More Cuties

moreCuties_anythingV3.safetensors

Anything v3 & woopanimehentai_11

THIS MODEL IS DEPRECATEDPlease 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 <a target="_blank" rel="ugc" href="https://civarchive.com/models/4041/woopwoop-photo">here</a>. 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 <a target="_blank" rel="ugc" href="http://Vast.AI">Vast.AI</a>: Follow <a target="_blank" rel="ugc" href="https://docs.vast.ai/guides/stable-diffusion">this guide</a> on how to launch Stable Diffusion on <a target="_blank" rel="ugc" href="http://Vast.AI">Vast.AI</a>, except where it says to put "/<a target="_blank" rel="ugc" href="http://start.sh">start.sh</a>" in as the on-start script, instead copy/paste in the contents of <a target="_blank" rel="ugc" href="https://gist.githubusercontent.com/zoidbb/3750efecbfb58662f31263fb51e33119/raw/77d9f63a967bece7a505a10b3f8ca161af8e851d/gistfile1.txt">this file</a> instead.

WoopWoop-Anime/Hentai

<ul><li>More natural poses, depth of features</li><li>Better rendering of eyes</li><li>WAY fewer negative prompts required (see examples)</li><li>More natural facial expressions</li><li>Split Anime and Dreamscape models out into separate published files</li><li>Now works wonderfully as a slim, fp16 model!</li></ul>

Files with SHA256: a7d6e49c19e72197ea4b8e478d4f78d9bd75c16337e5494c581e7fb4e6e313ac