Comparison of 3 Models: "うちしめり 菖蒲(あやめ)ぞかをる ほととぎす 鳴くや五月(さつき)の 雨の夕暮れ"(New Collection of Ancient and Modern Japanese Poems)
tare_koala
122 Followers·616 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.
I will compare the images of the waka poems I previously created on the theme of the rainy season (https://www.aipictors.com/posts/745978) by obtaining the prompts that GPT sent to the endpoint. left: fal-ai/flux-2-pro, image_size: 1532x1024, 17.524078s, $0.045 center: fal-ai/nano-banana-2, image_size: 1264x868, 10.653461s, $0.08 right: fal-ai/gpt-image-2, image_size: 1536x1024, 41.607174s, $0.0426 In my opinion, the results are more similar than I expected, but I think Flux.2[pro] excels at presentation (enhancing the image to look cool), NanoBanana2 is natural (not enhancing the image), and GPT2 conveys emotion (enhancing the image with feeling), and I think it really captured the model's personality. How do your impressions compare?
AI evaluation
Great
Strong consistencyStrong beauty
AI
霧に包まれた水辺の風景は、静寂と儚さを湛えた一幅の詩のよう。夕陽の残光が水面に揺らめき、紫菖蒲と小鳥の佇まいが静かな物語を紡ぎ出している。構図の層次と光の扱いは巧みであるが、全体の調和にやや単調さを感じる点も否めない。

