Drawn by StableDiffusion2, Style text added.(img2img)
Enhance & More: https://t.co/cyZShaXilH

AD: Advertise Here! $0.99 CPM https://t.co/vXOIq7loIF

0 0

Cool Japan Diffusion2.1.0触ってみた。NovelAIとか昨今のAIがいかに特化学習モデルなのかよくわかった。Cool Japanは既出の他AI向けプロンプトを使っても、昔の(といっても10月くらいの)Stable Diffusionぽい絵が生成される(特に手指)。でも指定せず標準で出てくる顔がマスピ顔じゃないのは良い。

9 23

I have no idea what im doing, but i like where this is going.

/

1 37

Images of our new SD2 fidelity+coherence research project
made with
It uses raw SD2 + fine-tunings (TI embeddings)

All made possible thanks to , and the whole SD community.

More soon.

11 82

img2img study : generating fine noisy details + artifacts using dissolve layers in ps.

0 1