video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2626
|
videos/HRA_part0/2626.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a cluster of jellyfish, predominantly moon jellyfish, gracefully floats in a harmonious formation. Their translucent bell-shaped bodies, illuminated by a soft blue light, reveal intricate patterns and textures. Surrounding them are various marine creatures, including small fish and other jellyfish species, adding to the vibrant ecosystem. The jellyfish pulsate rhythmically, propelling themselves through the water, while their trailing tentacles gently undulate, creating a mesmerizing visual display in this serene aquatic environment.]"
},
{
"from": "gpt",
"value": "Normal. The jellyfish's body is slightly distorted in the video."
}
] |
seed46_1234
|
videos/HRA_part2/1234.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic individual named Jay, donning a stylish gray jacket, a black turtleneck, and dark jeans, stands against a backdrop of city lights and a bridge, exuding confidence. He is captured in various poses, first looking directly at the viewer with a serious expression, then showing a side profile with a contemplative look. Jay then smiles warmly, showcasing his friendly demeanor, before striking a cool pose with his hands in his pockets, gazing into the distance. Throughout, the urban landscape behind him complements his modern style and enigmatic persona.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2292
|
videos/HRA_part0/2292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest and hard hat, finds himself in an unexpected scenario as he runs alongside a monkey, both moving rapidly across a cluttered urban environment. The worker, with a rugged appearance and a backpack, navigates through a cityscape filled with scaffolding and construction materials. Meanwhile, the monkey, displaying a mischievous yet determined demeanor, keeps pace, highlighting an unusual companionship between human and primate in a bustling urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's body is twisted, head is twisted, legs are twisted, arms are twisted, the monkey's body is twisted, legs are twisted."
}
] |
seed46_2568
|
videos/HRA_part2/2568.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A giant panda, clad in a red jacket and black pants, races through a city park surrounded by towering skyscrapers, lush greenery, and a clear blue sky. The panda, sporting sunglasses and a determined look, sprints past urban landmarks, including a towering glass building and a bridge. In another scene, the panda leaps over a log, its athletic prowess on full display against the cityscape backdrop. Finally, it continues its run, moving right to left across the screen, with the vibrant city as its dynamic setting.]"
},
{
"from": "gpt",
"value": "Bad. The panda's face and limbs in the video were generated abnormally, and the clothes on the panda's body suddenly disappeared in the middle frames."
}
] |
seed44_1197
|
videos/HRA_part1/1197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a plush koala toy, donning a red pilot's cap and a blue jacket, is placed on a model airport set, complete with miniature airplanes and runways. Suddenly, the koala begins to dance, swaying side to side with its arms raised, against a backdrop of a bustling airport terminal, filled with travelers and overhead announcements. The stuffed animal continues its lively jig, spinning around on the toy runway, surrounded by small figurines of people and luggage carts, capturing the imagination and playfulness of travel and adventure.]"
},
{
"from": "gpt",
"value": "Bad. The bear's body undergoes sudden changes and deformations while dancing."
}
] |
seed42_1089
|
videos/HRA_part0/1089.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit 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": "Good. No obvious problems."
}
] |
seed42_1912
|
videos/HRA_part0/1912.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bald musician, donning a black turtleneck, focuses intently on fixing a leaky faucet in an upscale bathroom with marble countertops. Initially, he looks thoughtful, holding a wrench and examining the faucet. Moments later, he is seen tightening the faucet with the tool, his sleeves rolled up, revealing a tattoo on his arm. He then tests the faucet, turning it on and off, ensuring no leaks remain. Finally, he wipes his hands on a towel, looking satisfied with his handiwork, all set against the backdrop of a luxurious bathroom with a marble sink and countertop.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1891
|
videos/HRA_part2/1891.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling airport terminal, a large, lifelike panda costume lays on its side, partially inflated, as a person inside attempts to crawl into it. The individual struggles comically within the confines of the costume, drawing curious glances from nearby travelers. Once fully inside, the person begins to crawl across the airport floor, the oversized panda head bouncing with each movement, creating a surreal and amusing scene amidst the typical airport chaos. Passengers of all ages watch in amusement, some capturing the unusual sight on their phones, as the person in the panda suit continues to crawl, adding a touch of whimsy to the otherwise ordinary airport environment.]"
},
{
"from": "gpt",
"value": "Bad. The panda person's body is twisted, with twisted arms and legs, and the faces and bodies of the surrounding people are also twisted."
}
] |
seed46_2327
|
videos/HRA_part2/2327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A pufferfish, with its distinctive round shape and small size, swims gracefully in a vibrant coral reef environment. Its body, covered in tiny, pebble-like protrusions, is a mix of yellow and white with intricate black patterns. The fish inflates to nearly twice its original size, demonstrating its defense mechanism against potential predators lurking among the colorful corals and marine life surrounding it. The water is crystal clear, allowing every detail of the pufferfish's unique appearance and behavior to be captured in stunning high definition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1487
|
videos/HRA_part1/1487.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a realistic zebra, complete with black and white stripes, finds itself crawling under a barrier typically found at train stations. The striped animal moves slowly and carefully, its body almost touching the ground, as it navigates beneath the yellow and black-striped barrier. The train station's typical features, such as tracks, platforms, and overhead signs, are visible in the background, adding to the surreal nature of the scene. The zebra's unusual behavior in this urban setting creates a striking and memorable image.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2012
|
videos/HRA_part2/2012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gentleman, presumably a writer, sits at a grand dining table, meticulously polishing silverware with a white cloth. He wears a dark blue blazer, a button-down shirt, and glasses, presenting a scholarly appearance. The room is dimly lit, with the only bright spot being the gleam from the silver as he works. The setting suggests a large, elegant dining hall, possibly in an old mansion, where the writer has taken on the unexpected task of preparing the cutlery. His focus and precision convey a sense of dedication to the task, contrasting with his intellectual pursuits.]"
},
{
"from": "gpt",
"value": "Bad. The gentleman's hand in the video has generation issues."
}
] |
seed42_1548
|
videos/HRA_part0/1548.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station with panoramic views of Earth and the cosmos, a distinguished lawyer, dressed in a sharp black suit and red tie, energetically jumps into the air with a triumphant smile. The room is elegantly lit with a blue hue, highlighting the advanced technology and sophistication of the space environment. The lawyer's enthusiastic leap is juxtaposed with the serious atmosphere of a political summit, where delegates from various planets gather to discuss intergalactic policy. The unique setting and dynamic action capture the essence of a thrilling and significant event in the realm of space politics.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_186
|
videos/HRA_part2/186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of cheerful children, ranging from toddlers to preteens, are engaged in the task of cleaning windows on a bright, sunny day. They wear casual clothes, including t-shirts, shorts, and sneakers, and sport various hairstyles, from pigtails to afros. The kids use squeegees and rags to wipe down the glass, leaving streaks of water and soap behind. They work together, laughing and chatting, as they tackle the large window panes of a suburban home, with lush greenery visible through the transparent surfaces. The atmosphere is one of teamwork and fun, with the youngsters taking pride in their chores under the warm glow of the sun.]"
},
{
"from": "gpt",
"value": "Bad. Their hands suddenly elongate and deform in the middle frames."
}
] |
seed42_121
|
videos/HRA_part0/121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene indoor scene opens with a close-up of a calm, gray tabby cat sitting on a wooden floor next to a white wall. The cat, adorned with a blue collar, gazes intently at the camera. Suddenly, a human hand enters the frame from above, gently stroking the cat's head, evoking a relaxed response. The camera then captures the affectionate interaction from various angles, showcasing the cat's contentment and the tender touch of the unseen person, all within the cozy confines of a home environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1833
|
videos/HRA_part0/1833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white dove with intricate feather patterns perches on a branch, nestled among lush green leaves that contrast beautifully with its pure white plumage. The bird looks towards the camera, revealing its detailed eye and beak. It then spreads its wings, displaying the impressive span and the delicate feather layers that catch the light, before taking flight against a clear blue sky, symbolizing peace and freedom. The final shot captures the dove soaring gracefully, its silhouette framed against the vastness of the sky, leaving behind a trail of tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2592
|
videos/HRA_part2/2592.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 focused young student sits at a wooden desk in a well-lit classroom, diligently sewing a button onto a piece of light blue fabric using a thin needle and white thread. The student, wearing a gray hoodie and blue jeans, attentively works on the sewing project, which is placed atop a larger piece of white fabric. The room is filled with natural light from a nearby window, illuminating the task at hand and highlighting the student's concentration and skill in performing this traditional craft.]"
},
{
"from": "gpt",
"value": "Bad. The hand movements of the person in the video are not smooth."
}
] |
seed46_1448
|
videos/HRA_part2/1448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room with large windows, a brown bear cub stands on its hind legs, curiously exploring its surroundings at the Space Education Center, filled with educational displays about astronomy. The bear is spotted wiping its nose with a paw, drawing attention to its adorable antics among the exhibits. The scene is set against a backdrop of a large, round, gray planetarium screen, adding a cosmic touch to the unexpected encounter between wildlife and space knowledge.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there is a sudden change."
}
] |
seed42_185
|
videos/HRA_part0/185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, clad in a casual black jacket and gray trousers, runs energetically across a large, open room within a space-themed educational facility. The room is adorned with detailed models of the Apollo spacecraft and other historical rockets, highlighting the center's focus on space exploration. As he moves, the director passes by a group of attentive students seated at tables, each engaged with interactive exhibits about space missions. The vibrant atmosphere reflects the excitement and educational value of the space center, emphasizing its commitment to inspiring the next generation of astronauts and scientists.]"
},
{
"from": "gpt",
"value": "Bad. The director's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_2758
|
videos/HRA_part1/2758.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a red plaid shirt, blue jeans, and a wide-brimmed straw hat, diligently sweeps his wooden porch with a long-handled broom, the early morning sun casting a warm glow over the rural scene. Beside him, a white dog rests lazily on the porch, enjoying the peaceful ambiance. The farmer pauses to wipe sweat from his brow, revealing a face lined with years of hard work and dedication to his land. He continues sweeping, the rhythmic sound of the broom against the wood providing a soothing soundtrack to the quiet countryside morning. Behind him, a lush green landscape stretches out, dotted with crops and farm buildings, a testament to his labor and connection to the earth.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand in the video is deformed, and in the middle frames, the man's hand and the broom in his hand suddenly distort, deform, or disappear."
}
] |
seed42_1761
|
videos/HRA_part0/1761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling train station filled with travelers, a diligent janitor wearing a yellow high-visibility vest is wiping down a large window, revealing the vibrant cityscape outside. The scene is set during the daytime, with bright sunlight illuminating the interior of the station. Among the crowd, a person dressed in a panda costume stands out, adding a whimsical touch to the busy environment. The janitor continues to clean the window, ensuring a clear view of the passing trains and the urban landscape beyond.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_287
|
videos/HRA_part1/287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a classic white uniform and a colorful headscarf, is seen energetically cleaning windows in a brightly lit hospital room. She moves with purpose, using a squeegee to clear away streaks, while patients rest peacefully in beds adorned with vibrant floral sheets. Sunlight filters through the partially cleaned panes, casting a warm glow over the serene space. In the background, a bustling city skyline is visible, contrasting the calm atmosphere within the room. The nurse's dedication to her task is evident in her focused expression and the gleaming glass that reflects her hard work.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's fingers in the video are deformed, and the patient is generated blurry."
}
] |
seed46_131
|
videos/HRA_part2/131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a red checked shirt, brown overalls, and a wide-brimmed hat is seen in a whimsical setting, sharing an unexpected dance with a playful otter. They are surrounded by lush green fields and vibrant wildflowers, with a rustic barn in the background. The otter, holding a miniature top hat, playfully imitates the farmer's dance moves, adding to the charming and surreal atmosphere. The farmer's joyful expression and the otter's animated antics create a heartwarming scene that celebrates the unexpected connections between humans and nature.]"
},
{
"from": "gpt",
"value": "Bad. Two otters appeared."
}
] |
seed44_2504
|
videos/HRA_part1/2504.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, clad in a white lab coat and protective goggles, embarks on an extraordinary adventure, crawling through a meticulously detailed, space-themed diorama. This unique setting features a realistic comet in pursuit, depicted through dynamic lighting and visual effects, creating an engaging narrative. The doctor, equipped with a futuristic tool kit, exhibits determination and focus, navigating the challenging terrain with precision. The comet, represented by a meticulously crafted model, trails closely behind, adding a thrilling element to the scene. Throughout the video, the doctor's journey is portrayed with a blend of scientific curiosity and cosmic wonder, set against a backdrop of meticulous craftsmanship and vivid imagination.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2452
|
videos/HRA_part1/2452.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a yellow jacket and black trousers, stands on a glacier, performing maintenance on a piece of equipment. The scene opens with a close-up of his hands, wearing black gloves, carefully wiping ice from a sophisticated device. The vast, icy landscape stretches behind him, with the sun casting a warm glow on the cold environment. As he continues to wipe away the frost, the camera pans out to reveal the enormity of the glacier and the solitude of his task. The engineer's focused expression and the stark beauty of the icy terrain provide a captivating contrast in this high-definition shot.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's action of wiping frost off the precision device with his hand is basically normal, but there is slight disharmony."
}
] |
seed46_220
|
videos/HRA_part2/220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sun-drenched subtropical shrubland, a striking red fox gently caresses the foliage with its bushy tail as it moves gracefully through the sparse landscape. The fox, with its vibrant fur and alert demeanor, interacts tenderly with the arid environment, highlighting the delicate balance between predator and habitat. Against the backdrop of scrub vegetation and scattered trees, the fox's movements convey a sense of care and connection to the natural world.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the red fox in the video are missing, the tail is excessively long, and the face is deformed."
}
] |
seed44_1778
|
videos/HRA_part1/1778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 actor, casually dressed in a dark gray t-shirt and black sweatpants, attentively unloads a dishwasher in a modern kitchen. The space features sleek white cabinets, a stainless steel refrigerator, and a large window allowing natural light to illuminate the room. He carefully places dishes into cupboards, revealing a methodical approach to the task. With a half-smile and relaxed posture, he demonstrates an unexpected domestic side, contrasting his typical on-screen persona. Throughout the scene, the kitchen remains orderly and clean, emphasizing the mundanity of the chore juxtaposed with his celebrity status.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2249
|
videos/HRA_part0/2249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a firefighter, dressed in full gear except for a red chicken hat, crawls through a dimly lit, misty hot springs area. The water reflects the ambient light, creating an ethereal glow around the unique character. Surrounded by the steamy, rocky landscape of the hot springs, the firefighter continues to crawl, adding an element of intrigue to the surreal setting.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's face generation in the video has problems."
}
] |
seed46_2158
|
videos/HRA_part2/2158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a gray shirt and khaki pants, sits in a modern office space with a clean desk, listening intently. He leans forward with his right elbow on his knee, his face partially covered by his right hand, and his eyes closed, indicating deep concentration. His left hand rests on a high-tech, silver-colored device, possibly a piece of machinery or equipment, while a large screen displays complex diagrams and data in the background. The office is illuminated by natural light from a window, casting a soft glow on the engineer and his workspace.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
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 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 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": "Bad. The video shows the director waving and the athletes performing their competitive moves, but the actions are not very fluid and there is a lack of coordination."
}
] |
seed42_2312
|
videos/HRA_part0/2312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male chef, donning a white chef's uniform with black stripes and a matching cap, meticulously washes dishes in a commercial kitchen. The room is illuminated by bright overhead lights, casting a glow on the stainless steel sink and countertops. Steam rises from the hot water, creating a misty atmosphere. The chef's sleeves are rolled up to his elbows, revealing tattoos, as he focuses intently on cleaning each plate with precision and care. In the background, the bustling kitchen is visible, with other chefs preparing meals and the sounds of clattering pots and sizzling pans adding to the lively ambiance.]"
},
{
"from": "gpt",
"value": "Bad. The male chef in the video has uncoordinated movements while washing the dishes."
}
] |
seed44_1984
|
videos/HRA_part1/1984.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station newsroom, illuminated by soft blue and orange lights, a realistic animated rabbit, wearing a small suit and tie, sits at a sleek desk. The room is filled with high-tech equipment and screens displaying galactic maps and data. The rabbit, with a serious expression, reads from a teleprompter, delivering the latest space news. Suddenly, the scene changes to the same rabbit running energetically on a treadmill, surrounded by floating zero-gravity objects, including a pen, a book, and a coffee cup, all set against the backdrop of the Earth through a large window.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2051
|
videos/HRA_part1/2051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed anthropomorphic fox, wearing a doctor's white lab coat over a crisp blue shirt and a stethoscope around its neck, is seen swimming in a clear blue pool. The fox maintains a relaxed yet focused expression, showcasing its unique ability to swim effortlessly while fully clothed. The pool is surrounded by lush greenery, creating a serene atmosphere as the sunlight filters through the leaves, casting dappled shadows on the water's surface.]"
},
{
"from": "gpt",
"value": "Normal. The fox's movements in the video are slightly unsmooth."
}
] |
seed42_1564
|
videos/HRA_part0/1564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white shirt and brown trousers, leads a llama on a leash through the verdant pathways of a zoological park, surrounded by lush greenery and exotic plants. The llama, adorned with a decorative blanket and colorful tassels, follows obediently as the farmer guides it past various enclosures housing different species. They walk alongside a water feature, such as a pond or stream, adding to the tranquil atmosphere of the park. The farmer's attire complements the natural surroundings, creating a harmonious scene as they navigate the scenic route together.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1080
|
videos/HRA_part2/1080.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna 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": "Bad. When the water buffalo moved, two bodies of the water buffalo appeared with multiple legs."
}
] |
seed42_194
|
videos/HRA_part0/194.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sparrowhawk soars gracefully in a clear blue sky, its sharp eyes scanning the grassy meadows below for prey. Its body is a sleek silhouette against the brightness, with a prominent head and compact wings. It then swoops down with remarkable agility, talons extended, targeting a small rodent in the tall grass. The bird's plumage is a striking mix of brown and gray, with a white underbelly marked by dark bands, as it lands on a branch, alert and ready to strike again. Finally, it takes flight once more, its powerful beats and aerodynamic form cutting through the air with precision, embodying the essence of a skilled avian predator.]"
},
{
"from": "gpt",
"value": "Bad. The goshawk's wing movements in the video are uncoordinated."
}
] |
seed46_1623
|
videos/HRA_part2/1623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, likely his cub, against the backdrop of a lush, green savannah during the golden hour. The father lion, with his thick, dark mane, displays affection and protection as he rubs his cheek against the cub's head. The cub, with its curious eyes and playful demeanor, responds with a nuzzle of its own, showcasing the intimate bond between them. This heartwarming interaction unfolds under a sky painted with warm hues of orange and pink, highlighting the emotional connection between the two lions.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the male lion rubbing against the cub and the cub rubbing against the male lion are basically normal, with only slight awkwardness."
}
] |
seed46_1495
|
videos/HRA_part2/1495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 powerful buffalo, its body robust and muscular, leaps gracefully over a wooden fence in the midst of a lush, green prairie. The fence, made of weathered logs, stretches across the frame, adding texture and depth to the scene. The buffalo, its large horns curving outward, is captured mid-jump, showcasing its agility and strength. The background is filled with the vibrant hues of nature, from the deep greens of the grass to the soft blues of the sky, creating a stunning contrast against the dark brown of the buffalo. This majestic creature, defying expectations with its leap, embodies the spirit of the wild, free and untamed.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the water buffalo in the video are generated unreasonably, and there is a clipping issue between the fence and the water buffalo."
}
] |
seed42_1925
|
videos/HRA_part0/1925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 male silverback gorilla, marked by a prominent sagittal crest and large, powerful body, crawls through dense, lush vegetation in a misty, mountainous habitat. His dark fur stands out against the vibrant greenery, and his expressive face, complete with attentive eyes and a strong jawline, conveys a sense of intelligence and strength. The scene is set in a protected wildlife reserve, where the gorilla moves purposefully through the undergrowth, highlighting the beauty and resilience of these endangered primates in their natural environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1300
|
videos/HRA_part2/1300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and beige pants, paints a vivid mural featuring a gorilla on a brick wall, surrounded by lush greenery. The gorilla, depicted in motion, seems to be running across the artwork, blending seamlessly with the real-world setting. The artist's focused gaze and deft brushstrokes capture the essence of movement and life, merging the realms of art and nature in a captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2166
|
videos/HRA_part1/2166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned janitor, clad in a gray jumpsuit with a yellow utility vest over it, diligently wipes down a pristine, metallic surface within a bustling space station habitat. The vibrant blue and white Earth can be seen through a large window in the background, providing a stunning contrast to the industrial interior. As he works, the man pushes a cleaning cart filled with various supplies, emphasizing his commitment to maintaining the cleanliness of the space station. Nearby, two fellow crew members, wearing matching gray jumpsuits with red accents, are engaged in a conversation, adding to the lively atmosphere of the space habitat. Throughout the scene, the janitor continues his task with a focused determination, highlighting the importance of his role in the maintenance of the space station.]"
},
{
"from": "gpt",
"value": "Bad. The background only generated one crew member wearing the same gray work uniform with red trim."
}
] |
seed46_2186
|
videos/HRA_part2/2186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful gazelle, marked with distinctive black chevrons on its rump, sprints across the frame, its hooves kicking up mist from a bubbling hot spring. The background features a vast, arid savanna with distant mountains and sparse vegetation. The gazelle, its coat a sandy brown hue, bounds over the water's edge, sending plumes of steam into the air with each leap. In the foreground, the hot spring's milky, turquoise waters simmer and bubble, contrasting starkly with the dry landscape. The sky above is a vivid orange, indicating either sunrise or sunset, casting a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Bad. The gazelle's jumping action in the video is not smooth."
}
] |
seed42_2897
|
videos/HRA_part0/2897.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique close-up of a baby kangaroo, or joey, wearing a red pouch, crawls on its front limbs across a wooden surface, demonstrating its early stages of mobility. The joey, with its distinctive marsupial features, including large ears and a small snout, is captured in high definition, revealing the intricate details of its fur and movements. Against a simple wooden background, the joey's red pouch stands out, adding a pop of color to the frame. The focus remains solely on the joey throughout, as it diligently crawls forward, showcasing its determination and innocence.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1257
|
videos/HRA_part2/1257.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a red jacket, gray beanie, and blue jeans, hikes through a dense forest with sunlight filtering through the trees, casting dappled shadows on the trail. They pause to observe a small stream, the water gently flowing over rocks, before continuing on the path, notebook in hand, ready to capture inspiration from nature's beauty. The scene focuses on the writer's contemplative gaze, the vibrant colors of autumn leaves surrounding them, and the peaceful atmosphere of the woodland setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2199
|
videos/HRA_part0/2199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 porcupine, with its distinctive quills standing out, is seen in a detailed close-up, wiping its face with a paw in a natural habitat, perhaps after eating or sensing its surroundings. The camera captures the intricate details of the porcupine's quills, the texture of its fur, and the precise movements of its paw as it carefully wipes across its face, all set against a backdrop of lush greenery, indicating a serene and undisturbed environment.]"
},
{
"from": "gpt",
"value": "Bad. The porcupine's movements in the video are not smooth and are uncoordinated."
}
] |
seed44_1840
|
videos/HRA_part1/1840.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, dressed in a yellow safety vest over a gray shirt and black pants, experiences time dilation as he leaps into the air in a high school gymnasium. The scene is captured from four different angles: first, he is seen standing still, looking at the camera. Then, he jumps into the air, the motion slowed down to emphasize the effect of time dilation, his posture mid-leap. In the next frame, he is frozen mid-air, with a basketball hoop and a volleyball net visible in the background. Lastly, he is shown in slow motion again, this time with a look of determination on his face, highlighting the unique experience of time distortion during his jump.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video is distorted, with a twisted face, twisted arms, twisted legs, and twisted hands."
}
] |
seed46_3063
|
videos/HRA_part2/3063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and utility belt, walks alongside a cheetah on a leash in an urban park setting. The officer, wearing sunglasses and a cap, maintains a calm demeanor as they stroll together. The cheetah, fitted with a specialized harness, looks up attentively, its spots clearly visible against the green foliage of the park. The pair meanders past park benches and trees, creating an unusual yet harmonious scene of law enforcement and wildlife coexisting in a city environment.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's head and limbs are generated abnormally, and the police officer's hands are uncoordinated."
}
] |
seed44_2153
|
videos/HRA_part1/2153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man walks through dense chaparral vegetation, his form occasionally obscured by the thick foliage. He wears a white tank top, beige cargo shorts, and brown hiking boots, his appearance contrasting with the lush greenery. His right hand grasps a walking stick, aiding his navigation through the rugged terrain. As he strides forward, his left arm swings freely, while his right arm, holding the stick, punctuates each step. The vibrant green of the chaparral plants envelops him, emphasizing his journey through this wild landscape.]"
},
{
"from": "gpt",
"value": "Bad. Both hands and legs show deformities and distortions."
}
] |
seed44_1653
|
videos/HRA_part1/1653.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, balding with graying hair, stands on a vibrant red carpet at a film festival, his eyes welling up with tears. He wears a classic black tuxedo, complete with a bow tie and a white pocket square, his attire reflecting the formal event. In the next scene, he is seen wiping away tears with a handkerchief, his emotional response to a significant moment captured in high definition. Throughout the footage, the director's facial expressions convey a range of emotions, from initial composure to visible vulnerability, all set against the backdrop of the glamorous film festival setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated, the eyes are not quite right, and the paper in his hand is generated unreasonably."
}
] |
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 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, 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": "Bad. The character's body structure in the video is abnormal, with issues in generating the hands, and there is a frame where the character has three legs."
}
] |
seed46_2442
|
videos/HRA_part2/2442.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic tiger, drenched in sunlight, strides into a serene pond, its striped coat shimmering against the clear water. Gracefully, it begins to swim, powerful paws propelling it forward, with droplets scattering from its body. The water's surface reflects the lush greenery surrounding the pond, creating a tranquil atmosphere as the tiger continues to paddle through the calm waters, highlighting its unexpected aquatic prowess.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2632
|
videos/HRA_part2/2632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, temperate shrubland during the golden hour, a capybara, the world's largest rodent, is seen running energetically across the landscape. The shrubland is dotted with various green shrubs and low-lying vegetation, providing a natural habitat for the capybara. The animal, with its brown fur and distinctive rodent features, bounds gracefully over the terrain, highlighting its agility and speed. As it moves, the capybara leaves a trail of displaced grass and dust, showcasing its vitality in this serene environment.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's running motion in the video is not smooth and coordinated."
}
] |
seed42_2428
|
videos/HRA_part0/2428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a small, slender green lizard with intricate patterns on its skin, perched on a dry, cracked earth surface under a clear blue sky. It licks its eye with its forked tongue, performing a natural behavior known as eye wiping, which helps keep its eyes clean. The scene is set outdoors, with the lizard's textured skin and the arid landscape providing a stark contrast against the vibrant blue sky in the background.]"
},
{
"from": "gpt",
"value": "Normal. The lizard's tongue generation in the video has issues."
}
] |
seed42_2091
|
videos/HRA_part0/2091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student wearing a gray sweater and black jeans sits in a classroom, wiping the surface of a large, advanced telescope with a cloth, as if preparing it for use. The room is dimly lit, with a projector screen displaying images of deep space in the background. The student's focus is intense, their actions deliberate, as they handle the telescope with care, its size and complexity suggesting it is used for serious astronomical research or communication. The overall scene conveys a sense of dedication and curiosity about the mysteries of the universe.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and undergo sudden changes."
}
] |
seed42_322
|
videos/HRA_part0/322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European brown hare is seen swimming across a serene, glassy lake, its ears perked up and alert. It moves gracefully through the water, showcasing its rarely-seen swimming ability. The hare's body, including its long legs and large hind feet, propels it forward as it navigates the calm lake surface. The scene is set against a lush green landscape, highlighting the unexpected yet captivating sight of a hare swimming.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2883
|
videos/HRA_part1/2883.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant scene unfolds as a talented musician, clad in a red fox-themed costume, plays a golden saxophone under the neon lights of a bustling city street. The fox's expressive face, complete with whiskers and gleaming eyes, comes alive as it dances energetically, captivating the crowd with its infectious rhythm. Surrounded by urban graffiti and the glow of city lights, the fox's movements are fluid and dynamic, its tail swaying in time with the music. The atmosphere is electric, with onlookers swaying to the beat, all drawn into the enchanting performance of this unique fox-musician.]"
},
{
"from": "gpt",
"value": "Normal. The musician wearing the fox costume has slightly unsmooth movements in the video."
}
] |
seed46_1564
|
videos/HRA_part2/1564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a white shirt and brown trousers, leads a llama on a leash through the verdant pathways of a zoological park, surrounded by lush greenery and exotic plants. The llama, adorned with a decorative blanket and colorful tassels, follows obediently as the farmer guides it past various enclosures housing different species. They walk alongside a water feature, such as a pond or stream, adding to the tranquil atmosphere of the park. The farmer's attire complements the natural surroundings, creating a harmonious scene as they navigate the scenic route together.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the legs are deformed, and the alpaca's legs are twisted."
}
] |
seed42_1245
|
videos/HRA_part0/1245.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, adorned in a red apron over a casual black t-shirt and dark jeans, skillfully chops fresh vegetables on a wooden cutting board in a vibrant kitchen filled with natural light. The room is alive with warm colors and modern decor, featuring a large window that lets in the afternoon sun. The musician, with short brown hair and a friendly smile, gracefully moves about the space, stirring a sizzling pan on a high-end stove, the aroma of a delicious meal blending with the upbeat tunes playing softly in the background. Moments later, they taste-test the simmering sauce, adjusting the seasoning with a practiced hand, all while the inviting glow of the kitchen enhances the cozy atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change, the knife in the person's hand suddenly turned into a spoon."
}
] |
seed44_1725
|
videos/HRA_part1/1725.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt and black pants, serves a dingo seated at a table set amidst dense green thickets. The dingo, wearing a red bandana, looks expectantly at the waiter, who holds a platter of food. Nearby, a swimming pool glistens under the sun, its clear blue water contrasting with the lush vegetation surrounding it. The waiter, with a friendly smile, places the dish before the dingo, who eagerly leans forward, creating a surreal yet charming tableau.]"
},
{
"from": "gpt",
"value": "Normal. The waiter in the video moves slowly, and the dingo's actions are not smooth."
}
] |
seed42_3023
|
videos/HRA_part0/3023.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a dark blue jacket over a gray shirt, and gray pants, stands in a taiga landscape marked by tall coniferous trees and a dense undergrowth of shrubs. Holding a towel in his right hand, he wipes his face, perhaps after a long day of work or physical exertion. The scene is set against the backdrop of the taiga, with the engineer's attire standing out against the natural greens and browns of the forest environment. The act of wiping his face with the towel conveys a sense of relief and respite in the midst of the rugged wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video, as well as the item they are holding."
}
] |
seed46_2857
|
videos/HRA_part2/2857.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant flamingo stands tall and proud on a sandy shore, its pink feathers glowing under the golden rays of the setting sun. Its long, slender legs elegantly support its body as it gazes out over the calm waters, creating a serene and picturesque scene. The flamingo's curved neck gracefully bends, while its beak rests gently on its chest, exuding a sense of tranquility and contentment. Surrounding palm trees sway gently in the breeze, adding to the idyllic atmosphere of this stunning coastal landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1828
|
videos/HRA_part2/1828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with graying hair, wearing a white blouse and glasses, meticulously irons clothes in a well-lit room. She starts by carefully smoothing out a white shirt with a hot iron, steam rising gently. Then, she moves on to press a pair of khaki pants, folding them neatly over the ironing board. Throughout, she maintains a focused demeanor, her glasses catching the light as she works diligently, the steam from the iron creating a serene, domestic atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The khaki pants suddenly started moving on their own. Human hands appeared deformed."
}
] |
seed42_3006
|
videos/HRA_part0/3006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green environment, a small brown mouse stands on the edge of a natural pool, surrounded by dense shrubbery and tall grass, creating an intricate network of thickets. The mouse looks intently at the water, its ears perked and body alert. Suddenly, it bravely leaps into the clear, shimmering pool, swimming with surprising agility, its tiny paws propelling it through the water. As it swims, the camera captures the ripples created by its movement, highlighting the contrast between the busy activity of the mouse and the stillness of the thickets surrounding the pool.]"
},
{
"from": "gpt",
"value": "Normal. The rat's movements are not smooth."
}
] |
seed44_1438
|
videos/HRA_part1/1438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a gray beanie, a dark jacket, and a checkered apron, stands against a vibrant blue wall, holding a large ladle as he stirs a bubbling pot. Moments later, he is seen attentively pouring oil into a pan, demonstrating culinary expertise. Then, he skillfully flips a food item in the pan, showcasing his cooking prowess, all while the blue wall and his attire remain consistent. Lastly, he is shown carefully seasoning the dish, his focus unwavering, against the same backdrop of the vivid blue wall and clad in the same attire, exemplifying his dedication to culinary artistry.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1133
|
videos/HRA_part2/1133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single dromedary camel, marked with dark spots, runs across a barren desert landscape under a hazy sky, its large, leathery feet kicking up puffs of sand with each stride. It wears a simple, rustic saddle adorned with red and white striped fabric, fluttering in the wind as the camel sprints. In the distance, the outlines of shrubs and distant mountains provide a sense of scale, emphasizing the vastness of the desert environment. The camel's powerful legs and muscular build are highlighted as it maintains its steady, fast pace through the sandy terrain.]"
},
{
"from": "gpt",
"value": "Normal. The limb proportions of the dromedary camel are not well-coordinated."
}
] |
seed44_2744
|
videos/HRA_part1/2744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dramatic scene unfolds as a sleek, black king cobra emerges from tall, dense grass, its hood partially spread. It races forward, muscles rippling under its shiny scales, demonstrating the surprising speed of these normally slow-moving serpents. The snake's eyes are intently focused ahead, suggesting a purposeful journey or a response to a nearby threat, all captured against a backdrop of lush, green foliage.]"
},
{
"from": "gpt",
"value": "Normal. The cobra in the video walks basically normally, but there is slight movement disharmony."
}
] |
seed44_2227
|
videos/HRA_part1/2227.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman with a charming smile, wearing a casual graphic T-shirt and dark jeans, is laughing joyously. Her laughter is contagious as she throws her head back, her wavy brown hair cascading down her shoulders. The scene is set in a cozy living room with wooden floors and a white couch, adding to the warm and intimate atmosphere. Her joyful expression, complete with closed eyes and a wide grin, radiates happiness, making the viewer feel like they're sharing in her delight.]"
},
{
"from": "gpt",
"value": "Bad. The character's face in the video is distorted."
}
] |
seed44_103
|
videos/HRA_part1/103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, donning a brown jacket and khaki pants, stands at a modern bus stop, gently caressing the sleek metal pole, seemingly finding comfort in its solid presence. His eyes are closed, lost in thought, as the urban landscape hums around him. The bus stop is designed with clean lines and glass panels, offering a glimpse into the daily life of the city. Passersby glance curiously at the engineer, his connection to the inanimate object a stark contrast to the hurried pace of the surroundings. The scene captures a rare moment of intimacy between a person and the urban infrastructure they interact with daily.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1042
|
videos/HRA_part1/1042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with graying hair tied in a ponytail engages in a fall activity, raking leaves in her spacious backyard. Dressed in a blue shirt, denim jacket, and brown gloves, she meticulously gathers the autumn foliage. The scene is set in late afternoon, as indicated by the soft, golden light filtering through the trees. She pauses to look up, her expression one of determination mixed with a sense of accomplishment, surrounded by piles of leaves and a red wheelbarrow nearby, emblematic of the season's chores and the beauty of nature's transition.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1517
|
videos/HRA_part2/1517.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charming hedgehog, adorned with a miniature top hat and a tiny bow tie, pirouettes gracefully on a wooden stage under the glow of a spotlight. The hedgehog's expressive eyes sparkle with joy as it twirls, its quills gently swaying to an unheard melody. The backdrop features a painted night sky, complete with twinkling stars and a crescent moon, adding a whimsical touch to the scene. The hedgehog continues its delightful dance, captivating the audience with its unexpected grace and charm, all set against the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1991
|
videos/HRA_part2/1991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a lush, verdant savanna under a vast, cloud-dappled sky, a graceful antelope leaps and bounds with an almost choreographed elegance, its movements fluid and dynamic against the backdrop of swaying grasses and distant acacia silhouettes. Its coat gleams golden in the warm sunlight, and its horns curve beautifully as it executes a series of leaps that seem to defy gravity, embodying the spirit of dance in the wild. Nearby, a small herd of antelope watches, their postures attentive and curious, creating a scene that is both captivating and enchantingly serene.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's movements in the video are not smooth."
}
] |
seed44_1383
|
videos/HRA_part1/1383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A musician, dressed in a black jacket and black jeans, is seen in a dimly lit room with a red background, wiping down a hyena that is sitting calmly on a table. The hyena, which has distinctive markings and a serious expression, is being carefully tended to by the musician, who uses a soft cloth to clean its fur. The scene conveys a sense of care and attention to detail, with the musician's focused gaze and gentle movements highlighting the bond between the two beings. Despite the unusual pairing, there is a palpable sense of trust and mutual respect between the musician and the hyena, making for a captivating and intriguing visual.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1006
|
videos/HRA_part2/1006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a police officer, clad in a navy uniform with a badge, cap, and sunglasses, interacts with a large brown teddy bear outside a row of shops, which include a bakery, a bookstore, and a clothing store, each with colorful awnings and signs. The officer gently lifts the stuffed animal, which is nearly as big as him, into the air. Nearby, a group of children watch in awe, sitting cross-legged on the sidewalk, their faces alight with wonder and joy. The officer then crawls on his hands and knees next to the bear, playfully engaging with the delighted kids, creating a heartwarming moment of connection between law enforcement and the community, all against the backdrop of a bustling street lined with charming stores.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands and legs are deformed, and the bear is also distorted."
}
] |
seed44_2279
|
videos/HRA_part1/2279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket, beige trousers, and a wide-brimmed hat, dances jovially in a mountainous landscape, the distant peaks shrouded in mist. A deer, with a full rack of antlers and a curious gaze, watches him from the edge of a lush forest. The farmer's movements are lively and carefree, his arms raised in the air, as if celebrating the beauty of nature that surrounds him. The deer, sensing no threat, cautiously approaches, its ears perked, adding a touch of whimsy to the scene. The mountains loom majestically in the background, their slopes dotted with trees and patches of greenery, providing a stunning natural backdrop to this unexpected dance.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's face, hands, and feet in the video are generated abnormally, with the farmer's hands and feet suddenly disappearing or appearing in the middle frames."
}
] |
seed46_1619
|
videos/HRA_part2/1619.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hardworking window cleaner, clad in a yellow high-visibility vest and dark pants, expertly maneuvers a squeegee across a large glass pane on a bright day. With a secure harness and helmet protecting him, he focuses intently on his task, ensuring crystal clear results. Perched on a platform lifted by a cherry picker, he cleans the exterior of a modern office building, the city skyline visible in the distance. As he moves, his confident posture and steady hand reveal his skill and dedication to leaving each window spotless.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1381
|
videos/HRA_part0/1381.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair, styled in a pixie cut, sits serenely on a yoga mat placed atop a wooden floor, set within a minimalistic room illuminated by soft, natural light. She wears a black tank top and gray yoga pants, her eyes gently closed as she focuses on her breathing. Her hands rest gracefully on her knees, adorned with a silver ring and bracelet, while a single earring dangles from her left ear. The atmosphere is calm and peaceful, with a potted plant and a water bottle visible in the background, hinting at her wellness routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2455
|
videos/HRA_part0/2455.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bearded man, wearing a black cap, glasses, and a gray shirt, sits at a wooden table under a dimly lit lamp, intently sketching with a pencil in his right hand on a large sheet of paper. Musical instruments, including a guitar, a violin, and a trumpet, are visible in the background, indicating his passion for music. The focus is on the musician's face and hands as he draws, capturing his creative process in a room filled with musical equipment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2172
|
videos/HRA_part2/2172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a live clam lying half-open on a bed of damp sand, revealing its intricate interior textures and colors. The clam's exterior is rugged and brownish-black, while the interior showcases a lustrous, pearly surface. The sandy substrate is speckled with small stones and shells, adding to the natural coastal environment. Sunlight filters through the water, casting a soft glow on the scene, highlighting the clam's delicate features and the surrounding grains of sand.]"
},
{
"from": "gpt",
"value": "Normal. The clams in the video have no movement."
}
] |
seed44_1174
|
videos/HRA_part1/1174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a dark green shirt and khaki pants, is seen wiping a wet floor with a mop, leaving behind a clean, glistening surface. Beside him, a small, fluffy white dog, possibly a Bichon Frise, looks up with curious brown eyes. The janitor pauses, resting the mop against a wall covered with inspirational posters and a fire extinguisher, before bending down to interact with the dog, who eagerly responds with a wagging tail and playful energy, creating a heartwarming moment in an otherwise mundane setting.]"
},
{
"from": "gpt",
"value": "Bad. Only one arm and hand were generated, and the mop handle sometimes detaches from the person's hand. Additionally, the person's hand becomes deformed."
}
] |
seed42_1545
|
videos/HRA_part0/1545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray shirt and khaki pants is seen in a whimsical scene, holding a small mouse on a wheel that matches the color of his shirt. The wheel rotates rapidly as the man watches, his gaze fixed on the active rodent. The scene is set against a plain, white backdrop, with the man's casual attire and focused expression contrasting with the unusual sight of the mouse energetically running on the miniature wheel.]"
},
{
"from": "gpt",
"value": "Bad. The rat's running in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed42_2419
|
videos/HRA_part0/2419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 leather jacket, blue shirt, and jeans, stands against a background of lush vegetation and distant mountains. His eyes are fixed on a graceful gazelle as it bounds across the terrain. The gazelle, exhibiting a display of speed and agility, leaps over shrubbery in the foreground, its movement captured in slow motion. The director, now holding a megaphone, directs the action, his gaze following the gazelle's path through the wilderness. Finally, the gazelle continues its run, moving away from the director and into the vast landscape, embodying freedom and beauty in motion.]"
},
{
"from": "gpt",
"value": "Bad. The video shows abnormal generation of the antelope's head and limbs, with the legs of the antelope in the middle frames being twisted and deformed."
}
] |
seed46_3082
|
videos/HRA_part2/3082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery illuminated by soft purple lighting, a distinguished doctor, wearing a crisp white lab coat over a button-down shirt and slacks, meticulously wipes an ancient relic. The artifact, seemingly made of obsidian, is displayed on a sleek, metallic pedestal amidst avant-garde artworks floating in zero gravity. The doctor's focused gaze and careful handling emphasize the significance of the object, while the surrounding art pieces, including abstract sculptures and vibrant paintings, add a touch of cultural richness to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's movements are not smooth."
}
] |
seed42_2973
|
videos/HRA_part0/2973.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quiet suburban neighborhood, two young boys stand side by side, wearing casual clothes; one in a gray t-shirt and denim shorts, the other in a red shirt and khaki shorts. They are positioned against a backdrop of a white-painted wooden fence, with lush green bushes visible beyond. The boy in gray has his left foot raised, while the other boy leans forward, both engaged in a playful interaction. Their stance and attire are typical of summertime leisure, capturing a candid moment of childhood camaraderie against a backdrop of a sunny day.]"
},
{
"from": "gpt",
"value": "Bad. The boy's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_1292
|
videos/HRA_part0/1292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom setting, a teacher, dressed in a yellow sweater and blue jeans, is depicted mid-jump, leaping over a stuffed weasel mascot that is sitting on a desk. The mascot is wearing a small graduation cap and holding a book, adding to the playful atmosphere. The teacher's jump is energetic and joyful, conveying a sense of fun and engagement in the educational environment. The scene is brightly lit, capturing the dynamic action and the expressions of delight on the faces of the students watching in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2913
|
videos/HRA_part0/2913.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and black tactical gear, is seen in a residential backyard with green grass and trees in the background. He kneels beside a golden retriever, gently washing it with a hose and a sponge. The dog, wearing a red collar, happily shakes off water, splashing the officer who laughs good-naturedly. The scene conveys a heartwarming moment of care and connection between the officer and the dog, set against a backdrop of blue skies and lush greenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1389
|
videos/HRA_part0/1389.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a compassionate nurse, clad in a blue uniform and wearing a stethoscope around her neck, leaps with exhilaration against a cosmic backdrop featuring an artist's impression of a recently discovered exoplanet. Simultaneously, a cobra, coiled and ready to strike, mimics the action of jumping, adding an unexpected element to the scene. Both figures, the nurse and the cobra, are captured mid-leap, their silhouettes outlined against the star-studded universe, creating a vivid contrast between human emotion and the raw power of nature, all set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's jumping action in the video is basically normal, with slight disharmony."
}
] |
seed46_3091
|
videos/HRA_part2/3091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man sits at a desk, bathed in the warm glow of a table lamp, surrounded by books and papers. He is wearing a gray t-shirt and dark glasses, and has a full beard. He yawns widely, stretching his arms above his head, showing signs of fatigue. His computer screen reflects the light, partially obscuring his face, as he leans back in his chair, the room's atmosphere conveying a sense of late-night writing and contemplation.]"
},
{
"from": "gpt",
"value": "Normal. The yawning action of the character in the video is slightly unsmooth."
}
] |
seed44_241
|
videos/HRA_part1/241.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a tropical dry forest, golden light filters through the canopy, spotlighting a graceful gazelle. It prances and leaps in an open glade, its movements almost choreographed, as if dancing to an unheard melody. The gazelle, adorned with a shimmering gold collar that catches the sunlight, seems to perform for an audience of lush greenery and scattered wildflowers. Its elegant leaps and bounds are mirrored by the swaying branches above, creating a harmonious dance between predator and prey, all set against the vibrant backdrop of the dry forest's flora.]"
},
{
"from": "gpt",
"value": "Bad. The golden collar mentioned in the caption does not appear in the video."
}
] |
seed42_1210
|
videos/HRA_part0/1210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college-aged student, wearing a yellow rubber glove on their left hand and a look of determination, scrubs the white tiles of a bathroom shower stall with a green scrub brush. The bathroom has a modern design with stainless steel fixtures. The student, dressed in blue jeans, a gray t-shirt, and sneakers, leans into their task with focused energy. In another angle, the student continues scrubbing the tiles, now revealed to be in a dorm room bathroom, with a shower curtain featuring a geometric pattern in the background. The student's dedication to cleaning is evident in their posture and the intensity of their scrubbing motion.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated."
}
] |
seed46_233
|
videos/HRA_part2/233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a plaid shirt, denim overalls, and a worn baseball cap, stands in a modern kitchen. He methodically unloads a sleek, stainless steel dishwasher, handling each plate and utensil with unexpected gentleness. The contrast between his calloused hands and the shiny, clean dishes highlights the unusual domestic task for someone more accustomed to farm chores. The kitchen is spacious and well-lit, featuring granite countertops and contemporary appliances, offering a glimpse into the farmer's home life beyond the fields.]"
},
{
"from": "gpt",
"value": "Bad. The faces, hands, arms, and items like plates are distorted in the video."
}
] |
seed44_2546
|
videos/HRA_part1/2546.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer with short, dark hair and a neatly trimmed beard stands on a wooden chair, set atop a checkered floor, inside a rustic barn illuminated by soft, warm lighting. Dressed in a plaid shirt, blue jeans, and a brown vest, he reaches up to change a light bulb, his face reflecting concentration. The barn's wooden structure, adorned with tools and equipment, provides a backdrop for this everyday task, highlighting the farmer's practical skills and the cozy, well-lit interior of the barn.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the farmer extending his arms to change the light bulb, but the movements are not continuous and smooth."
}
] |
seed46_1208
|
videos/HRA_part2/1208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a meticulously crafted aquarium filled with vibrant green aquatic plants, a ghost shrimp, nearly transparent with faint blue-gray veins, clings to a piece of driftwood. Its delicate antennae wave gently in the water current, and its legs grip the wood securely. Nearby, a stone arch adds to the scenery, while the shrimp's see-through body allows a glimpse of its internal organs. The shrimp's translucent exoskeleton and the lush underwater environment create a captivating scene, enhanced by the play of light and shadow in the tank.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2065
|
videos/HRA_part0/2065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a warm, sandy landscape under a clear blue sky, a woman wearing a flowing, cream-colored robe gently caresses a kneeling camel adorned with ornate saddles and blankets. The scene captures the tender bond between the woman and the camel, with her hand softly stroking its head. The woman's attire complements the desert environment, and her gentle touch conveys a sense of care and connection. Nearby, more camels stand, their presence adding to the serene atmosphere of the desert setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2195
|
videos/HRA_part0/2195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush, temperate deciduous forest during autumn, a dedicated park ranger wearing a brown uniform and a wide-brimmed hat runs along a winding dirt trail. Surrounded by tall, leafy trees with vibrant orange and red foliage, the ranger navigates the path with focused determination. As the camera follows, we see the ranger's strong legs propelling them forward, their breath visible in the crisp air, and their eyes alert for any signs of wildlife or forest health issues. The scenery is alive with the sounds of rustling leaves, chirping birds, and the occasional distant call of a wild animal, all contributing to the immersive experience of running in a breathtaking natural environment.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video has a twisted body, twisted feet, twisted legs, and twisted arms."
}
] |
seed42_2723
|
videos/HRA_part0/2723.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a blue medical uniform, pauses in a hospital room to appreciate a vibrant painting hanging on the wall. The artwork depicts a lush forest landscape, filled with shades of green, brown, and blue, evoking a sense of peace and tranquility. Sunlight filters through the painted trees, casting a warm glow on the nurse's face as she stands beside a patient's bed, momentarily lost in the serene scene before her. The contrast between the sterile hospital environment and the natural beauty of the painting highlights the nurse's ability to find moments of calm amidst the demands of her profession.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1028
|
videos/HRA_part2/1028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut, clad in a white spacesuit adorned with the American flag, embarks on a spacewalk to repair a satellite. Holding a specialized tool in one hand and a cleaning wipe in the other, they meticulously clean a solar panel against the backdrop of Earth, visible in the distance. The astronaut's gloved hands carefully grip the cleaning wipe as they perform maintenance tasks, ensuring the satellite's functionality. Throughout the spacewalk, the vastness of space surrounds the astronaut, highlighting the isolation and importance of their mission to repair critical equipment orbiting the planet.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth."
}
] |
seed42_2024
|
videos/HRA_part0/2024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled female student sits cross-legged on a clean, white surface, diligently hemming a pair of black pants with a focused expression. She wears a grey cardigan over a white collared shirt and blue jeans, her attire casual yet neat. The environment is bright and minimalistic, with ample natural light illuminating her task. Tools of her activity, such as scissors, thread, and a needle, are neatly arranged within reach, highlighting her attention to detail and organization. The scene captures her absorbed in the sewing process, her hands skillfully manipulating the fabric, demonstrating a blend of practical skill and academic studiousness.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers and legs are missing in the video, and the scissors, needles, and threads are deformed."
}
] |
seed46_1642
|
videos/HRA_part2/1642.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in a brown jacket and beige pants is seen crawling on his hands and knees through a lush, green forest, with ferns and mossy rocks surrounding him. Moments later, a large moose with a majestic rack of antlers stands tall and vigilant nearby, observing the man's unusual behavior. The scene then focuses on the man's face, showing his determination and focus, while the moose continues to watch from a distance, its presence adding a sense of wildness and unpredictability to the forest setting. Finally, the man and the moose share a silent moment of connection, both existing in harmony within the natural world, the man still crawling and the moose standing tall, creating a unique and unexpected encounter in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_3111
|
videos/HRA_part1/3111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray sweater and blue jeans, steps out from a charming cottage, holding a small trash bag. She walks purposefully down a stone path, surrounded by lush greenery and flowers, to reach a large wooden bin. The scene is set in the golden hour, with soft sunlight filtering through the trees, casting a warm glow on the idyllic setting. The writer pauses for a moment, looking contemplative, before depositing the trash bag into the bin. The peaceful atmosphere and natural beauty of the surroundings provide the perfect backdrop for her daily routine, offering a glimpse into the simple yet meaningful moments in the life of an artist.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3058
|
videos/HRA_part0/3058.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious monkey, dressed in a red life jacket, sits on a wooden pier extending over a serene body of water, surrounded by lush greenery and tall trees. The monkey then playfully jumps into the clear blue water, creating ripples that spread outward. It swims energetically, its small arms paddling through the water, while a pair of sunglasses float nearby, adding a touch of whimsy to the scene. The monkey eventually climbs back onto the pier, shaking off droplets of water, with the sun casting a warm glow over the entire setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2277
|
videos/HRA_part0/2277.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest, blue jeans, and a gray shirt, sits on a wooden beam high above the city skyline, nodding thoughtfully as he listens to his supervisor's instructions. His hard hat is resting beside him, and he holds a water bottle in one hand, pausing from his labor under the clear blue sky. The bustling cityscape, complete with skyscrapers and moving cars, provides a dynamic backdrop to his momentary break. His facial expression conveys attentiveness and understanding, emphasizing the importance of communication in his line of work.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.