Offering a Java Sparrow
tare_koala
122 Followers·617 Posts
I'm writing prompts to generate accurate and precise (and hopefully even cuter) models of Japanese women's uniforms and attire. These are generally publicly available, so please feel free to take them (at your own risk). Be aware that many are long models for the latest styles. Compliments on my posts are welcome, as are any opinions or questions. *I don't dislike R15 content, but it's not my main purpose. I mute accounts with many images of underwear, large breasts, or extreme swimsuits, and in severe cases, I block them. Thank you for your understanding.
[Story] Kaori has brought a Java Sparrow—donated by a pet shop located near the shopping street by the shrine—to the front of the main hall, intending to present it to the enshrined deity, Hi-miko-sama. A reporter from the local *Hi-shin Nippo* (Sun-God Daily News) captured this scene from within the shrine grounds using a telephoto lens. [Explanation] Simply showing someone looking at a bird in a cage is a bit too mundane, so I set up a more complex scenario: capturing Kaori standing in the sacred space in front of the main hall, as seen through a telephoto lens from elsewhere on the shrine grounds. Including an overhead view of the shrine grounds (the second image) was essential; this, combined with the details of Kaori’s character profile (the third image), allowed for a perfect depiction of the shrine’s architecture. It’s clear that current generative AI models, when provided with the right information, can even grasp and render the spatial relationships between buildings. Overhead shots of building layouts are quite useful. I spent two "low-quality" generation attempts to refine the perspective from within the shrine grounds, and three "medium-quality" attempts to get the right shot of her looking toward the hall. Before arriving at the overhead shot, I had already used about eight additional attempts (a mix of low and medium quality). [Generation Info] https://openart.ai/suite/create-image/gpt-image-2-5, GPT Image 2.5 Sunburst, 2:3, Quality: medium, 1024x1536, $0.0471 = 7.39 JPY/image
AI evaluation
Great
Strong detailStrong consistency
Pictor-chan
わーい!ぴくたーちゃんだよ〜♪ この巫女さん姿がとっても美しいね!赤と白の衣装の色合いが鮮やかで82点、背景の神社や木々のディテールも細かくて85点だよ!構図のバランスも80点で素敵♪ 全体的に75点…

