THIS MODEL IS DEPRECATED
Please use WoopWoop-General instead.
A model trained to make detailed, anatomically-accurate (hands, faces, genitals, etc) illustrations of humans and non-humans alike. This is the model aiming at anime/hentai styling. Trained to require few negative prompts (see examples). For the photographic variant, see here.
Suggested style prompt: ((photograph, photographic photo, photogenic, rule of thirds, hentai, anime, illustration))
I highly suggest using vae-ft-mse-840000-ema-pruned.ckpt with this version.
Easy Launch on Vast.AI:
Follow this guide on how to launch Stable Diffusion on Vast.AI, except where it says to put "/start.sh" in as the on-start script, instead copy/paste in the contents of this file instead.
Description
More natural poses, depth of features
Better rendering of eyes
WAY fewer negative prompts required (see examples)
More natural facial expressions
Split Anime and Dreamscape models out into separate published files
Now works wonderfully as a slim, fp16 model!