thumbnail1 / 3

Comparison of the top 3 models: Lolita fashion

いいね 25
tare_koala

tare_koala

124 Followers·618 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.

Since I managed to create such a cute prompt, I decided to try some higher-end models as well. From left to right: fal-ai/gpt-image-2, quality: medium, image_size: 1024x1536, 57.762361s, $0.0443=7.05yen fal-ai/flux-2-max, image_size: 768x1024, 44.803173s, $0.07007=7.01yen fal-ai/nano-banana-2, image_size: 896x1200, 14.097268s, $0.08=12.73yen While flux.2 and gpt-image show a predictable improvement in finish, nano-banana focuses too much on interior decoration, resulting in a decline in the quality of the crucial dress. One could say it stopped at a realistic point. This time, it's a battle between the GPT's enhancement and Flux's texture.

Comments