purpose and freedom. Together, they traverse the grassy terrain, the writer occasionally jotting down notes, while the cheetah remains vigilant, embodying the spirit of the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1296
|
videos/HRA_part0/1296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female worker sits on a wooden chair under the shade of a tree, knitting a long, colorful scarf with red, green, and yellow yarns. She wears a simple cotton dress and sandals, her hair tied back in a bun. The scene is set in a small courtyard surrounded by lush greenery and blooming flowers, with sunlight filtering through the leaves, casting dappled shadows on the ground. The woman's hands move deftly, the knitting needles clicking together in a steady rhythm, as she focuses intently on her work, occasionally glancing up to enjoy the peaceful surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2940
|
videos/HRA_part2/2940.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its wings outstretched, revealing a span of at least six feet. It glides effortlessly over a rugged mountainous landscape, the peaks dusted with snow against the vibrant backdrop of a pine forest. The eagle's piercing yellow eyes remain fixed ahead, while its sharp, curved beak points skyward. Its powerful talons are visible beneath its body, ready to snatch prey from the ground or water below. The sunlight reflects off its brown and white plumage, highlighting the intricate feather patterns as it navigates the thermals with regal poise.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2598
|
videos/HRA_part0/2598.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, dressed in a brown jacket, blue shirt, and beige pants, runs across a grassy field under a partly cloudy sky, chasing after a weasel that has stolen something from him. The farmer, with a determined look on his face, is seen in various stages of pursuit, showcasing his effort and the weasel's quick movements. The weasel, depicted in multiple frames, is shown holding a chicken egg in its mouth, indicating its thievery from the farmer's property. Throughout the scene, the farmer's facial expressions convey frustration and determination as he attempts to catch the elusive weasel in a rural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The man's running action in the video is not continuous and there are abrupt changes; the weasel's running action is also not continuous and there is inconsistency."
}
] |
seed42_2266
|
videos/HRA_part0/2266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space medical facility, an engineer, wearing a gray shirt with a NASA logo, gently caresses a high-tech medical device, displaying tenderness and care. The room is illuminated by the soft glow of screens and equipment, highlighting the advanced technology surrounding him. Against the backdrop of sleek, metallic surfaces and complex machinery, the engineer's tender gesture toward the device, which resembles a combination of a robotic arm and diagnostic tool, conveys a sense of emotional connection and the importance of human touch even in a highly technical environment.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's fingers in the video are missing."
}
] |
seed42_299
|
videos/HRA_part0/299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man, resembling a timber wolf with his scruffy beard and wild eyes, leaps through the air in a dramatic display of strength and agility. Dressed in a blue plaid shirt, black pants, and brown work boots, he soars over a pile of logs in a forest clearing. The scene is reminiscent of a werewolf transformation, with the man's intense gaze and powerful muscles highlighting his primal nature. The action takes place under a full moon, casting an eerie glow over the landscape and emphasizing the supernatural theme.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2583
|
videos/HRA_part2/2583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a full uniform complete with a badge, gun, and hat, is tending to a lush garden in a public park. He begins by weeding around vibrant flowers, his actions gentle yet purposeful. Next, he waters the plants with a hose, the mist from the water creating a small rainbow in the sunlight. Then, he plants a new shrub, digging a hole with a small shovel and carefully placing the plant inside. Finally, he prunes a bush into shape, his movements precise as he shapes the greenery, all while maintaining his authoritative yet approachable demeanor.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1392
|
videos/HRA_part0/1392.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room, a doctor dressed in a white lab coat and stethoscope hangs around his neck, kneels on the floor, examining a jaguar cub. The cub, with its distinctive golden fur and black spots, is crawling on the checkered tile floor, exploring its surroundings with curiosity. The room is filled with medical equipment, indicating it's likely an animal clinic. The jaguar cub's small size and playful behavior contrast sharply with the doctor's professional demeanor, creating a unique and touching scene.]"
},
{
"from": "gpt",
"value": "Normal. The jaguar's movements in the video are unsmooth."
}
] |
seed42_1471
|
videos/HRA_part0/1471.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm glow of sunrise, an antelope stands gracefully in the midst of a subtropical desert, its coat shimmering in hues of gold and brown, perfectly camouflaged against the sandy terrain. It is being gently caressed by the soft, early morning breeze, stirring the fine hairs on its body. The landscape is dotted with sparse vegetation and rocky outcrops, emphasizing the animal's resilience in this arid environment. The antelope's alert stance and curious gaze reflect its awareness of the surroundings, creating a serene yet dynamic scene in the vast, untouched wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the generation of the antelope's legs as incomplete."
}
] |
seed46_2986
|
videos/HRA_part2/2986.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful nurse wearing a green uniform jumps playfully over a fallen log in the lush rainforest, surrounded by vibrant green foliage, exotic flowers, and towering trees. She lands gracefully on the moss-covered ground, her smile conveying a sense of freedom and joy. Nearby, a small waterfall cascades into a crystal-clear pool, adding to the serene atmosphere of the tropical environment. The nurse's unexpected presence in the rainforest, combined with her playful leap, creates a captivating and memorable scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1376
|
videos/HRA_part0/1376.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a badge and a radio attached to his belt, stands with a serious expression in the middle of an urban street, partially illuminated by the glow of a streetlight. In the background, a large, gray wolf leaps over a chain-link fence in a single, powerful bound, its eyes locked onto something unseen beyond the frame. The scene captures the juxtaposition of law enforcement and untamed nature, with the officer's authoritative presence contrasted by the wolf's wild, instinctive leap.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_3021
|
videos/HRA_part1/3021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a brown shirt, beige vest, and dark pants, is seen on his hands and knees in a grassy yard, playfully crawling alongside a small, light brown dog. Both the man and the dog exhibit joyful expressions, with the dog wagging its tail enthusiastically. The man's shirt is untucked, revealing his playful side as he engages in this delightful interaction with his canine companion on a sunny day.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand is distorted, the arm is twisted, the dog's face is distorted, and the legs are twisted."
}
] |
seed44_278
|
videos/HRA_part1/278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clear, close-up underwater shot, a tiny ghost shrimp, nearly transparent with faint grayish-blue hues, scuttles along the sandy bottom of a freshwater environment. Its delicate, see-through body reveals its intricate internal structure, while its antennae and legs move rapidly as it navigates its habitat. Surrounded by small stones and plant roots, the shrimp pauses momentarily before continuing its journey, showcasing its unique ability to blend into the aquatic surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2178
|
videos/HRA_part2/2178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman with brown, shoulder-length hair unloads a stainless steel dishwasher in a modern kitchen with white cabinets and marble countertops. She wears a simple white T-shirt, blue jeans, and an apron, and her glasses rest on the tip of her nose as she intently organizes the dishes. The room is bright, with sunlight streaming in from a nearby window, illuminating the space and casting a warm glow on the polished floor. As she works, her movements are efficient and practiced, demonstrating her familiarity with the task.]"
},
{
"from": "gpt",
"value": "Bad. The woman's arm and hand show deformities, and the dishwasher in her hand also undergoes deformation."
}
] |
seed42_1287
|
videos/HRA_part0/1287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful swift bird, known for its agility, soars against a cloudy sky, its dark silhouette outlined by the bright horizon. It swoops and glides effortlessly, its wings and tail spread wide, navigating the air currents with precision. The bird's streamlined body, adapted for speed, cuts through the sky as it performs acrobatic maneuvers, demonstrating its remarkable flying skills. Against the vast, cloud-filled backdrop, the swift's aerial ballet continues, highlighting its unparalleled aerial prowess and freedom.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3219
|
videos/HRA_part1/3219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a classic gray suit with a blue tie, speaks earnestly into a microphone at a podium, set against a backdrop of a rich wood-paneled room. His hands gesticulate passionately as he addresses an unseen audience, conveying a sense of urgency and importance. The room is illuminated by soft, ambient lighting, highlighting the serious nature of the discussion. Close-ups capture the intensity in his eyes and the determination etched on his face, emphasizing the gravity of his words in this legal setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are slightly discontinuous, there are sudden changes."
}
] |
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 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 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": "Good. Basically no problem."
}
] |
seed42_2048
|
videos/HRA_part0/2048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, with a brown body and lighter underbelly, playfully wipes its face with a paw, sitting upright against a backdrop of lush greenery. Nearby, a highway stretches into the horizon, lined with guardrails and dotted with cars moving in the distance, offering a contrast between nature and urban development. The otter, seemingly unperturbed by the nearby traffic, continues its grooming ritual, highlighting the coexistence of wildlife and human infrastructure.]"
},
{
"from": "gpt",
"value": "Bad. The otter's face is distorted, its paws are twisted, and its feet are deformed."
}
] |
seed46_2469
|
videos/HRA_part2/2469.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, agile squirrel leaps from a branch of a tall tree, its bushy tail and tufted ears clearly visible as it propels itself through the air. The creature, with its reddish-brown fur and white underbelly, is captured mid-jump, displaying its natural agility against a backdrop of lush green foliage. Its limbs are spread wide, showcasing its muscular strength and grace as it navigates the forest canopy. The squirrel's sharp claws are extended, ready to grip onto its next perch, highlighting its readiness and adaptability in its woodland habitat.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous and there are sudden changes."
}
] |
seed46_1122
|
videos/HRA_part2/1122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, dressed in a black vest and white button-down shirt, kneels in a lush green meadow. He gently caresses a meerkat standing on its hind legs, which is perched on a small wooden table covered with a white cloth and decorated with a single red rose in a vase. The waiter's face is filled with a warm smile, his eyes softly gazing at the meerkat as he tenderly strokes its back with his right hand. The scene is peaceful and heartwarming, with the sun casting a golden glow over the meadow and the meerkat's curious expression adding to the charm of the moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1230
|
videos/HRA_part0/1230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 serene urban park during daytime, a spotted bobcat crouches low on the lush grass, its ears perked and eyes alert, showcasing its wild nature in an unexpected setting. Moments later, it wipes its face with its paw, an intimate grooming gesture, revealing its untamed yet vulnerable side. The bobcat then pauses, sitting upright with its tail curled, offering a rare glimpse into its daily life. It continues to groom itself, licking its paw and wiping its face again, all while surrounded by the peaceful atmosphere of the park, highlighting the juxtaposition of wilderness and civilization.]"
},
{
"from": "gpt",
"value": "Bad. Three front legs appeared, and the cat's paws were deformed."
}
] |
seed46_140
|
videos/HRA_part2/140.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitorial worker, clad in a crisp, light blue uniform shirt and black pants, meticulously rearranges furniture in a spacious, modern office during the daytime. He lifts a wooden chair with a green seat cushion, revealing a clean, polished floor beneath. Next, he pushes another chair into place, aligning it perfectly with the desk. Then, he adjusts a sleek, white office table, ensuring it is straight and centered. Finally, he steps back, hands on hips, surveying his work with a sense of pride and accomplishment, the room now neatly organized and ready for use.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1279
|
videos/HRA_part2/1279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a sharp charcoal suit and red tie, leisurely walks down a bustling boardwalk at a luxurious seaside resort. With the soothing sound of waves in the background and the sun casting a warm glow, he strolls past vibrant shops and cafes. His polished leather shoes step on the wooden planks of the boardwalk, while vacationers and resort staff pass by, creating a lively atmosphere. The lawyer's confident demeanor and tailored attire stand out against the casual beachside setting, offering a glimpse into his balanced life between work and leisure.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated and discontinuous."
}
] |
seed42_2854
|
videos/HRA_part0/2854.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 coyote, with a gray and cream coat, runs across a sunlit prairie, its ears perked and tail held low. It bounds through the tall grass, leaving a slight dust cloud in its wake, indicating speed and purpose. The coyote's focused gaze and agile movements showcase its hunting prowess, as it navigates the open landscape under a clear blue sky. Moments later, it leaps over a small obstacle, demonstrating its agility and grace, all while maintaining its steady pace across the vast, golden plains.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the hyena running and jumping on the grassland, but the movements are not continuous and smooth, and there is a lack of coordination."
}
] |
seed46_1741
|
videos/HRA_part2/1741.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male janitor, dressed in a gray sweater over a white collared shirt and khaki pants, pauses from his cleaning duties to take deep breaths, standing in a brightly lit, modern office hallway. He holds a mop in his right hand and rests his left hand on a mop bucket, while his eyes are closed, focusing on his breathing. The clean, minimalist surroundings emphasize the tranquility of the moment as he takes a moment to collect himself, his facial expression one of peaceful concentration.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands in the video have some issues."
}
] |
seed44_11
|
videos/HRA_part1/11.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rocky terrain below. It circles gracefully, riding the thermals, with a backdrop of lush green mountains and a distant waterfall. Its piercing yellow eyes scan the landscape, searching for prey, while its sharp talons remain ready to strike. The eagle's brown and white plumage glistens in the sunlight, a symbol of freedom and strength against the stunning natural scenery.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_20
|
videos/HRA_part1/20.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female cashier with a headband, working at a checkout counter filled with various snacks and beverages, gently caresses a stuffed cheetah. The stuffed animal is placed on the counter next to a cash register, amidst a selection of candy bars. The woman looks lovingly at the toy, her hands tenderly stroking its soft fur, as if sharing a moment of affection with an imaginary companion in the midst of her daily routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_163
|
videos/HRA_part0/163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a brown jacket over a white shirt and blue jeans, stands in a well-lit, rustic farm supply store. He meticulously organizes shelves filled with neatly arranged seed packets, each labeled with vibrant illustrations of the crops they contain. The scene conveys a sense of preparation and anticipation for the upcoming planting season, with the farmer's careful attention to detail highlighting the importance of organization in farming. Behind him, additional shelves stocked with farming tools and equipment create a backdrop that reinforces the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand generation in the video has issues; a seed pack suddenly appears in the character's hand in the middle frames."
}
] |
seed46_1120
|
videos/HRA_part2/1120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull, distinguished by its gray wings, white body, and yellow legs, stands prominently on a sandy beach. It faces left, capturing its silhouette against a stunning sunset. The bird's right wing is slightly raised, creating a dramatic effect. Its beak, also yellow, is curved, adding to its distinctive appearance. In another scene, the seagull takes flight, soaring above the ocean waves, its wings fully extended, against a clear blue sky. The final shot focuses on the gull's piercing eyes, accentuated by its white feathers, as it perches on a rocky outcropping, offering a compelling close-up of this resilient bird.]"
},
{
"from": "gpt",
"value": "Bad. The seagull's head is deformed, it has an extra pair of wings, and its claws are twisted."
}
] |
seed42_1882
|
videos/HRA_part0/1882.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated female nurse, clad in a white uniform and wearing her hair in a bun, attentively checks a smoke detector mounted on the ceiling in a modern hospital hallway. The space is pristine and well-lit, with pale green walls and white trim, exuding a sense of cleanliness and professionalism. The nurse, displaying her commitment to safety, uses a long, red-handled tool to test the device, ensuring it functions properly in the healthcare environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1306
|
videos/HRA_part2/1306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up of a rotisserie chicken, golden brown and crispy-skinned, slowly turning on a spit under the glow of overhead lights. The chicken is surrounded by an array of fresh vegetables, including bell peppers, onions, and tomatoes, which are also roasting alongside it. The scene is set in a bustling open-air market, with the rotisserie stand positioned between colorful fabric canopies and bustling shoppers. The camera captures the succulent chicken from various angles, highlighting its mouthwatering texture and the aromatic steam rising from it, all against the vibrant backdrop of the market.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1699
|
videos/HRA_part2/1699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a blue button-down shirt and khaki pants, rearranges furniture in a cozy room with wooden floors and a fireplace, aiming to find inspiration. He thoughtfully adjusts a brown leather sofa, placing it at an angle near the hearth, with a glass coffee table in front. Next, he moves a wooden chair with a green cushion to the right side of the sofa, creating a conversational space. Then, he positions a tall bookshelf behind the chair, filled with books and trinkets, adding character to the room. Lastly, he places a small wooden desk with a typewriter next to the window, basking in natural light, perfect for writing, all while maintaining the warm, inviting atmosphere of the space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2891
|
videos/HRA_part2/2891.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a 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": "Bad. The giraffe in the video is overall generated unreasonably."
}
] |
seed46_1718
|
videos/HRA_part2/1718.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 bee-eater perches on a thin branch, its vibrant plumage of green, blue, and orange feathers catching the sunlight. It has a slender body, a long, pointed tail, and a distinctive, curved beak. The bird's eyes are alert, scanning the surroundings for potential prey. Suddenly, it takes flight, its wings a blur of motion as it darts through the air, chasing after an unsuspecting insect. The scene is set against a backdrop of lush vegetation and clear blue skies, capturing the bird's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_209
|
videos/HRA_part0/209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male musician, donning a white button-down shirt and khaki pants, meticulously dusts a vintage gramophone with a feather duster in a warmly lit, cluttered room filled with musical instruments. His attire includes a brown belt and brown shoes, adding to his polished appearance. The room is decorated with a variety of string instruments hanging from the walls, including violins and cellos, highlighting the musician's passion for music. Throughout the scene, he continues to dust various objects, showcasing his dedication to preserving his cherished belongings, all within the cozy, wood-paneled space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1274
|
videos/HRA_part1/1274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged fisherman, clad in a yellow raincoat and matching hat, stands waist-deep in the water, his gaze fixed on the horizon. His hands, weathered from years of labor, expertly handle the fishing net as he casts it into the vast, shimmering sea. The early morning sun bathes the scene in a golden glow, casting long shadows and highlighting the droplets of water clinging to the net. Seagulls circle overhead, their calls adding to the serene atmosphere of the coastal landscape. In the distance, the silhouette of a small fishing village can be seen, smoke rising from the chimneys of the quaint houses, a reminder of the community that thrives on the fruits of the sea.]"
},
{
"from": "gpt",
"value": "Normal. The seagull generation in the video has issues."
}
] |
seed46_2393
|
videos/HRA_part2/2393.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A tiny, charming finch perches on a thin branch, its olive-green feathers blending harmoniously with the lush foliage of a tree set against a clear blue sky. The bird turns its head, revealing its distinct facial markings and vibrant yellow underbelly, before it takes flight, its wings beating rapidly against the crisp air. It lands gracefully on another branch, where it joins a group of similar finches, their chirping filling the serene atmosphere of the woodland scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3133
|
videos/HRA_part1/3133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature man with graying hair, dressed in a white T-shirt and black exercise pants, stretches his body against a gray studio wall. He leans forward with his right leg extended, foot against the wall, and his left leg bent, demonstrating flexibility. His hands rest on his right thigh and shin, while his head tilts down, showcasing a focused expression. Behind him, a large window reveals a blurred outdoor view, adding depth to the scene. The room is illuminated by soft, natural light, highlighting the man's dedication to maintaining his physical health.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1890
|
videos/HRA_part2/1890.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a green vest and khaki pants, walks purposefully down a dimly lit hallway, pushing a squeaky cleaning cart. On the wall, a badger mascot poster from a local college, Wausau Woodchucks, adds a touch of whimsy. The scene shifts slightly to reveal more of the hallway, showcasing the linoleum floor and overhead lights. The janitor continues his journey, passing a row of lockers adorned with stickers and graffiti, while the badger poster remains visible, adding a sense of character to the otherwise mundane setting. Finally, the focus is on the janitor's interaction with the environment, as he pushes the cart with determination, the badger poster serving as a silent observer in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1810
|
videos/HRA_part2/1810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrial engineer in a gray shirt and khaki pants stands confidently in a modern factory, surrounded by large machinery and pipes, with a swimming pool visible through a window in the background. He then walks purposefully toward the camera, passing by the heavy industrial equipment, with the pool still visible in the distance. Next, he is seen from behind, approaching a large machine with pipes, while the pool can be glimpsed outside through the window. Finally, the engineer takes a break from his work, enjoying a refreshing swim in the outdoor pool, which is now the focal point, set against the backdrop of the industrial facility.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2673
|
videos/HRA_part1/2673.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in casual attire, leaps into the air against the backdrop of a vibrant village scene. The village is set amidst lush greenery, with colorful houses lining the cobblestone streets. The student, wearing a yellow t-shirt and denim shorts, is captured mid-jump, their arms spread wide in exhilaration. The scene is filled with natural beauty, from the verdant foliage to the clear blue sky above. As the student jumps, they seem to embody the spirit of youth and adventure, their face alight with joy and energy. Behind them, the village bustles with life, with locals going about their daily routines and children playing nearby. The overall effect is one of vitality and happiness, capturing a fleeting moment of pure delight in a picturesque village setting.]"
},
{
"from": "gpt",
"value": "Bad. The student in the video has missing limb generation, facial distortion, and disharmonious body generation."
}
] |
seed46_2996
|
videos/HRA_part2/2996.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a black puffer jacket and dark cap, oversees a futuristic space sports event. He is surrounded by a vast, otherworldly landscape, with distant celestial bodies visible in the sky. Athletes in high-tech gear compete in zero-gravity, performing acrobatic maneuvers against the backdrop of a grandstand filled with spectators. The scene is dynamic, featuring fast-paced action and dramatic wipe transitions between shots, capturing the intensity and spectacle of the extraterrestrial competition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2013
|
videos/HRA_part1/2013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow safety vest, blue jeans, and brown work boots, stretches his body against the backdrop of a building site at sunrise. His routine begins with him bending forward, touching his toes, and then transitioning into a series of stretches that showcase his physical preparation for the day ahead. Throughout the sequence, his attire remains consistent, and the background features a partially constructed building and other workers in the distance, highlighting the early morning setting at the worksite.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1262
|
videos/HRA_part1/1262.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lush subtropical wet forest, an enthusiastic teacher, wearing a green shirt and khaki shorts, energetically dances among tall trees, their leaves forming a dense canopy overhead. The educator gracefully leaps and twirls, engaging with the natural surroundings, while a curious hare watches from the undergrowth, its ears perked up in interest. Sunlight filters through the foliage, casting dappled shadows on the forest floor, enhancing the magical atmosphere as the teacher continues to dance, celebrating the beauty of the environment with joyful movements.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, and the legs are severely deformed."
}
] |
seed42_2298
|
videos/HRA_part0/2298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, industrial warehouse space filled with rows of neatly stacked boxes, a doctor, identifiable by her stethoscope draped around her neck and wearing a white lab coat over a blue shirt, performs an unexpected action. She leaps into the air with an expression of pure joy, her feet leaving the ground, and her arms spread wide, capturing a moment of uninhibited happiness amidst the sterile environment. The high-definition shot captures the contrast between the clinical setting and the doctor's spontaneous act of exuberance.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's face, limbs, and stethoscope in the video are generated distorted."
}
] |
seed46_1142
|
videos/HRA_part2/1142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gaunt writer, clad in a brown leather jacket, gray t-shirt, and dark jeans, crawls through a desert landscape, reminiscent of a jackal, with a vintage typewriter strapped to his back. The scene opens with him crawling on sandy terrain, his face reflecting determination and resolve. Next, he continues his arduous journey, his clothes and skin stained with dirt, showcasing his unwavering commitment to his craft. The camera then captures him from above, emphasizing his small figure against the vast, barren environment. Lastly, he pauses to rest, the camera focusing on his weathered hands as they gently touch the typewriter, symbolizing his dedication and the intimate connection between the writer and his instrument.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video is walking, not crawling, and there is a lack of scenes where they stop to rest or lightly touch the typewriter."
}
] |
seed42_2843
|
videos/HRA_part0/2843.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, clad in a navy-blue jacket adorned with badges and a matching hat, diligently shovels snow from the sidewalk in front of a modest, red-brick building. The scene is set in the early morning hours, as indicated by the dimly lit street and the absence of pedestrians. Snowflakes continue to fall gently from the gray sky, accumulating on the officer's shoulders and the brim of his hat. Despite the cold, he works with determination, clearing a path for safe passage, embodying the spirit of service and community. The shovel he uses is standard issue, with a sturdy wooden handle and a metal blade, further emphasizing the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed42_1136
|
videos/HRA_part0/1136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, donning a red cap, stylish sunglasses, and a gray shirt, stands against a blurred background, engagingly waving at the audience with his right hand. Moments later, he passionately plays his guitar, exuding energy and confidence. He then smiles broadly, his eyes closed, clearly enjoying the music and the connection with his fans. Finally, he returns to waving, his joyful demeanor and dynamic presence captivating the crowd, all set against a backdrop of a lively concert atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2677
|
videos/HRA_part2/2677.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a dark suit, white shirt, and red tie, stands on a chair in a grandiose office with high ceilings, wood-paneled walls, and large windows. He holds a light bulb with one hand, about to screw it into the socket of a chandelier hanging above his head. The room is partially lit by the sunlight filtering through the windows, casting dramatic shadows across the space. Behind him, bookshelves filled with leather-bound law books line the walls, and a large wooden desk sits to the side, cluttered with papers and legal documents. The lawyer's face is serious, focused on the task at hand, as he completes this unexpected duty in his professional environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2050
|
videos/HRA_part0/2050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a futuristic silver jacket and dark pants, races across the barren, rocky terrain of Mars under a stunning night sky filled with stars and two moons. The landscape features red soil and distant Martian mountains, with the Milky Way galaxy prominently visible above. The writer pauses mid-stride, gazing upwards in awe and inspiration, before continuing the run with determination, the dynamic scene capturing the essence of stargazing from the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, and legs are distorted in the video."
}
] |
seed44_1696
|
videos/HRA_part1/1696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a middle-aged doctor, wearing a stethoscope around his neck and a crisp white lab coat over his neatly pressed blue scrubs, finds himself unexpectedly dancing in a vast savanna. As he moves with surprising grace, a curious cheetah, intrigued by the unusual sight, approaches cautiously from the tall grass. The big cat, known for its speed and agility, mirrors the doctor's dance steps, its movements fluid and powerful. The unlikely pair continues their impromptu dance, surrounded by the vast, open landscape, creating a surreal and captivating moment captured in high-definition footage.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the doctor and the cheetah dancing in the video are not smooth and continuous, with the cheetah's limbs showing sudden changes in between frames."
}
] |
seed46_2019
|
videos/HRA_part2/2019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, dressed in a straw hat, blue shirt, and khaki shorts, playfully swims in a clear, freshwater pond, holding a rabbit securely above the waterline. The farmer, now wearing a wide-brimmed hat, blue button-down shirt, and khaki shorts, gently cradles the rabbit, which sits comfortably in his hands, as they both float on the surface of the water. The idyllic scene is set against a backdrop of lush greenery and clear blue skies, capturing the essence of a peaceful rural life.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1255
|
videos/HRA_part2/1255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal space setting filled with stars and galaxies, a beautifully dressed couple exchanges vows during an extraordinary wedding ceremony. A majestic gazelle, adorned with a golden collar and standing on a floating platform nearby, watches the event with calm interest. The bride, in a flowing white gown, and the groom, in a tailored black suit, hold hands tenderly, their faces reflecting deep love and commitment. As they caress each other's faces, the gazelle gently nuzzles the bride's arm, adding a touch of magic and wonder to this celestial union.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_236
|
videos/HRA_part1/236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical dry forest, an empathetic nurse, clad in a white uniform, gently caresses the cheek of an elderly patient sitting on a wooden bench, offering comfort and care amidst the lush, arid surroundings. Nearby, a stethoscope rests on a picnic table, hinting at a medical check-up. The nurse, wearing a white blouse, khaki pants, and a name badge, tenderly touches the patient's arm, conveying compassion and attentiveness. Surrounded by the unique flora of the subtropical dry forest, including cacti and succulents, the scene captures a moment of human connection and medical care in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate a picnic table or stethoscope."
}
] |
seed42_2229
|
videos/HRA_part0/2229.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a majestic brown horse gallops gracefully across the foreground, its muscular form silhouetted against a backdrop of sprawling factories with billowing smokestacks. Amidst this industrial landscape, a group of diverse individuals dressed in vibrant, eclectic clothing forms a stark contrast as they engage in expressive dance moves, their joyous expressions and dynamic movements standing out against the grey, mechanical setting. This unlikely fusion of nature, industry, and human spirit creates a compelling narrative of resilience and vitality.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_268
|
videos/HRA_part0/268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, male, walks through a dense, green forest, its large ears flapping gently. It carries small branches on its back, and its eyes, visible through the foliage, express a sense of peace. The elephant continues its journey, passing by a tree with lush leaves, highlighting the tranquility of its surroundings. It moves forward, its massive body displacing the undergrowth, leaving a path of disturbed vegetation in its wake, all under the shade of towering trees and a filtered light that adds to the serenity of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_119
|
videos/HRA_part2/119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 heartwarming scene, two children, a boy and a girl, are seen gently caressing a juvenile antelope in a lush, green meadow. The boy, wearing a blue shirt and shorts, leans over to pet the animal with a tender smile, while the girl, dressed in a yellow dress, watches adoringly, her hands clasped together. Moments later, the girl takes her turn, stroking the antelope's back as it stands calmly, accepting the affection. The boy looks on with a joyful expression, his right hand raised in excitement. The idyllic setting, complete with verdant grass and blue skies, adds to the peaceful and endearing nature of the interaction between the children and the young antelope.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1393
|
videos/HRA_part0/1393.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a beige jacket, beige pants, and brown shoes, is seen in a close-up shot, wiping his face with a towel, looking exhausted yet determined. Behind him, a kangaroo, possibly a joeey given its smaller size, stands on the lush green grass of what appears to be a vast Australian outback, adding an element of surprise and quirkiness to the scene. The kangaroo's presence suggests an unusual encounter or storyline, while the actor's weary yet resolute demeanor hints at a challenging journey or performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2852
|
videos/HRA_part2/2852.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, dressed in a white shirt, blue overalls, and a wide-brimmed straw hat, runs across a vast, golden wheat field under a clear blue sky. Suddenly, the scene transforms as if by quantum leap, revealing the farmer now sprinting through a futuristic cityscape filled with neon lights and towering skyscrapers. Despite the change, he maintains his determined expression and rustic attire, creating a stark contrast between the rural and urban environments.]"
},
{
"from": "gpt",
"value": "Normal. No flickering neon lights generated."
}
] |
seed46_2715
|
videos/HRA_part2/2715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great blue heron stands tall and majestic in a serene marshland setting, its feathers gleaming under the soft sunlight. The heron's piercing yellow eyes scan the waters intently, its long, sharp bill poised for action. Nearby, lush green vegetation provides a vibrant contrast to the heron's stately form. Suddenly, the heron takes flight, its broad wings gracefully propelling it through the air, against a backdrop of calm water and a clear blue sky dotted with fluffy white clouds. As it soars, the heron's silhouette is beautifully framed by the natural beauty of its marshland habitat.]"
},
{
"from": "gpt",
"value": "Bad. The blue heron in the video is deformed when flying."
}
] |
seed44_1814
|
videos/HRA_part1/1814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a large moose, adorned with a red bow tie and a top hat, stands on a wooden boardwalk illuminated by warm, golden lights. It gracefully sways side to side, as if dancing to an invisible melody, under a starlit night sky. The boardwalk stretches into the distance, lined with quaint shops and twinkling lanterns, creating a surreal and enchanting atmosphere where reality and fantasy blend seamlessly.]"
},
{
"from": "gpt",
"value": "Normal. The moose's movements in the video are not smooth."
}
] |
seed42_1282
|
videos/HRA_part0/1282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young boys, one wearing a red shirt and the other in a white shirt, walk side by side near an oil refinery complex with large tanks and pipes in the background, under a clear blue sky. They stroll along a dirt path, surrounded by the industrial landscape, their expressions serious as they navigate the terrain together. Despite the imposing structures around them, the children maintain a steady pace, their presence creating a stark contrast against the backdrop of the oil facility.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video walks basically normally, with slight lack of coordination and smoothness."
}
] |
seed46_1309
|
videos/HRA_part2/1309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a yellow fire-resistant jacket, leads a calm brown horse into a shallow, clear lake during a sunny day. The firefighter gently guides the horse, which is adorned with a red blanket, into the water. Both the firefighter and the horse are knee-deep in the refreshing lake, surrounded by lush greenery and a peaceful environment, creating a heartwarming and unexpected scene of tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3191
|
videos/HRA_part1/3191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A prehistoric mammoth, its woolly coat dark and shaggy, is seen wading through a cold, icy lake during the last Ice Age. Its large body creates ripples in the water, and it moves with a surprising grace for its size. The mammoth uses its tusks to navigate through the submerged branches and logs, demonstrating its adaptability to aquatic environments. Despite the freezing temperature, the mammoth appears comfortable, showcasing its ability to thrive in harsh conditions. The backdrop is a lush, green landscape with distant mountains, highlighting the diversity of habitats these ancient creatures inhabited.]"
},
{
"from": "gpt",
"value": "Bad. The mammoth's tusks and trunk in the video have generation issues, and there are multiple legs generated."
}
] |
seed46_167
|
videos/HRA_part2/167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, clad in period-specific attire from the late 1800s, including a brown shirt, brown trousers, and brown boots, explores historical sites in a rural setting. He crawls through dense grass to uncover ancient artifacts, revealing a deep interest in history. Against a backdrop of historical ruins, the farmer meticulously examines the site, emphasizing his connection to the land and its past. Throughout, he maintains a focused demeanor, highlighting his dedication to understanding the historical significance of the area.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1098
|
videos/HRA_part0/1098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a futuristic, metallic silver jumpsuit performs an intricate dance routine inside a mammoth spaceship, illuminated by pulsating neon lights. The ship suddenly initiates a hyperspace jump, stars warping into elongated streaks of light in the background, adding a surreal touch to the scene. Despite the gravity fluctuations, the woman continues to dance gracefully, her movements synchronized with the electronic beats emanating from the ship's audio system. Her face, a mix of determination and joy, reflects the vibrant colors of the spaceship's interior, creating a mesmerizing spectacle as she dances amidst the cosmic chaos.]"
},
{
"from": "gpt",
"value": "Bad. The dancing in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed46_1194
|
videos/HRA_part2/1194.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, distinguished by his uniform consisting of a navy blue shirt with badges, dark pants, and black shoes, vacuums the carpet in a modest living room. The room features a small brown couch, a glass coffee table, and a beige recliner, with sunlight streaming through the window, highlighting dust particles in the air. The officer, displaying a serious demeanor, methodically maneuvers the vacuum cleaner across the carpeted floor, revealing his commitment to household chores despite his profession. The domestic scene contrasts sharply with his authoritative attire, emphasizing the duality of his role as both protector and provider.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2965
|
videos/HRA_part1/2965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male writer, dressed in a black turtleneck sweater and khaki pants, walks through a vast grassland with rolling hills under a clear blue sky. He pauses to observe a herd of deer grazing nearby, the animals' presence adding to the tranquility of the landscape. The writer continues his journey, a pen and notebook visible in his pocket, suggesting inspiration drawn from nature. As he moves further into the grassland, the distant silhouette of mountains can be seen, enhancing the sense of adventure and exploration. Throughout the scene, the focus remains on the writer's contemplative walk among the deer, with the vibrant green grass and expansive sky creating a serene and inspiring atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1505
|
videos/HRA_part1/1505.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, plump quail with brown and black speckled feathers stands prominently in the foreground, nestled among lush green foliage that includes leaves, ferns, and tall grasses. It faces left, its head turned slightly toward the camera, revealing its distinctive facial features, including a small beak and alert eyes. The bird's textured feathers are intricately detailed, and its legs are visible as it perches on the forest floor, surrounded by the vibrant flora.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2806
|
videos/HRA_part0/2806.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, wearing a dark blue jacket, beige pants, and carrying a brown backpack, runs along the docks on a misty day, passing by large ships and industrial buildings. He stops momentarily to gaze at the water, his reflection visible in the wet pavement. Continuing his run, he passes wooden benches and green spaces, with the city skyline in the distance. Throughout his journey, he remains engrossed in his thoughts, occasionally glancing down at a notebook tucked into his backpack, the colors of the docks' wood and metal contrasting against the muted tones of the surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1896
|
videos/HRA_part2/1896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, dreamlike sequence, an astronaut clad in a pristine spacesuit gently caresses a bobcat on the lunar surface, under the Earth's watchful gaze. The astronaut's visor reflects the desolate landscape, while the bobcat, undeterred by its extraterrestrial surroundings, responds with curiosity. The scene is illuminated by the distant Earthshine, casting a soft glow on the moon's dusty terrain, highlighting the tenderness of this interstellar encounter.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the astronaut reflecting the desolate landscape."
}
] |
seed46_2320
|
videos/HRA_part2/2320.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor wearing a yellow high-visibility vest and khaki pants walks purposefully down a dimly lit tunnel, holding a flashlight that illuminates the way ahead. The tunnel walls, painted a dull gray, are lined with pipes and electrical conduits, providing a gritty industrial backdrop. Shadows cast by the janitor's flashlight dance on the walls, adding a sense of depth and mystery to the scene. The janitor's steps echo in the confined space, punctuating the otherwise silent atmosphere of the tunnel system.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand in the video has generation issues."
}
] |
seed46_2651
|
videos/HRA_part2/2651.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged doctor, wearing a white lab coat over a blue button-down shirt, sits in a modern office filled with medical equipment. He is holding a pen and papers, looking concerned as he coughs into his right hand. The scene is set indoors, with the doctor seated at a desk cluttered with medical files and supplies. Soft, ambient lighting highlights the professional yet somber atmosphere. The doctor's cough is noticeable, drawing attention to his discomfort amidst the sterile environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1767
|
videos/HRA_part2/1767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary buzzard perches majestically on a barren branch, its piercing eyes scanning the vast, sunlit savannah below for any signs of movement. The bird, with its distinct brown and white plumage, contrasts starkly against the muted tones of the landscape. Suddenly, it spreads its impressive wingspan and takes flight, gliding effortlessly over the terrain. Its sharp talons are clearly visible as it descends with laser-like precision towards a potential meal, showcasing the raw power and agility of this apex predator. The scene is set against a backdrop of rolling hills and scattered trees, bathed in the warm glow of the afternoon sun.]"
},
{
"from": "gpt",
"value": "Bad. The eagle's wings and claws are distorted in the video."
}
] |
seed46_2406
|
videos/HRA_part2/2406.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 warbler perches on a thin branch, its vibrant yellow and olive-green feathers illuminated by the soft sunlight filtering through the dense foliage of a lush forest. Its bright yellow underparts contrast sharply with the olive-green upperparts, while its two wing bars and eyestripe add distinctive touches. The bird's sharp, dark eye is focused intently ahead, and its slender beak is slightly open, as if about to burst into song. The warbler's delicate feet grip the branch firmly, and its tail feathers fan out slightly, adding balance as it prepares to take flight or sing its melodic tune.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the warbler's claws in the video is problematic, with three claws appearing in the middle frame."
}
] |
seed42_1080
|
videos/HRA_part0/1080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna dotted with small shrubs and trees, a large herd of buffalo gathers. Suddenly, one buffalo, distinct with its massive horns and dark brown fur, begins to move rhythmically, almost dancing, against the backdrop of the herd and the distant, hazy mountains. Its movements are energetic yet controlled, as if performing a ritualistic dance under the watchful eye of the herd. The camera focuses on this unique spectacle, capturing the buffalo's dance in the midst of its natural habitat, surrounded by the rest of the herd and the serene beauty of the African landscape.]"
},
{
"from": "gpt",
"value": "Normal. The buffalo's movements are not smooth."
}
] |
seed46_1542
|
videos/HRA_part2/1542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled man, presumably a writer, stands on a ladder, cleaning the rain gutters of a charming, old house. He wears a brown jacket over a checked shirt, blue jeans, and a cap, while holding a long-handled gutter scoop. The scene is set against a backdrop of lush greenery, indicating a peaceful, suburban environment. The writer's focused expression and the tools of his current task, including the ladder, scoop, and a bucket placed on the grass, suggest a dedicated approach to home maintenance. Despite the mundane activity, his attire hints at his dual identity as a creative professional and a homeowner managing everyday chores.]"
},
{
"from": "gpt",
"value": "Bad. The long-handled rain gutter cleaning shovel, and the ladder have issues with generation, and the character's hand suddenly disappears in the middle frames."
}
] |
seed46_332
|
videos/HRA_part2/332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, attired in a khaki safari outfit, navigates through the dense undergrowth of a tropical dry forest. The sunlight filters through the canopy, casting dappled shadows on the rugged terrain. Lush, gnarled trees surround him, their leaves whispering in the gentle breeze. Insects buzz softly in the background, adding to the ambiance of the wild. The director walks purposefully, his boots crunching on the carpet of fallen leaves and twigs, holding a detailed map in one hand and occasionally stopping to consult it, his focus intense and unwavering.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1089
|
videos/HRA_part2/1089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 museum hall, a life-sized jaguar statue leaps across the space, seemingly frozen in mid-air as it jumps from one side to the other. The museum is filled with exhibits of historical artifacts, including ancient pottery and weaponry displayed in glass cases along the walls. The jaguar, crafted with intricate details and positioned mid-jump, captures the animal's agility and power, making it the focal point of the room. Its leap is so vividly portrayed that it appears ready to pounce at any moment, adding a dynamic element to the otherwise static environment.]"
},
{
"from": "gpt",
"value": "Normal. The jaguar's movements in the video are not smooth."
}
] |
seed44_306
|
videos/HRA_part1/306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, donning a white tank top, beige shorts, and brown leather sandals, assembles a wooden table in a bright room with large windows and a view of greenery outside. He starts by carefully examining the instructions, his brows furrowed in concentration. Next, he skillfully uses a screwdriver to attach the legs to the tabletop, showcasing his handyman abilities. Then, he wipes his forehead with the back of his hand, a small smile on his lips, indicating satisfaction in his progress. Finally, he stands back to admire the finished product, hands on hips, revealing the completed table in the well-lit space, surrounded by lush vegetation visible through the window.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.